InternLM / InternLM-XComposer

InternLM-XComposer2 is a groundbreaking vision-language large model (VLLM) excelling in free-form text-image composition and comprehension.
1.92k stars 121 forks source link

Does it support multi-image interleaved conversations? #277

Open starxhong opened 2 months ago

starxhong commented 2 months ago

the demo looks like only support one image in one prompt. i wonder does it support multi-image interleaved conversation? e.g. input 2 images at once and compare which is brighter

yuhangzang commented 2 months ago

Please refer to this issue.