Spaces:

Salesforce
/

BLIP2

Runtime error

App Files Files Community

Resources

View closed (13)

Question about multimodal BLIP-2 inputs : text, image or text+image embeddings need to end up in identical semantic space

#24 opened 13 days ago by

Test OCR Invoice

#22 opened about 1 year ago by

Create arch

#21 opened about 1 year ago by

Upload app.py

#18 opened over 1 year ago by

Local auto installer tutorial

#17 opened over 1 year ago by

Allow image uploads

#16 opened about 2 years ago by

files

#14 opened about 2 years ago by

A clever way to stop stupid generation starting after a certain amount of words at runtime?

#13 opened about 2 years ago by

Inference Endpoints

#12 opened about 2 years ago by

"num_captions" parameter for BLIP2. (model.generate)

#11 opened about 2 years ago by