Salesforce/blip-image-captioning-base

Adding `safetensors` variant of this model

#48 opened 14 days ago by

SFconvertbot

Adding `safetensors` variant of this model

#47 opened 25 days ago by

SFconvertbot

Adding `safetensors` variant of this model

#46 opened 26 days ago by

SFconvertbot

Adding `safetensors` variant of this model

#45 opened 26 days ago by

SFconvertbot

Adding `safetensors` variant of this model

#44 opened about 2 months ago by

SFconvertbot

Adding `safetensors` variant of this model

#43 opened 2 months ago by

SFconvertbot

Adding `safetensors` variant of this model

#42 opened 2 months ago by

dechin

Adding `safetensors` variant of this model

1

#41 opened 3 months ago by

SFconvertbot

How to make the description longer and more detailed?

1

#40 opened 3 months ago by

oddball516

Extract probability instead of caption ?

#39 opened 3 months ago by

Camillo

Adding `safetensors` variant of this model

#38 opened 5 months ago by

SFconvertbot

Adding `safetensors` variant of this model

#37 opened 5 months ago by

SFconvertbot

Update README.md

#36 opened 5 months ago by

Vibrantvixen

Problem running the code

#34 opened 7 months ago by

MartinsCarlos111

about init.py

#33 opened 8 months ago by

zebbsb

the model can not distinguish color

#32 opened 9 months ago by

liuchao888

Model is supporting EN again?

1

#31 opened 11 months ago by

Baptbe

Fine tuning on Roco dataset and facing problem

#30 opened 12 months ago by

TanVir17Niloy

Upload Screenshot_20240501_151902_com.whatsapp~2.jpg

#29 opened 12 months ago by

vsbv18

repeat penalty

2

#28 opened 12 months ago by

vinnitu

somthing wrong when running clipintterogator...anyone kind to help?

#27 opened about 1 year ago by

kelvinyoung

getting different embedding values for the same image when trying to generate embeddings from two different sagemaker instances of the same model.

1

#26 opened over 1 year ago by

rnekkanti

Isit Possible to Upload Multiple Images at once and generate a all the list for example like 10 images

1

#25 opened over 1 year ago by

Kinglyz

image to prompt

#24 opened over 1 year ago by

rizwan0994

Adding `safetensors` variant of this model

#23 opened over 1 year ago by

SFconvertbot

Is finetuning possible for this model?

2

#21 opened over 1 year ago by

husjerry

Rename README.md to caixa de vidro boiando na água cristalina de uma praia ,ensolarada, cheia de pedras preciosas.

#20 opened almost 2 years ago by

pricelessgoodnews

Input for calling predictor.predict() on Sagemaker

1

6

#19 opened almost 2 years ago by

Callam

Adding `safetensors` variant of this model

#18 opened almost 2 years ago by

SFconvertbot

Info about the pre-trained checkpoint

1

#15 opened about 2 years ago by

nicolafan

Length of captions

8

#14 opened about 2 years ago by

Gandharv

Same as "model_base_caption_capfilt_large.pth"?

1

#10 opened about 2 years ago by

davidas85

Typo.

#9 opened about 2 years ago by

airplanegobrr

Adding `safetensors` variant of this model

#7 opened about 2 years ago by

SFconvertbot

I can not download this model.

2

#6 opened about 2 years ago by

xiaoxiaofeifei

Can't import "Salesforce/blip-image-captioning-base" on transformers==4.25.1

1

#2 opened over 2 years ago by

tnavin

Update tokenizer_config.json

#1 opened over 2 years ago by

ybelkada

Adding `safetensors` variant of this model

Adding `safetensors` variant of this model

Adding `safetensors` variant of this model

Adding `safetensors` variant of this model

Adding `safetensors` variant of this model

Adding `safetensors` variant of this model

Adding `safetensors` variant of this model

Adding `safetensors` variant of this model

How to make the description longer and more detailed?

Extract probability instead of caption ?

Adding `safetensors` variant of this model

Adding `safetensors` variant of this model

Update README.md

Problem running the code

about __init__.py

the model can not distinguish color

Model is supporting EN again?

Fine tuning on Roco dataset and facing problem

Upload Screenshot_20240501_151902_com.whatsapp~2.jpg

repeat penalty

somthing wrong when running clipintterogator...anyone kind to help?

getting different embedding values for the same image when trying to generate embeddings from two different sagemaker instances of the same model.

Isit Possible to Upload Multiple Images at once and generate a all the list for example like 10 images

image to prompt

Adding `safetensors` variant of this model

Is finetuning possible for this model?

Rename README.md to caixa de vidro boiando na água cristalina de uma praia ,ensolarada, cheia de pedras preciosas.

Input for calling predictor.predict() on Sagemaker

Adding `safetensors` variant of this model

Info about the pre-trained checkpoint

Length of captions

Same as "model_base_caption_capfilt_large.pth"?

Typo.

Adding `safetensors` variant of this model

I can not download this model.

Can't import "Salesforce/blip-image-captioning-base" on transformers==4.25.1

Update tokenizer_config.json

about init.py