haotian-liu / LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Home Page:https://llava.hliu.cc

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Question about multiple images in the same prompt

JesseZZZZZ opened this issue · comments

image
Hi! I saw this on huggingface, it says that if I want to use multiple images in the same prompt, I may receive inaccurate results. So how can I do this? I have the need to use text-image-mixed input to do things like "what are the difference between the first and second image I gave you?". Thanks a lot!!!