This archive copy may be incomplete. The original-source link is preserved in the card footer.
RT @LiJunnan0409: Can LLMs understand images? We introduce 🔥BLIP-2🔥, a generic and efficient vision-language pre-training strategy that boo…
More notes on nearby ideas
Post · Apr 25, 2023what's your best prompting tips n tricks for generating better images, chatbots, writing? also any advice for using langchain?Reply · Oct 16, 2023@fentpot yeah maybe multimodal is asking too much rn... maybe could be a frankenstein of models? want speech2text & image recognition w good ocr &…Reply · Mar 15, 2023@SmokeAwayyy longer just bec I'd heard multimodal w video, but actually it's just image prompts and not yet releasedPost · Feb 16, 2026people say that people are beginning to talk like llms. i wonder how many tokens of chat for p(style transfer) > .5 and if it varies by model?