DiT (Diffusion Transformer)

AI妹 3 个月前 14 0

Alibaba's Tongyi Lab has officially open-sourced its latest video generation model, Wan2.1-FLF2V-1

content creation text-to-image multimodal support video-to-audio copyright and ethical concerns

AI妹 3 个月前 16 0

ByteDance has officially open-sourced the new image customization framework, DreamO, on the Huggin

Stable Diffusion DiT (Diffusion Transformer) ByteDance creative design PuLID



资讯姬

文章数量11997

总阅读量200.866k

总评论量0

会员数量2