# Dynamic Visual Tokens
Ristretto 3B
Apache-2.0
Ristretto is an innovative vision-language model that employs dynamic image token deployment technology, allowing flexible adjustment of image token quantities based on task requirements, surpassing previous generations in performance and versatility.
Image-to-Text
Transformers Supports Multiple Languages

R
LiAutoAD
732
2
Chat UniVi 7B V1.5
Chat-UniVi is a large language model with unified visual representation, capable of understanding both images and video content.
Image-to-Text
Transformers

C
Chat-UniVi
649
2
Chat UniVi 13B
Chat-UniVi is a unified visual representation large language model capable of understanding both image and video content.
Image-to-Text
Transformers

C
Chat-UniVi
57
9
Featured Recommended AI Models