multimodal understanding

AI妹 3 个月前 15 0

ByteDance has released a new open-source multimodal foundation model named BAGEL, featuring 7 bill

Qwen2.5-VL SD3 Mixture of Transformers (MoT) image editing Hugging Face

AI妹 3 个月前 12 0

Recently, Princeton University, ByteDance, Tsinghua University, and Peking University have teamed

diffusion model UniGRPO image inpainting gpt-4 modality-agnostic design



资讯姬

文章数量11999

总阅读量201.328k

总评论量0

会员数量2