-
论文标题:MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation -
论文链接:https://arxiv.org/abs/2401.04468 -
项目地址:https://magicvideov2.github.io/
-
论文标题:PixelLM:Pixel Reasoning with Large Multimodal Model -
论文链接:https://arxiv.org/pdf/2312.02228.pdf -
项目地址:https://pixellm.github.io/
-
论文标题:Vista-LLaMA:Reliable Video Narrator via Equal Distance to Visual Tokens -
论文链接:https://arxiv.org/pdf/2312.08870.pdf -
项目地址:https://jinxxian.github.io/Vista-LLaMA/
-
论文标题:COSA: Concatenated Sample Pretrained Vision-Language Foundation Model -
论文链接:https://arxiv.org/pdf/2306.09085.pdf -
项目主页:https://github.com/TXH-mercury/COSA
-
论文标题:MagicAnimate:Temporally Consistent Human Image Animation using Diffusion Model -
论文链接:https://arxiv.org/pdf/2311.16498.pdf -
项目地址:https://showlab.github.io/magicanimate/
-
论文标题:DREAM-Talk:Diffusion-based Realistic Emotional Audio-driven Method for Single Image Talking Face Generation -
论文链接:https://arxiv.org/pdf/2312.13578.pdf -
项目地址:https://dreamtalkemo.github.io/
-
论文标题:Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method -
论文链接:https://arxiv.org/pdf/2312.12030.pdf
-
论文标题:Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models -
论文链接:https://arxiv.org/pdf/2307.10711.pdf
-
论文标题;Harnessing Diffusion Models for Visual Perception with Meta Prompts -
论文链接:https://arxiv.org/pdf/2312.14733.pdf
© 版权声明
文章版权归作者所有,未经允许请勿转载。
THE END
暂无评论内容