yfzhang114 / SliME

✨✨Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models
Apache License 2.0
137 stars 7 forks source link

Question about LLaVA-HD #11

Open zachary19889 opened 2 weeks ago

zachary19889 commented 2 weeks ago

Hi, thank you so much for your fascinating work! I'm just a beginner in MLLM, and I couldn’t locate the high-resolution inference code of LLaVA-HD. Could you offer some guidance on how to run LLaVA-HD at higher resolutions, like 1008x1008? Looking forward to hearing from you!

yfzhang114 commented 1 week ago

It is confusing to me, what is the meaning of 'run llava-hd at higher resolution?'