RiddleHe commited on
Commit
e3db5b9
·
verified ·
1 Parent(s): 9ba0357

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -6
README.md CHANGED
@@ -19,10 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
19
  # LoRA text2image fine-tuning - RiddleHe/SD14_pathology_lora
20
  These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights were fine-tuned on the None dataset. You can find some example images in the following.
21
 
22
- ![img_1](./image_1.png)
23
- ![img_2](./image_2.png)
24
- ![img_3](./image_3.png)
25
-
 
 
 
26
 
27
 
28
  ## Intended uses & limitations
@@ -30,7 +33,14 @@ These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights w
30
  #### How to use
31
 
32
  ```python
33
- # TODO: add an example code snippet for running this diffusion pipeline
 
 
 
 
 
 
 
34
  ```
35
 
36
  #### Limitations and bias
@@ -39,4 +49,4 @@ These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights w
39
 
40
  ## Training details
41
 
42
- [TODO: describe the data used to train the model]
 
19
  # LoRA text2image fine-tuning - RiddleHe/SD14_pathology_lora
20
  These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights were fine-tuned on the None dataset. You can find some example images in the following.
21
 
22
+ <table>
23
+ <tr>
24
+ <td><img src="./image_1.png"></td>
25
+ <td><img src="./image_2.png"></td>
26
+ <td><img src="./image_3.png"></td>
27
+ </tr>
28
+ </table>
29
 
30
 
31
  ## Intended uses & limitations
 
33
  #### How to use
34
 
35
  ```python
36
+ pipe = DiffusionPipeline.from_pretrained(
37
+ “CompVis/stable-diffusion-v1-4, torch_dtype=torch.float16
38
+ )
39
+
40
+ pipe.load_lora_weights(args.lora_model_name_or_path)
41
+ pipe.to('cuda')
42
+
43
+ prompt = "A histopathology image of breast cancer tissue"
44
  ```
45
 
46
  #### Limitations and bias
 
49
 
50
  ## Training details
51
 
52
+ This model is trained on 28216 breast cancer tissue images from the BRCA dataset.