htdong

Wan-Alpha: High-Quality Text-to-Video Generation with Alpha Channel [](https://arxiv.org/pdf/2509.24979) [](https://donghaotian123.github.io/Wan-Alpha/) [](https://github.com/WeChatCV/Wan-Alpha) [](https://huggingface.co/htdong/Wan-Alpha) [](https://huggingface.co/htdong/Wan-AlphaComfyUI) >Qualitative results of video generation using Wan-Alpha. Our model successfully generates various scenes with accurate and clearly rendered transparency. Notably, it can synthesize diverse semi-transparent objects, glowing effects, and fine-grained details such as hair. 🔥 News [2025.09.30] Released Wan-Alpha v1.0, the Wan2.1-14B-T2V–adapted weights and inference code are now open-sourced. | Prompt | Preview Video | Alpha Video | | :---: | :---: | :---: | | "Medium shot. A little girl holds a bubble wand and blows out colorful bubbles that float and pop in the air. The background of this video is transparent. Realistic style." | | | This project is built upon the following excellent open-source projects: DiffSynth-Studio (training/inference framework) Wan2.1 (base video generation model) LightX2V (inference acceleration) WanVideocomfy (inference acceleration) We sincerely thank the authors and contributors of these projects. If you find our work helpful for your research, please consider citing our paper: If you have any questions or suggestions, feel free to reach out via GitHub Issues . We look forward to your feedback!

Wan-Alpha: High-Quality Text-to-Video Generation with Alpha Channel [](https://arxiv.org/pdf/2509.24979) [](https://donghaotian123.github.io/Wan-Alpha/) [](https://github.com/WeChatCV/Wan-Alpha) [](https://huggingface.co/htdong/Wan-Alpha) [](https://huggingface.co/htdong/Wan-AlphaComfyUI) >Qualitative results of video generation using Wan-Alpha. Our model successfully generates various scenes with accurate and clearly rendered transparency. Notably, it can synthesize diverse semi-transparent objects, glowing effects, and fine-grained details such as hair. 🔥 News [2025.09.30] Released Wan-Alpha v1.0, the Wan2.1-14B-T2V–adapted weights and inference code are now open-sourced. | Prompt | Preview Video | Alpha Video | | :---: | :---: | :---: | | "Medium shot. A little girl holds a bubble wand and blows out colorful bubbles that float and pop in the air. The background of this video is transparent. Realistic style." | | | This project is built upon the following excellent open-source projects: DiffSynth-Studio (training/inference framework) Wan2.1 (base video generation model) LightX2V (inference acceleration) WanVideocomfy (inference acceleration) We sincerely thank the authors and contributors of these projects. If you find our work helpful for your research, please consider citing our paper: If you have any questions or suggestions, feel free to reach out via GitHub Issues . We look forward to your feedback!