Salesforce
/

blip-image-captioning-large

image-text-to-text

image-captioning

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (13)

Interview request: Thoughts on genAI evaluation & documentation

#41 opened 2 months ago by

Finetune with Distributed Training

#40 opened 3 months ago by

Upload 3 files

#38 opened 3 months ago by

This Model can run on mobile app?

#37 opened 6 months ago by

How can I use this in ComfyUI ?

#35 opened 7 months ago by

Update README.md

#34 opened 8 months ago by

Upload 20240604_142924.jpg

#33 opened 9 months ago by

Get reproducable image features

#32 opened 10 months ago by

Rename README.md to man holding his dog

#31 opened 10 months ago by

Data privacy of uploaded image

#30 opened 10 months ago by

Can existing large datasets be used to fine tune the blip'large_caption task?

#29 opened 11 months ago by

Problem with API using JavaScript

#28 opened about 1 year ago by

How to train model with custom data?

#27 opened about 1 year ago by

Incorrect format used for Image, error when trying to invoke sagemaker endpoint.

#26 opened over 1 year ago by

Issue with Salesforce/blip-image-captioning-large Endpoint: "input_ids or inputs_embeds" Error

#25 opened over 1 year ago by

Image captioning using image url only without blob?

#23 opened over 1 year ago by

How do I create an Inference Endpoint with this model?

#22 opened over 1 year ago by

How to access the question-answer feature?

#21 opened over 1 year ago by

Why does it generates arafed so much ?

#20 opened over 1 year ago by

ideepankarsharma2003

[AUTOMATED] Model Memory Requirements

#19 opened over 1 year ago by

model-sizer-bot

Anyone has same problem when using api?

#17 opened over 1 year ago by

Is finetuning supported for this model? If so can people give me some pointers?

#16 opened over 1 year ago by

Load the tensorflow version

#15 opened over 1 year ago by

Calling predictor.predict() on deployed model via SageMaker

#14 opened over 1 year ago by

ONNX?

#13 opened over 1 year ago by

Adding `safetensors` variant of this model

#12 opened over 1 year ago by

Adding `safetensors` variant of this model

#6 opened almost 2 years ago by

[blip_text_model] num_attention_heads is 8? not 12? [blip_vision_model] eps is 1e-5?

#5 opened about 2 years ago by

Update tokenizer_config.json

#1 opened about 2 years ago by