Using in Python - Githubissues

microsoft / LLaVA-Med

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

Other

1.29k stars 148 forks source link

Open spatiallysaying opened 8 months ago

spatiallysaying commented 8 months ago

How to get a basic description of the Image without the elaborate prompt engineering that you mentioned in CLI?

Is there a way to do something like

llava_model=getmodel('llava-v1.5-7b')
text_desc=llava_model.get_text_description(image_path)
print(text_desc)