UniVTG
π
15
Ask questions about YouTube videos
image captioning, VQA
BLIP2 (cutting edge image captioning) in π€transformers
Compare different visual question answering
Play with all the pix2struct variants in this d
Cutting edge open-vocabulary object detection app
Chat with a GPT-4 language model
Chat with GPTβ4 using your own OpenAI API key
Generate summaries for long-form text
Generate detailed prompts describing an image