diff --git "a/auto_diffusers.log" "b/auto_diffusers.log" new file mode 100644--- /dev/null +++ "b/auto_diffusers.log" @@ -0,0 +1,1334 @@ +2025-05-29 14:50:28,409 - __main__ - INFO - Initializing GradioAutodiffusers +2025-05-29 14:50:28,409 - __main__ - DEBUG - API key found, length: 39 +2025-05-29 14:50:28,409 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator +2025-05-29 14:50:28,409 - auto_diffusers - DEBUG - API key length: 39 +2025-05-29 14:50:28,409 - auto_diffusers - INFO - Successfully configured Gemini AI model +2025-05-29 14:50:28,409 - hardware_detector - INFO - Initializing HardwareDetector +2025-05-29 14:50:28,409 - hardware_detector - DEBUG - Starting system hardware detection +2025-05-29 14:50:28,409 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64 +2025-05-29 14:50:28,409 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11 +2025-05-29 14:50:28,409 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi +2025-05-29 14:50:28,413 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected +2025-05-29 14:50:28,413 - hardware_detector - DEBUG - Checking PyTorch availability +2025-05-29 14:50:28,856 - hardware_detector - INFO - PyTorch 2.7.0 detected +2025-05-29 14:50:28,856 - hardware_detector - DEBUG - CUDA available: False, MPS available: True +2025-05-29 14:50:28,856 - hardware_detector - INFO - Hardware detection completed successfully +2025-05-29 14:50:28,856 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'} +2025-05-29 14:50:28,856 - auto_diffusers - INFO - Hardware detector initialized successfully +2025-05-29 14:50:28,856 - __main__ - INFO - AutoDiffusersGenerator initialized successfully +2025-05-29 14:50:28,856 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator +2025-05-29 14:50:28,856 - simple_memory_calculator - DEBUG - HuggingFace API initialized +2025-05-29 14:50:28,856 - __main__ - ERROR - Failed to initialize SimpleMemoryCalculator: 'SimpleMemoryCalculator' object has no attribute 'known_models' +2025-05-29 14:52:16,109 - __main__ - INFO - Initializing GradioAutodiffusers +2025-05-29 14:52:16,109 - __main__ - DEBUG - API key found, length: 39 +2025-05-29 14:52:16,109 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator +2025-05-29 14:52:16,109 - auto_diffusers - DEBUG - API key length: 39 +2025-05-29 14:52:16,109 - auto_diffusers - INFO - Successfully configured Gemini AI model +2025-05-29 14:52:16,109 - hardware_detector - INFO - Initializing HardwareDetector +2025-05-29 14:52:16,109 - hardware_detector - DEBUG - Starting system hardware detection +2025-05-29 14:52:16,109 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64 +2025-05-29 14:52:16,109 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11 +2025-05-29 14:52:16,109 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi +2025-05-29 14:52:16,113 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected +2025-05-29 14:52:16,113 - hardware_detector - DEBUG - Checking PyTorch availability +2025-05-29 14:52:16,551 - hardware_detector - INFO - PyTorch 2.7.0 detected +2025-05-29 14:52:16,551 - hardware_detector - DEBUG - CUDA available: False, MPS available: True +2025-05-29 14:52:16,551 - hardware_detector - INFO - Hardware detection completed successfully +2025-05-29 14:52:16,551 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'} +2025-05-29 14:52:16,551 - auto_diffusers - INFO - Hardware detector initialized successfully +2025-05-29 14:52:16,551 - __main__ - INFO - AutoDiffusersGenerator initialized successfully +2025-05-29 14:52:16,551 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator +2025-05-29 14:52:16,551 - simple_memory_calculator - DEBUG - HuggingFace API initialized +2025-05-29 14:52:16,551 - simple_memory_calculator - DEBUG - Known models in database: 4 +2025-05-29 14:52:16,551 - __main__ - INFO - SimpleMemoryCalculator initialized successfully +2025-05-29 14:52:16,551 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7 +2025-05-29 14:52:16,553 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 14:52:16,566 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None +2025-05-29 14:52:16,572 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 14:52:16,648 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 14:52:16,683 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None +2025-05-29 14:52:16,684 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 14:52:16,684 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 14:52:16,684 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 14:52:16,684 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 14:52:16,684 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 05:52:16 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')]) +2025-05-29 14:52:16,685 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 14:52:16,685 - httpcore.connection - DEBUG - close.started +2025-05-29 14:52:16,685 - httpcore.connection - DEBUG - close.complete +2025-05-29 14:52:16,686 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None +2025-05-29 14:52:16,686 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 14:52:16,686 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 14:52:16,686 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 14:52:16,686 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 14:52:16,686 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 14:52:16,686 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 14:52:16,692 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 05:52:16 GMT'), (b'server', b'uvicorn'), (b'content-length', b'73070'), (b'content-type', b'text/html; charset=utf-8')]) +2025-05-29 14:52:16,692 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2025-05-29 14:52:16,692 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 14:52:16,692 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 14:52:16,692 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 14:52:16,692 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 14:52:16,692 - httpcore.connection - DEBUG - close.started +2025-05-29 14:52:16,692 - httpcore.connection - DEBUG - close.complete +2025-05-29 14:52:16,703 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None +2025-05-29 14:52:16,842 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 14:52:16,842 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=3 +2025-05-29 14:52:16,852 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0 +2025-05-29 14:52:16,861 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 14:52:16,861 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=30 +2025-05-29 14:52:17,179 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 14:52:17,179 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 14:52:17,180 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 14:52:17,180 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 14:52:17,180 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 14:52:17,180 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 14:52:17,182 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 14:52:17,182 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 14:52:17,182 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 14:52:17,182 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 14:52:17,183 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 14:52:17,183 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 14:52:17,340 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 05:52:17 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')]) +2025-05-29 14:52:17,340 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK" +2025-05-29 14:52:17,340 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 14:52:17,340 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 14:52:17,340 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 14:52:17,340 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 14:52:17,340 - httpcore.connection - DEBUG - close.started +2025-05-29 14:52:17,340 - httpcore.connection - DEBUG - close.complete +2025-05-29 14:52:17,354 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 05:52:17 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')]) +2025-05-29 14:52:17,355 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2025-05-29 14:52:17,355 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 14:52:17,355 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 14:52:17,355 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 14:52:17,355 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 14:52:17,355 - httpcore.connection - DEBUG - close.started +2025-05-29 14:52:17,355 - httpcore.connection - DEBUG - close.complete +2025-05-29 14:52:18,360 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 14:52:18,573 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0 +2025-05-29 15:59:34,212 - __main__ - INFO - Initializing GradioAutodiffusers +2025-05-29 15:59:34,212 - __main__ - DEBUG - API key found, length: 39 +2025-05-29 15:59:34,212 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator +2025-05-29 15:59:34,212 - auto_diffusers - DEBUG - API key length: 39 +2025-05-29 15:59:34,212 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools +2025-05-29 15:59:34,212 - hardware_detector - INFO - Initializing HardwareDetector +2025-05-29 15:59:34,212 - hardware_detector - DEBUG - Starting system hardware detection +2025-05-29 15:59:34,212 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64 +2025-05-29 15:59:34,212 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11 +2025-05-29 15:59:34,212 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi +2025-05-29 15:59:34,216 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected +2025-05-29 15:59:34,216 - hardware_detector - DEBUG - Checking PyTorch availability +2025-05-29 15:59:34,645 - hardware_detector - INFO - PyTorch 2.7.0 detected +2025-05-29 15:59:34,646 - hardware_detector - DEBUG - CUDA available: False, MPS available: True +2025-05-29 15:59:34,646 - hardware_detector - INFO - Hardware detection completed successfully +2025-05-29 15:59:34,646 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'} +2025-05-29 15:59:34,646 - auto_diffusers - INFO - Hardware detector initialized successfully +2025-05-29 15:59:34,646 - __main__ - INFO - AutoDiffusersGenerator initialized successfully +2025-05-29 15:59:34,646 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator +2025-05-29 15:59:34,646 - simple_memory_calculator - DEBUG - HuggingFace API initialized +2025-05-29 15:59:34,646 - simple_memory_calculator - DEBUG - Known models in database: 4 +2025-05-29 15:59:34,646 - __main__ - INFO - SimpleMemoryCalculator initialized successfully +2025-05-29 15:59:34,646 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7 +2025-05-29 15:59:34,648 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 15:59:34,661 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None +2025-05-29 15:59:34,667 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 15:59:34,749 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 15:59:34,784 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None +2025-05-29 15:59:34,785 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 06:59:34 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')]) +2025-05-29 15:59:34,786 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2025-05-29 15:59:34,786 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 15:59:34,786 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 15:59:34,786 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 15:59:34,786 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 15:59:34,786 - httpcore.connection - DEBUG - close.started +2025-05-29 15:59:34,786 - httpcore.connection - DEBUG - close.complete +2025-05-29 15:59:34,786 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None +2025-05-29 15:59:34,787 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 15:59:34,787 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 15:59:34,787 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 15:59:34,787 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 15:59:34,787 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 15:59:34,787 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 15:59:34,792 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 06:59:34 GMT'), (b'server', b'uvicorn'), (b'content-length', b'73058'), (b'content-type', b'text/html; charset=utf-8')]) +2025-05-29 15:59:34,792 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2025-05-29 15:59:34,792 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 15:59:34,792 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 15:59:34,792 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 15:59:34,792 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 15:59:34,793 - httpcore.connection - DEBUG - close.started +2025-05-29 15:59:34,793 - httpcore.connection - DEBUG - close.complete +2025-05-29 15:59:34,803 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None +2025-05-29 15:59:34,825 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 15:59:34,825 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=3 +2025-05-29 15:59:34,940 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 15:59:34,940 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=30 +2025-05-29 15:59:34,971 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0 +2025-05-29 15:59:35,099 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 15:59:35,099 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 15:59:35,100 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 15:59:35,100 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 15:59:35,100 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 15:59:35,100 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 15:59:35,222 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 15:59:35,222 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 15:59:35,223 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 15:59:35,223 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 15:59:35,223 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 15:59:35,223 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 15:59:35,237 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 06:59:35 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')]) +2025-05-29 15:59:35,238 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2025-05-29 15:59:35,238 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 15:59:35,238 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 15:59:35,238 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 15:59:35,238 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 15:59:35,238 - httpcore.connection - DEBUG - close.started +2025-05-29 15:59:35,239 - httpcore.connection - DEBUG - close.complete +2025-05-29 15:59:35,362 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 06:59:35 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')]) +2025-05-29 15:59:35,363 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK" +2025-05-29 15:59:35,363 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 15:59:35,364 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 15:59:35,364 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 15:59:35,364 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 15:59:35,365 - httpcore.connection - DEBUG - close.started +2025-05-29 15:59:35,365 - httpcore.connection - DEBUG - close.complete +2025-05-29 15:59:36,012 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 15:59:36,260 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0 +2025-05-29 16:02:12,960 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:12,961 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:12,961 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0} +2025-05-29 16:02:12,961 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM +2025-05-29 16:02:12,961 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:12,962 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:12,962 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:02:12,962 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:12,962 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:32,785 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:32,785 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:32,785 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM +2025-05-29 16:02:32,785 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:32,785 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:32,786 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:02:32,786 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:32,786 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:47,460 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:47,460 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:47,460 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM +2025-05-29 16:02:47,460 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:47,460 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:47,460 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:02:47,460 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:47,460 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,300 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,300 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,300 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:02:52,300 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,300 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,300 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:02:52,300 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,300 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,452 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,452 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,452 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:02:52,452 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,452 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,452 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:02:52,452 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:52,452 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:54,804 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:54,804 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:54,804 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:02:54,804 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:54,804 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:54,804 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:02:54,804 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:54,804 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:54,804 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4 +2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True +2025-05-29 16:02:54,804 - auto_diffusers - INFO - Using manual hardware specifications +2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': [{'name': 'RTX 5090', 'memory_mb': 32768}]} +2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - GPU detected with 32.0 GB VRAM +2025-05-29 16:02:54,804 - auto_diffusers - INFO - Selected optimization profile: performance +2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API +2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - Prompt length: 3456 characters +2025-05-29 16:02:54,804 - auto_diffusers - INFO - Sending request to Gemini API with tool calling enabled +2025-05-29 16:03:10,966 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used) +2025-05-29 16:03:10,966 - auto_diffusers - DEBUG - Response length: 1710 characters +2025-05-29 16:08:00,894 - __main__ - INFO - Initializing GradioAutodiffusers +2025-05-29 16:08:00,894 - __main__ - DEBUG - API key found, length: 39 +2025-05-29 16:08:00,894 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator +2025-05-29 16:08:00,894 - auto_diffusers - DEBUG - API key length: 39 +2025-05-29 16:08:00,894 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools +2025-05-29 16:08:00,894 - hardware_detector - INFO - Initializing HardwareDetector +2025-05-29 16:08:00,894 - hardware_detector - DEBUG - Starting system hardware detection +2025-05-29 16:08:00,894 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64 +2025-05-29 16:08:00,894 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11 +2025-05-29 16:08:00,894 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi +2025-05-29 16:08:00,898 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected +2025-05-29 16:08:00,898 - hardware_detector - DEBUG - Checking PyTorch availability +2025-05-29 16:08:01,310 - hardware_detector - INFO - PyTorch 2.7.0 detected +2025-05-29 16:08:01,310 - hardware_detector - DEBUG - CUDA available: False, MPS available: True +2025-05-29 16:08:01,310 - hardware_detector - INFO - Hardware detection completed successfully +2025-05-29 16:08:01,310 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'} +2025-05-29 16:08:01,310 - auto_diffusers - INFO - Hardware detector initialized successfully +2025-05-29 16:08:01,310 - __main__ - INFO - AutoDiffusersGenerator initialized successfully +2025-05-29 16:08:01,310 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator +2025-05-29 16:08:01,310 - simple_memory_calculator - DEBUG - HuggingFace API initialized +2025-05-29 16:08:01,310 - simple_memory_calculator - DEBUG - Known models in database: 4 +2025-05-29 16:08:01,310 - __main__ - INFO - SimpleMemoryCalculator initialized successfully +2025-05-29 16:08:01,310 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7 +2025-05-29 16:08:01,312 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 16:08:01,325 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None +2025-05-29 16:08:01,325 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 16:08:01,404 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 16:08:01,439 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None +2025-05-29 16:08:01,440 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:08:01,440 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:08:01,440 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:08:01,440 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:08:01 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')]) +2025-05-29 16:08:01,441 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:08:01,441 - httpcore.connection - DEBUG - close.started +2025-05-29 16:08:01,441 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:08:01,442 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None +2025-05-29 16:08:01,442 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:08:01,442 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:08:01,442 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:08:01,442 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:08:01,442 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:08:01,442 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:08:01,447 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:08:01 GMT'), (b'server', b'uvicorn'), (b'content-length', b'73065'), (b'content-type', b'text/html; charset=utf-8')]) +2025-05-29 16:08:01,448 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2025-05-29 16:08:01,448 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:08:01,448 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:08:01,448 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:08:01,448 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:08:01,448 - httpcore.connection - DEBUG - close.started +2025-05-29 16:08:01,448 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:08:01,459 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None +2025-05-29 16:08:01,611 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0 +2025-05-29 16:08:01,746 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:08:01,746 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=30 +2025-05-29 16:08:01,764 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:08:01,764 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=3 +2025-05-29 16:08:02,034 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 16:08:02,035 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:08:02,035 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:08:02,036 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:08:02,036 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:08:02,036 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:08:02,101 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 16:08:02,101 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:08:02,101 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:08:02,101 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:08:02,101 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:08:02,101 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:08:02,186 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:08:02 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')]) +2025-05-29 16:08:02,186 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK" +2025-05-29 16:08:02,187 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:08:02,187 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:08:02,187 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:08:02,187 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:08:02,187 - httpcore.connection - DEBUG - close.started +2025-05-29 16:08:02,187 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:08:02,272 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:08:02 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')]) +2025-05-29 16:08:02,273 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2025-05-29 16:08:02,273 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:08:02,273 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:08:02,273 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:08:02,273 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:08:02,273 - httpcore.connection - DEBUG - close.started +2025-05-29 16:08:02,273 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:08:02,845 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 16:08:03,061 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0 +2025-05-29 16:08:25,941 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:25,942 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:25,942 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0} +2025-05-29 16:08:25,942 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM +2025-05-29 16:08:25,942 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:25,942 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:25,942 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:08:25,942 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:25,943 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:30,760 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:30,761 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:30,761 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM +2025-05-29 16:08:30,761 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:30,761 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:30,761 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:08:30,761 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:30,761 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,477 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,477 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,478 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:08:37,478 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,478 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,478 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:08:37,480 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,480 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,527 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,527 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,527 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:08:37,527 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,527 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,527 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:08:37,527 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:37,527 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:39,349 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:39,350 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:39,350 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:08:39,350 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:39,350 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:39,351 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:08:39,351 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:39,351 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:39,351 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:08:39,351 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4 +2025-05-29 16:08:39,351 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True +2025-05-29 16:08:39,351 - auto_diffusers - INFO - Using manual hardware specifications +2025-05-29 16:08:39,351 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': [{'name': 'RTX 5090', 'memory_mb': 32768}]} +2025-05-29 16:08:39,352 - auto_diffusers - DEBUG - GPU detected with 32.0 GB VRAM +2025-05-29 16:08:39,352 - auto_diffusers - INFO - Selected optimization profile: performance +2025-05-29 16:08:39,352 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API +2025-05-29 16:08:39,352 - auto_diffusers - DEBUG - Prompt length: 3456 characters +2025-05-29 16:08:39,352 - auto_diffusers - INFO - ================================================================================ +2025-05-29 16:08:39,352 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API: +2025-05-29 16:08:39,352 - auto_diffusers - INFO - ================================================================================ +2025-05-29 16:08:39,352 - auto_diffusers - INFO - +You are an expert in optimizing diffusers library code for different hardware configurations. + +NOTE: Advanced tool calling features are available when dependencies are installed. + +TASK: Generate optimized Python code for running a diffusion model with the following specifications: +- Model: black-forest-labs/FLUX.1-schnell +- Prompt: "A cat holding a sign that says hello world" +- Image size: 768x1360 +- Inference steps: 4 + +HARDWARE SPECIFICATIONS: +- Platform: Linux (manual_input) +- CPU Cores: 8 +- CUDA Available: False +- MPS Available: False +- Optimization Profile: performance +- GPU: RTX 5090 (32.0 GB VRAM) + +MEMORY ANALYSIS: +- Model Memory Requirements: 36.0 GB (FP16 inference) +- Model Weights Size: 24.0 GB (FP16) +- Memory Recommendation: ⚠️ Model weights fit, enable memory optimizations +- Recommended Precision: float16 +- Attention Slicing Recommended: True +- VAE Slicing Recommended: True + +OPTIMIZATION REQUIREMENTS: +Please scrape and analyze the latest optimization techniques from this URL: https://huggingface.co/docs/diffusers/main/en/optimization + +IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed. + +Based on the hardware specs and optimization profile, generate Python code that includes: + +1. **Memory Optimizations** (if low VRAM): + - Model offloading (enable_model_cpu_offload, enable_sequential_cpu_offload) + - Attention slicing (enable_attention_slicing) + - VAE slicing (enable_vae_slicing) + - Memory efficient attention + +2. **Speed Optimizations**: + - Appropriate torch.compile() usage + - Optimal dtype selection (torch.float16, torch.bfloat16) + - Device placement optimization + +3. **Hardware-Specific Optimizations**: + - CUDA optimizations for NVIDIA GPUs + - MPS optimizations for Apple Silicon + - CPU fallbacks when needed + +4. **Model-Specific Optimizations**: + - Appropriate scheduler selection + - Optimal inference parameters + - Pipeline configuration + +5. **Data Type (dtype) Selection**: + - If user specified a dtype, use that exact dtype in the code + - If no dtype specified, automatically select the optimal dtype based on hardware: + * Apple Silicon (MPS): prefer torch.bfloat16 + * NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 based on capability + * CPU only: use torch.float32 + - Add a comment explaining why that dtype was chosen + +IMPORTANT GUIDELINES: +- Include all necessary imports +- Add brief comments explaining optimization choices +- Use the most current and effective optimization techniques +- Ensure code is production-ready + +CODE STYLE REQUIREMENTS - GENERATE COMPACT CODE: +- Assign static values directly to function arguments instead of using variables when possible +- Minimize variable declarations - inline values where it improves readability +- Reduce exception handling to essential cases only - assume normal operation +- Use concise, direct code patterns +- Combine operations where logical and readable +- Avoid unnecessary intermediate variables +- Keep code clean and minimal while maintaining functionality + +Examples of preferred compact style: +- pipe = Pipeline.from_pretrained("model", torch_dtype=torch.float16) instead of storing dtype in variable +- image = pipe("prompt", num_inference_steps=4, height=768, width=1360) instead of separate variables +- Direct assignment: device = "cuda" if torch.cuda.is_available() else "cpu" + +Generate ONLY the Python code, no explanations before or after the code block. + +2025-05-29 16:08:39,353 - auto_diffusers - INFO - ================================================================================ +2025-05-29 16:08:39,353 - auto_diffusers - INFO - Sending request to Gemini API +2025-05-29 16:08:54,821 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used) +2025-05-29 16:08:54,821 - auto_diffusers - DEBUG - Response length: 2512 characters +2025-05-29 16:16:14,940 - __main__ - INFO - Initializing GradioAutodiffusers +2025-05-29 16:16:14,940 - __main__ - DEBUG - API key found, length: 39 +2025-05-29 16:16:14,940 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator +2025-05-29 16:16:14,940 - auto_diffusers - DEBUG - API key length: 39 +2025-05-29 16:16:14,940 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools +2025-05-29 16:16:14,940 - hardware_detector - INFO - Initializing HardwareDetector +2025-05-29 16:16:14,940 - hardware_detector - DEBUG - Starting system hardware detection +2025-05-29 16:16:14,940 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64 +2025-05-29 16:16:14,940 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11 +2025-05-29 16:16:14,940 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi +2025-05-29 16:16:14,943 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected +2025-05-29 16:16:14,943 - hardware_detector - DEBUG - Checking PyTorch availability +2025-05-29 16:16:15,359 - hardware_detector - INFO - PyTorch 2.7.0 detected +2025-05-29 16:16:15,359 - hardware_detector - DEBUG - CUDA available: False, MPS available: True +2025-05-29 16:16:15,359 - hardware_detector - INFO - Hardware detection completed successfully +2025-05-29 16:16:15,359 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'} +2025-05-29 16:16:15,359 - auto_diffusers - INFO - Hardware detector initialized successfully +2025-05-29 16:16:15,359 - __main__ - INFO - AutoDiffusersGenerator initialized successfully +2025-05-29 16:16:15,359 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator +2025-05-29 16:16:15,359 - simple_memory_calculator - DEBUG - HuggingFace API initialized +2025-05-29 16:16:15,359 - simple_memory_calculator - DEBUG - Known models in database: 4 +2025-05-29 16:16:15,359 - __main__ - INFO - SimpleMemoryCalculator initialized successfully +2025-05-29 16:16:15,359 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7 +2025-05-29 16:16:15,362 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 16:16:15,374 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None +2025-05-29 16:16:15,381 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 16:16:15,454 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 16:16:15,488 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None +2025-05-29 16:16:15,489 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:16:15,489 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:16:15,489 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:16:15,489 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:16:15,489 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:16:15,489 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:16:15,490 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:16:15 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')]) +2025-05-29 16:16:15,490 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2025-05-29 16:16:15,490 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:16:15,490 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:16:15,490 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:16:15,490 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:16:15,490 - httpcore.connection - DEBUG - close.started +2025-05-29 16:16:15,490 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:16:15,490 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None +2025-05-29 16:16:15,491 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:16:15,491 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:16:15,491 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:16:15,491 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:16:15,491 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:16:15,491 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:16:15,496 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:16:15 GMT'), (b'server', b'uvicorn'), (b'content-length', b'73064'), (b'content-type', b'text/html; charset=utf-8')]) +2025-05-29 16:16:15,496 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2025-05-29 16:16:15,496 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:16:15,496 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:16:15,496 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:16:15,496 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:16:15,496 - httpcore.connection - DEBUG - close.started +2025-05-29 16:16:15,496 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:16:15,507 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None +2025-05-29 16:16:15,593 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:16:15,593 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=3 +2025-05-29 16:16:15,648 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:16:15,648 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=30 +2025-05-29 16:16:15,663 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0 +2025-05-29 16:16:15,894 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 16:16:15,895 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:16:15,896 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:16:15,896 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:16:15,896 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:16:15,896 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:16:15,930 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 16:16:15,931 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:16:15,931 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:16:15,931 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:16:15,931 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:16:15,931 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:16:16,047 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:16:16 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')]) +2025-05-29 16:16:16,047 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2025-05-29 16:16:16,047 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:16:16,048 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:16:16,048 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:16:16,048 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:16:16,048 - httpcore.connection - DEBUG - close.started +2025-05-29 16:16:16,048 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:16:16,073 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:16:16 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')]) +2025-05-29 16:16:16,074 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK" +2025-05-29 16:16:16,074 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:16:16,074 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:16:16,074 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:16:16,074 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:16:16,074 - httpcore.connection - DEBUG - close.started +2025-05-29 16:16:16,074 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:16:16,750 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 16:16:16,967 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0 +2025-05-29 16:16:50,011 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:16:50,012 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:16:50,012 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0} +2025-05-29 16:16:50,012 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM +2025-05-29 16:16:50,012 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:16:50,012 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:16:50,012 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:16:50,012 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:16:50,012 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:16:56,212 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:16:56,212 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:16:56,212 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM +2025-05-29 16:16:56,212 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:16:56,212 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:16:56,212 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:16:56,212 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:16:56,212 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,382 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,382 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,383 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:17:00,383 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,383 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,383 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:17:00,383 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,383 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,534 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,534 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,534 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:17:00,534 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,534 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,534 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:17:00,534 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:00,535 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:02,112 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:02,112 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:02,112 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:17:02,112 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:02,112 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:02,112 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:17:02,112 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:02,112 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:02,112 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:17:02,112 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4 +2025-05-29 16:17:02,112 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True +2025-05-29 16:17:02,112 - auto_diffusers - INFO - Using manual hardware specifications +2025-05-29 16:17:02,112 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': [{'name': 'RTX 5090', 'memory_mb': 32768}]} +2025-05-29 16:17:02,112 - auto_diffusers - DEBUG - GPU detected with 32.0 GB VRAM +2025-05-29 16:17:02,112 - auto_diffusers - INFO - Selected optimization profile: performance +2025-05-29 16:17:02,112 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API +2025-05-29 16:17:02,113 - auto_diffusers - DEBUG - Prompt length: 3456 characters +2025-05-29 16:17:02,113 - auto_diffusers - INFO - ================================================================================ +2025-05-29 16:17:02,113 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API: +2025-05-29 16:17:02,113 - auto_diffusers - INFO - ================================================================================ +2025-05-29 16:17:02,113 - auto_diffusers - INFO - +You are an expert in optimizing diffusers library code for different hardware configurations. + +NOTE: Advanced tool calling features are available when dependencies are installed. + +TASK: Generate optimized Python code for running a diffusion model with the following specifications: +- Model: black-forest-labs/FLUX.1-schnell +- Prompt: "A cat holding a sign that says hello world" +- Image size: 768x1360 +- Inference steps: 4 + +HARDWARE SPECIFICATIONS: +- Platform: Linux (manual_input) +- CPU Cores: 8 +- CUDA Available: False +- MPS Available: False +- Optimization Profile: performance +- GPU: RTX 5090 (32.0 GB VRAM) + +MEMORY ANALYSIS: +- Model Memory Requirements: 36.0 GB (FP16 inference) +- Model Weights Size: 24.0 GB (FP16) +- Memory Recommendation: ⚠️ Model weights fit, enable memory optimizations +- Recommended Precision: float16 +- Attention Slicing Recommended: True +- VAE Slicing Recommended: True + +OPTIMIZATION REQUIREMENTS: +Please scrape and analyze the latest optimization techniques from this URL: https://huggingface.co/docs/diffusers/main/en/optimization + +IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed. + +Based on the hardware specs and optimization profile, generate Python code that includes: + +1. **Memory Optimizations** (if low VRAM): + - Model offloading (enable_model_cpu_offload, enable_sequential_cpu_offload) + - Attention slicing (enable_attention_slicing) + - VAE slicing (enable_vae_slicing) + - Memory efficient attention + +2. **Speed Optimizations**: + - Appropriate torch.compile() usage + - Optimal dtype selection (torch.float16, torch.bfloat16) + - Device placement optimization + +3. **Hardware-Specific Optimizations**: + - CUDA optimizations for NVIDIA GPUs + - MPS optimizations for Apple Silicon + - CPU fallbacks when needed + +4. **Model-Specific Optimizations**: + - Appropriate scheduler selection + - Optimal inference parameters + - Pipeline configuration + +5. **Data Type (dtype) Selection**: + - If user specified a dtype, use that exact dtype in the code + - If no dtype specified, automatically select the optimal dtype based on hardware: + * Apple Silicon (MPS): prefer torch.bfloat16 + * NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 based on capability + * CPU only: use torch.float32 + - Add a comment explaining why that dtype was chosen + +IMPORTANT GUIDELINES: +- Include all necessary imports +- Add brief comments explaining optimization choices +- Use the most current and effective optimization techniques +- Ensure code is production-ready + +CODE STYLE REQUIREMENTS - GENERATE COMPACT CODE: +- Assign static values directly to function arguments instead of using variables when possible +- Minimize variable declarations - inline values where it improves readability +- Reduce exception handling to essential cases only - assume normal operation +- Use concise, direct code patterns +- Combine operations where logical and readable +- Avoid unnecessary intermediate variables +- Keep code clean and minimal while maintaining functionality + +Examples of preferred compact style: +- pipe = Pipeline.from_pretrained("model", torch_dtype=torch.float16) instead of storing dtype in variable +- image = pipe("prompt", num_inference_steps=4, height=768, width=1360) instead of separate variables +- Direct assignment: device = "cuda" if torch.cuda.is_available() else "cpu" + +Generate ONLY the Python code, no explanations before or after the code block. + +2025-05-29 16:17:02,113 - auto_diffusers - INFO - ================================================================================ +2025-05-29 16:17:02,113 - auto_diffusers - INFO - Sending request to Gemini API +2025-05-29 16:17:17,152 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used) +2025-05-29 16:17:17,153 - auto_diffusers - DEBUG - Response length: 2451 characters +2025-05-29 16:47:23,476 - __main__ - INFO - Initializing GradioAutodiffusers +2025-05-29 16:47:23,476 - __main__ - DEBUG - API key found, length: 39 +2025-05-29 16:47:23,476 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator +2025-05-29 16:47:23,476 - auto_diffusers - DEBUG - API key length: 39 +2025-05-29 16:47:23,477 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools +2025-05-29 16:47:23,477 - hardware_detector - INFO - Initializing HardwareDetector +2025-05-29 16:47:23,477 - hardware_detector - DEBUG - Starting system hardware detection +2025-05-29 16:47:23,477 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64 +2025-05-29 16:47:23,477 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11 +2025-05-29 16:47:23,477 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi +2025-05-29 16:47:23,480 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected +2025-05-29 16:47:23,480 - hardware_detector - DEBUG - Checking PyTorch availability +2025-05-29 16:47:23,928 - hardware_detector - INFO - PyTorch 2.7.0 detected +2025-05-29 16:47:23,928 - hardware_detector - DEBUG - CUDA available: False, MPS available: True +2025-05-29 16:47:23,928 - hardware_detector - INFO - Hardware detection completed successfully +2025-05-29 16:47:23,928 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'} +2025-05-29 16:47:23,928 - auto_diffusers - INFO - Hardware detector initialized successfully +2025-05-29 16:47:23,928 - __main__ - INFO - AutoDiffusersGenerator initialized successfully +2025-05-29 16:47:23,928 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator +2025-05-29 16:47:23,928 - simple_memory_calculator - DEBUG - HuggingFace API initialized +2025-05-29 16:47:23,928 - simple_memory_calculator - DEBUG - Known models in database: 4 +2025-05-29 16:47:23,928 - __main__ - INFO - SimpleMemoryCalculator initialized successfully +2025-05-29 16:47:23,928 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7 +2025-05-29 16:47:23,930 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 16:47:23,944 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None +2025-05-29 16:47:23,950 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 16:47:24,025 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 16:47:24,059 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None +2025-05-29 16:47:24,060 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:47:24,060 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:47:24,060 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:47:24,060 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:47:24 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')]) +2025-05-29 16:47:24,061 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:47:24,061 - httpcore.connection - DEBUG - close.started +2025-05-29 16:47:24,061 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:47:24,062 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None +2025-05-29 16:47:24,062 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:47:24,062 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:47:24,062 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:47:24,062 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:47:24,062 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:47:24,062 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:47:24,068 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:47:24 GMT'), (b'server', b'uvicorn'), (b'content-length', b'73064'), (b'content-type', b'text/html; charset=utf-8')]) +2025-05-29 16:47:24,068 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2025-05-29 16:47:24,068 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:47:24,068 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:47:24,068 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:47:24,068 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:47:24,068 - httpcore.connection - DEBUG - close.started +2025-05-29 16:47:24,068 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:47:24,079 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None +2025-05-29 16:47:24,140 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:47:24,140 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=3 +2025-05-29 16:47:24,220 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:47:24,220 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=30 +2025-05-29 16:47:24,223 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0 +2025-05-29 16:47:24,415 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 16:47:24,415 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:47:24,415 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:47:24,415 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:47:24,415 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:47:24,415 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:47:24,504 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 16:47:24,505 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:47:24,505 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:47:24,505 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:47:24,505 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:47:24,505 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:47:24,553 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:47:24 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')]) +2025-05-29 16:47:24,554 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2025-05-29 16:47:24,554 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:47:24,554 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:47:24,554 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:47:24,554 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:47:24,554 - httpcore.connection - DEBUG - close.started +2025-05-29 16:47:24,554 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:47:24,648 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:47:24 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')]) +2025-05-29 16:47:24,648 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK" +2025-05-29 16:47:24,648 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:47:24,648 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:47:24,648 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:47:24,648 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:47:24,649 - httpcore.connection - DEBUG - close.started +2025-05-29 16:47:24,649 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:47:25,332 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 16:47:25,554 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0 +2025-05-29 16:47:35,239 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:35,239 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:35,239 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0} +2025-05-29 16:47:35,239 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM +2025-05-29 16:47:35,239 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:35,239 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:35,239 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:47:35,240 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:35,240 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:40,282 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:40,282 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:40,282 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM +2025-05-29 16:47:40,282 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:40,282 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:40,282 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:47:40,282 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:40,282 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:43,895 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:43,895 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:43,895 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:47:43,895 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:43,895 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:43,895 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:47:43,895 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:43,896 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:44,048 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:44,048 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:44,048 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:47:44,048 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:44,048 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:44,048 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:47:44,048 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:44,048 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:48,011 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:48,011 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:48,011 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM +2025-05-29 16:47:48,011 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:48,011 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:48,011 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:47:48,011 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:48,012 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:48,012 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4 +2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True +2025-05-29 16:47:48,012 - auto_diffusers - INFO - Using manual hardware specifications +2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': [{'name': 'RTX 5090', 'memory_mb': 32768}]} +2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - GPU detected with 32.0 GB VRAM +2025-05-29 16:47:48,012 - auto_diffusers - INFO - Selected optimization profile: performance +2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API +2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - Prompt length: 7613 characters +2025-05-29 16:47:48,012 - auto_diffusers - INFO - ================================================================================ +2025-05-29 16:47:48,012 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API: +2025-05-29 16:47:48,013 - auto_diffusers - INFO - ================================================================================ +2025-05-29 16:47:48,013 - auto_diffusers - INFO - +You are an expert in optimizing diffusers library code for different hardware configurations. + +NOTE: This system includes curated optimization knowledge from HuggingFace documentation. + +TASK: Generate optimized Python code for running a diffusion model with the following specifications: +- Model: black-forest-labs/FLUX.1-schnell +- Prompt: "A cat holding a sign that says hello world" +- Image size: 768x1360 +- Inference steps: 4 + +HARDWARE SPECIFICATIONS: +- Platform: Linux (manual_input) +- CPU Cores: 8 +- CUDA Available: False +- MPS Available: False +- Optimization Profile: performance +- GPU: RTX 5090 (32.0 GB VRAM) + +MEMORY ANALYSIS: +- Model Memory Requirements: 36.0 GB (FP16 inference) +- Model Weights Size: 24.0 GB (FP16) +- Memory Recommendation: ⚠️ Model weights fit, enable memory optimizations +- Recommended Precision: float16 +- Attention Slicing Recommended: True +- VAE Slicing Recommended: True + +OPTIMIZATION KNOWLEDGE BASE: + +# DIFFUSERS OPTIMIZATION TECHNIQUES + +## Memory Optimization Techniques + +### 1. Model CPU Offloading +Use `enable_model_cpu_offload()` to move models between GPU and CPU automatically: +```python +pipe.enable_model_cpu_offload() +``` +- Saves significant VRAM by keeping only active models on GPU +- Automatic management, no manual intervention needed +- Compatible with all pipelines + +### 2. Sequential CPU Offloading +Use `enable_sequential_cpu_offload()` for more aggressive memory saving: +```python +pipe.enable_sequential_cpu_offload() +``` +- More memory efficient than model offloading +- Moves models to CPU after each forward pass +- Best for very limited VRAM scenarios + +### 3. Attention Slicing +Use `enable_attention_slicing()` to reduce memory during attention computation: +```python +pipe.enable_attention_slicing() +# or specify slice size +pipe.enable_attention_slicing("max") # maximum slicing +pipe.enable_attention_slicing(1) # slice_size = 1 +``` +- Trades compute time for memory +- Most effective for high-resolution images +- Can be combined with other techniques + +### 4. VAE Slicing +Use `enable_vae_slicing()` for large batch processing: +```python +pipe.enable_vae_slicing() +``` +- Decodes images one at a time instead of all at once +- Essential for batch sizes > 4 +- Minimal performance impact on single images + +### 5. VAE Tiling +Use `enable_vae_tiling()` for high-resolution image generation: +```python +pipe.enable_vae_tiling() +``` +- Enables 4K+ image generation on 8GB VRAM +- Splits images into overlapping tiles +- Automatically disabled for 512x512 or smaller images + +### 6. Memory Efficient Attention (xFormers) +Use `enable_xformers_memory_efficient_attention()` if xFormers is installed: +```python +pipe.enable_xformers_memory_efficient_attention() +``` +- Significantly reduces memory usage and improves speed +- Requires xformers library installation +- Compatible with most models + +## Performance Optimization Techniques + +### 1. Half Precision (FP16/BF16) +Use lower precision for better memory and speed: +```python +# FP16 (widely supported) +pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) + +# BF16 (better numerical stability, newer hardware) +pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) +``` +- FP16: Halves memory usage, widely supported +- BF16: Better numerical stability, requires newer GPUs +- Essential for most optimization scenarios + +### 2. Torch Compile (PyTorch 2.0+) +Use `torch.compile()` for significant speed improvements: +```python +pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True) +# For some models, compile VAE too: +pipe.vae.decode = torch.compile(pipe.vae.decode, mode="reduce-overhead", fullgraph=True) +``` +- 5-50% speed improvement +- Requires PyTorch 2.0+ +- First run is slower due to compilation + +### 3. Fast Schedulers +Use faster schedulers for fewer steps: +```python +from diffusers import LMSDiscreteScheduler, UniPCMultistepScheduler + +# LMS Scheduler (good quality, fast) +pipe.scheduler = LMSDiscreteScheduler.from_config(pipe.scheduler.config) + +# UniPC Scheduler (fastest) +pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config) +``` + +## Hardware-Specific Optimizations + +### NVIDIA GPU Optimizations +```python +# Enable Tensor Cores +torch.backends.cudnn.benchmark = True + +# Optimal data type for NVIDIA +torch_dtype = torch.float16 # or torch.bfloat16 for RTX 30/40 series +``` + +### Apple Silicon (MPS) Optimizations +```python +# Use MPS device +device = "mps" if torch.backends.mps.is_available() else "cpu" +pipe = pipe.to(device) + +# Recommended dtype for Apple Silicon +torch_dtype = torch.bfloat16 # Better than float16 on Apple Silicon + +# Attention slicing often helps on MPS +pipe.enable_attention_slicing() +``` + +### CPU Optimizations +```python +# Use float32 for CPU +torch_dtype = torch.float32 + +# Enable optimized attention +pipe.enable_attention_slicing() +``` + +## Model-Specific Guidelines + +### FLUX Models +- Do NOT use guidance_scale parameter (not needed for FLUX) +- Use 4-8 inference steps maximum +- BF16 dtype recommended +- Enable attention slicing for memory optimization + +### Stable Diffusion XL +- Enable attention slicing for high resolutions +- Use refiner model sparingly to save memory +- Consider VAE tiling for >1024px images + +### Stable Diffusion 1.5/2.1 +- Very memory efficient base models +- Can often run without optimizations on 8GB+ VRAM +- Enable VAE slicing for batch processing + +## Memory Usage Estimation +- FLUX.1: ~24GB for full precision, ~12GB for FP16 +- SDXL: ~7GB for FP16, ~14GB for FP32 +- SD 1.5: ~2GB for FP16, ~4GB for FP32 + +## Optimization Combinations by VRAM + +### 24GB+ VRAM (High-end) +```python +pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) +pipe = pipe.to("cuda") +pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True) +``` + +### 12-24GB VRAM (Mid-range) +```python +pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) +pipe = pipe.to("cuda") +pipe.enable_model_cpu_offload() +pipe.enable_xformers_memory_efficient_attention() +``` + +### 8-12GB VRAM (Entry-level) +```python +pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) +pipe.enable_sequential_cpu_offload() +pipe.enable_attention_slicing() +pipe.enable_vae_slicing() +pipe.enable_xformers_memory_efficient_attention() +``` + +### <8GB VRAM (Low-end) +```python +pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) +pipe.enable_sequential_cpu_offload() +pipe.enable_attention_slicing("max") +pipe.enable_vae_slicing() +pipe.enable_vae_tiling() +``` + + +IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed. + +Using the OPTIMIZATION KNOWLEDGE BASE above, generate Python code that: + +1. **Selects the best optimization techniques** for the specific hardware profile +2. **Applies appropriate memory optimizations** based on available VRAM +3. **Uses optimal data types** for the target hardware: + - User specified dtype (if provided): Use exactly as specified + - Apple Silicon (MPS): prefer torch.bfloat16 + - NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 + - CPU only: use torch.float32 +4. **Implements hardware-specific optimizations** (CUDA, MPS, CPU) +5. **Follows model-specific guidelines** (e.g., FLUX guidance_scale handling) + +IMPORTANT GUIDELINES: +- Reference the OPTIMIZATION KNOWLEDGE BASE to select appropriate techniques +- Include all necessary imports +- Add brief comments explaining optimization choices +- Generate compact, production-ready code +- Inline values where possible for concise code +- Generate ONLY the Python code, no explanations before or after the code block + +2025-05-29 16:47:48,013 - auto_diffusers - INFO - ================================================================================ +2025-05-29 16:47:48,013 - auto_diffusers - INFO - Sending request to Gemini API +2025-05-29 16:48:09,467 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used) +2025-05-29 16:48:09,467 - auto_diffusers - DEBUG - Response length: 3996 characters +2025-05-29 16:57:34,668 - __main__ - INFO - Initializing GradioAutodiffusers +2025-05-29 16:57:34,668 - __main__ - DEBUG - API key found, length: 39 +2025-05-29 16:57:34,668 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator +2025-05-29 16:57:34,668 - auto_diffusers - DEBUG - API key length: 39 +2025-05-29 16:57:34,668 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools +2025-05-29 16:57:34,668 - hardware_detector - INFO - Initializing HardwareDetector +2025-05-29 16:57:34,668 - hardware_detector - DEBUG - Starting system hardware detection +2025-05-29 16:57:34,668 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64 +2025-05-29 16:57:34,668 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11 +2025-05-29 16:57:34,668 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi +2025-05-29 16:57:34,672 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected +2025-05-29 16:57:34,672 - hardware_detector - DEBUG - Checking PyTorch availability +2025-05-29 16:57:35,129 - hardware_detector - INFO - PyTorch 2.7.0 detected +2025-05-29 16:57:35,129 - hardware_detector - DEBUG - CUDA available: False, MPS available: True +2025-05-29 16:57:35,129 - hardware_detector - INFO - Hardware detection completed successfully +2025-05-29 16:57:35,129 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'} +2025-05-29 16:57:35,129 - auto_diffusers - INFO - Hardware detector initialized successfully +2025-05-29 16:57:35,129 - __main__ - INFO - AutoDiffusersGenerator initialized successfully +2025-05-29 16:57:35,129 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator +2025-05-29 16:57:35,129 - simple_memory_calculator - DEBUG - HuggingFace API initialized +2025-05-29 16:57:35,129 - simple_memory_calculator - DEBUG - Known models in database: 4 +2025-05-29 16:57:35,129 - __main__ - INFO - SimpleMemoryCalculator initialized successfully +2025-05-29 16:57:35,129 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7 +2025-05-29 16:57:35,131 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 16:57:35,145 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None +2025-05-29 16:57:35,145 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 16:57:35,222 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 16:57:35,257 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None +2025-05-29 16:57:35,257 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:57:35 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')]) +2025-05-29 16:57:35,259 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2025-05-29 16:57:35,259 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:57:35,259 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:57:35,259 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:57:35,259 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:57:35,259 - httpcore.connection - DEBUG - close.started +2025-05-29 16:57:35,259 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:57:35,259 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None +2025-05-29 16:57:35,260 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:57:35,260 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:57:35,260 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:57:35,260 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:57:35,260 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:57:35,260 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:57:35,265 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:57:35 GMT'), (b'server', b'uvicorn'), (b'content-length', b'75554'), (b'content-type', b'text/html; charset=utf-8')]) +2025-05-29 16:57:35,265 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2025-05-29 16:57:35,265 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:57:35,265 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:57:35,265 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:57:35,266 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:57:35,266 - httpcore.connection - DEBUG - close.started +2025-05-29 16:57:35,266 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:57:35,276 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None +2025-05-29 16:57:35,346 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:57:35,346 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=3 +2025-05-29 16:57:35,425 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0 +2025-05-29 16:57:35,434 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 16:57:35,434 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=30 +2025-05-29 16:57:35,637 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 16:57:35,638 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:57:35,638 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:57:35,638 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:57:35,638 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:57:35,638 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:57:35,751 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 16:57:35,751 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 16:57:35,752 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 16:57:35,752 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 16:57:35,752 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 16:57:35,752 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 16:57:35,786 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:57:35 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')]) +2025-05-29 16:57:35,787 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2025-05-29 16:57:35,787 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:57:35,787 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:57:35,787 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:57:35,787 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:57:35,787 - httpcore.connection - DEBUG - close.started +2025-05-29 16:57:35,788 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:57:35,912 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:57:35 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')]) +2025-05-29 16:57:35,912 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK" +2025-05-29 16:57:35,912 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 16:57:35,912 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 16:57:35,912 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 16:57:35,912 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 16:57:35,912 - httpcore.connection - DEBUG - close.started +2025-05-29 16:57:35,912 - httpcore.connection - DEBUG - close.complete +2025-05-29 16:57:36,487 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 16:57:36,707 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0 +2025-05-29 16:57:49,246 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:57:49,246 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:57:49,246 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0} +2025-05-29 16:57:49,246 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM +2025-05-29 16:57:49,246 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:57:49,246 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 16:57:49,247 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 16:57:49,247 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 16:57:49,247 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 17:00:22,113 - __main__ - INFO - Initializing GradioAutodiffusers +2025-05-29 17:00:22,113 - __main__ - DEBUG - API key found, length: 39 +2025-05-29 17:00:22,113 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator +2025-05-29 17:00:22,113 - auto_diffusers - DEBUG - API key length: 39 +2025-05-29 17:00:22,113 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools +2025-05-29 17:00:22,113 - hardware_detector - INFO - Initializing HardwareDetector +2025-05-29 17:00:22,113 - hardware_detector - DEBUG - Starting system hardware detection +2025-05-29 17:00:22,113 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64 +2025-05-29 17:00:22,113 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11 +2025-05-29 17:00:22,113 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi +2025-05-29 17:00:22,117 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected +2025-05-29 17:00:22,117 - hardware_detector - DEBUG - Checking PyTorch availability +2025-05-29 17:00:22,530 - hardware_detector - INFO - PyTorch 2.7.0 detected +2025-05-29 17:00:22,530 - hardware_detector - DEBUG - CUDA available: False, MPS available: True +2025-05-29 17:00:22,530 - hardware_detector - INFO - Hardware detection completed successfully +2025-05-29 17:00:22,530 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'} +2025-05-29 17:00:22,530 - auto_diffusers - INFO - Hardware detector initialized successfully +2025-05-29 17:00:22,530 - __main__ - INFO - AutoDiffusersGenerator initialized successfully +2025-05-29 17:00:22,530 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator +2025-05-29 17:00:22,530 - simple_memory_calculator - DEBUG - HuggingFace API initialized +2025-05-29 17:00:22,530 - simple_memory_calculator - DEBUG - Known models in database: 4 +2025-05-29 17:00:22,530 - __main__ - INFO - SimpleMemoryCalculator initialized successfully +2025-05-29 17:00:22,530 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7 +2025-05-29 17:00:22,532 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 17:00:22,545 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None +2025-05-29 17:00:22,550 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 17:00:22,624 - asyncio - DEBUG - Using selector: KqueueSelector +2025-05-29 17:00:22,657 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None +2025-05-29 17:00:22,657 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 17:00:22,657 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 17:00:22,657 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 08:00:22 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')]) +2025-05-29 17:00:22,658 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK" +2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 17:00:22,658 - httpcore.connection - DEBUG - close.started +2025-05-29 17:00:22,658 - httpcore.connection - DEBUG - close.complete +2025-05-29 17:00:22,659 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None +2025-05-29 17:00:22,659 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 17:00:22,659 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 17:00:22,659 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 17:00:22,659 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 17:00:22,659 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 17:00:22,659 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 17:00:22,665 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 08:00:22 GMT'), (b'server', b'uvicorn'), (b'content-length', b'75615'), (b'content-type', b'text/html; charset=utf-8')]) +2025-05-29 17:00:22,665 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK" +2025-05-29 17:00:22,665 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 17:00:22,665 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 17:00:22,665 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 17:00:22,665 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 17:00:22,665 - httpcore.connection - DEBUG - close.started +2025-05-29 17:00:22,665 - httpcore.connection - DEBUG - close.complete +2025-05-29 17:00:22,676 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None +2025-05-29 17:00:22,750 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 17:00:22,750 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=3 +2025-05-29 17:00:22,815 - httpcore.connection - DEBUG - connect_tcp.complete return_value= +2025-05-29 17:00:22,815 - httpcore.connection - DEBUG - start_tls.started ssl_context= server_hostname='api.gradio.app' timeout=30 +2025-05-29 17:00:22,823 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0 +2025-05-29 17:00:23,027 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 17:00:23,028 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 17:00:23,028 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 17:00:23,029 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 17:00:23,029 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 17:00:23,029 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 17:00:23,090 - httpcore.connection - DEBUG - start_tls.complete return_value= +2025-05-29 17:00:23,090 - httpcore.http11 - DEBUG - send_request_headers.started request= +2025-05-29 17:00:23,091 - httpcore.http11 - DEBUG - send_request_headers.complete +2025-05-29 17:00:23,091 - httpcore.http11 - DEBUG - send_request_body.started request= +2025-05-29 17:00:23,091 - httpcore.http11 - DEBUG - send_request_body.complete +2025-05-29 17:00:23,091 - httpcore.http11 - DEBUG - receive_response_headers.started request= +2025-05-29 17:00:23,199 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 08:00:23 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')]) +2025-05-29 17:00:23,201 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK" +2025-05-29 17:00:23,201 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 17:00:23,201 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 17:00:23,201 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 17:00:23,201 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 17:00:23,201 - httpcore.connection - DEBUG - close.started +2025-05-29 17:00:23,202 - httpcore.connection - DEBUG - close.complete +2025-05-29 17:00:23,232 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 08:00:23 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')]) +2025-05-29 17:00:23,232 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK" +2025-05-29 17:00:23,232 - httpcore.http11 - DEBUG - receive_response_body.started request= +2025-05-29 17:00:23,233 - httpcore.http11 - DEBUG - receive_response_body.complete +2025-05-29 17:00:23,233 - httpcore.http11 - DEBUG - response_closed.started +2025-05-29 17:00:23,233 - httpcore.http11 - DEBUG - response_closed.complete +2025-05-29 17:00:23,233 - httpcore.connection - DEBUG - close.started +2025-05-29 17:00:23,233 - httpcore.connection - DEBUG - close.complete +2025-05-29 17:00:23,883 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443 +2025-05-29 17:00:24,103 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0 +2025-05-29 17:00:34,004 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 17:00:34,004 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 17:00:34,005 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0} +2025-05-29 17:00:34,005 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM +2025-05-29 17:00:34,005 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 17:00:34,005 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell +2025-05-29 17:00:34,005 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB +2025-05-29 17:00:34,005 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell +2025-05-29 17:00:34,005 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell