Excited to share our two #CVPR2026 papers FlowPortal and LLSA, for background replacement & relighting and a trainable sparse attention mechanism that reduces attention complexity from O(N²) to O(N log N).
- 𝐅𝐑𝐄𝐒𝐂𝐎 is now integrated into Hugging Face🤗. A web demo and a Diffusers pipeline are available. See github.com/williamyang199… for the details. Info for our poster at #CVPR2024 today: Poster Session 2 Arch 4A-E #378, 17:15 - 18:45😆
- Our tutorial on "New Era of Artificial Intelligence: Unleashing the Power of Large Models in Visual Applications" was successfully held on ISCAS 2024😋. Now, we are happy to share our tutorial slides👀. Please find it at williamyang1991.github.io/projects/ISCAS…
- Excited to share 𝐅𝐑𝐄𝐒𝐂𝐎, accepted by #CVPR2024, for generating coherent videos with #Stable_Diffusion and is more robust to large motions than our previous work Rerender-A-Video. Code is released and try it at: github.com/williamyang199…
- Excited to share 𝐑𝐞𝐫𝐞𝐧𝐝𝐞𝐫-𝐀-𝐕𝐢𝐝𝐞𝐨, accepted by #SIGGRAPH_Asia 2023, for generating fantastic and coherent videos with #Stable_Diffusion and #Ebsynth. Code is released and try it at: github.com/williamyang199…Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page: huggingface.co/papers/2306.07… Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring
