Duplicate from htdong/Wan-Alpha

Co-authored-by: Dong Haotian <htdong@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,38 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/girl_pha.gif filter=lfs diff=lfs merge=lfs -text
+assets/girl.gif filter=lfs diff=lfs merge=lfs -text
+assets/teaser.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,175 @@
+---
+base_model:
+- Wan-AI/Wan2.1-T2V-14B
+license: apache-2.0
+pipeline_tag: text-to-video
+tags:
+  - rgba
+  - transparency
+---
+
+<div align="center">
+
+  <h1>
+    Wan-Alpha
+  </h1>
+
+  <h3>Wan-Alpha: High-Quality Text-to-Video Generation with Alpha Channel</h3>
+
+
+
+[![arXiv](https://img.shields.io/badge/arXiv-2509.24979-b31b1b)](https://arxiv.org/pdf/2509.24979)
+[![HF Paper](https://img.shields.io/badge/HuggingFace-Paper-blue)](https://huggingface.co/papers/2509.24979)
+[![Project Page](https://img.shields.io/badge/Project_Page-Link-green)](https://donghaotian123.github.io/Wan-Alpha/)
+[![GitHub](https://img.shields.io/badge/GitHub-Repo-black?logo=github)](https://github.com/WeChatCV/Wan-Alpha)
+[![🤗 HuggingFace](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Model-orange)](https://huggingface.co/htdong/Wan-Alpha)
+[![ComfyUI](https://img.shields.io/badge/ComfyUI-Version-blue)](https://huggingface.co/htdong/Wan-Alpha_ComfyUI)
+[![🤗 HuggingFace](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Model_v2.0-yellow)](https://huggingface.co/htdong/Wan-Alpha-v2.0)
+
+</div>
+
+<img src="assets/teaser.png" alt="Wan-Alpha Qualitative Results" style="max-width: 100%; height: auto;">
+
+>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.
+
+---
+
+## Abstract
+RGBA video generation, which includes an alpha channel to represent transparency, is gaining increasing attention across a wide range of applications. However, existing methods often neglect visual quality, limiting their practical usability. In this paper, we propose Wan-Alpha, a new framework that generates transparent videos by learning both RGB and alpha channels jointly. We design an effective variational autoencoder (VAE) that encodes the alpha channel into the RGB latent space. Then, to support the training of our diffusion transformer, we construct a high-quality and diverse RGBA video dataset. Compared with state-of-the-art methods, our model demonstrates superior performance in visual quality, motion realism, and transparency rendering. Notably, our model can generate a wide variety of semi-transparent objects, glowing effects, and fine-grained details such as hair strands. The released model is available on our website: this https URL .
+
+---
+
+## 🔥 News
+* **[2025.09.30]** Released Wan-Alpha v1.0, the Wan2.1-14B-T2V–adapted weights and inference code are now open-sourced.
+
+---
+## 🌟 Showcase
+
+### Text-to-Video Generation with Alpha Channel
+
+
+| 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." | <img src="assets/girl.gif" width="320" height="180" style="object-fit:contain; display:block; margin:auto;"/> | <img src="assets/girl_pha.gif" width="335" height="180" style="object-fit:contain; display:block; margin:auto;"/> |
+
+### For more results, please visit [Our Website](https://donghaotian123.github.io/Wan-Alpha/)
+
+## 🚀 Quick Start
+
+### 1. Environment Setup
+```bash
+# Clone the project repository
+git clone https://github.com/WeChatCV/Wan-Alpha.git
+cd Wan-Alpha
+
+# Create and activate Conda environment
+conda create -n Wan-Alpha python=3.11 -y
+conda activate Wan-Alpha
+
+# Install dependencies
+pip install -r requirements.txt
+```
+
+### 2. Model Download
+Download [Wan2.1-T2V-14B](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B)
+
+Download [Lightx2v-T2V-14B](https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Lightx2v/lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16.safetensors)
+
+Download [Wan-Alpha VAE](https://huggingface.co/htdong/Wan-Alpha)
+
+### 🧪 Usage
+You can test our model through:
+```bash
+torchrun --nproc_per_node=8 --master_port=29501 generate_dora_lightx2v.py --size 832*480\
+         --ckpt_dir "path/to/your/Wan-2.1/Wan2.1-T2V-14B" \
+         --dit_fsdp --t5_fsdp --ulysses_size 8 \
+         --vae_lora_checkpoint "path/to/your/decoder.bin" \
+         --lora_path "path/to/your/epoch-13-1500.safetensors" \
+         --lightx2v_path "path/to/your/lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16.safetensors" \
+         --sample_guide_scale 1.0 \
+         --frame_num 81 \
+         --sample_steps 4 \
+         --lora_ratio 1.0 \
+         --lora_prefix "" \
+         --prompt_file ./data/prompt.txt \
+         --output_dir ./output 
+```
+You can specify the weights of `Wan2.1-T2V-14B` with `--ckpt_dir`, `LightX2V-T2V-14B with` `--lightx2v_path`, `Wan-Alpha-VAE` with `--vae_lora_checkpoint`, and `Wan-Alpha-T2V` with `--lora_path`. Finally, you can find the rendered RGBA videos with a checkerboard background and PNG frames at `--output_dir`.
+
+**Prompt Writing Tip:** You need to specify that the background of the video is transparent, the visual style, the shot type (such as close-up, medium shot, wide shot, or extreme close-up), and a description of the main subject. Prompts support both Chinese and English input.
+
+```bash
+# An example of prompt.
+This video has a transparent background. Close-up shot. A colorful parrot flying. Realistic style.
+```
+
+### 🔨 Official ComfyUI Version
+
+Note: We have reorganized our models to ensure they can be easily loaded into ComfyUI. Please note that these models differ from the ones mentioned above.
+
+1. Download models
+- The Wan DiT base model: [wan2.1_t2v_14B_fp16.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_t2v_14B_fp16.safetensors)
+- The Wan text encoder: [umt5_xxl_fp8_e4m3fn_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)
+- The LightX2V model: [lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Lightx2v/lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16.safetensors)
+- Our RGBA Dora: [epoch-13-1500_changed.safetensors](https://huggingface.co/htdong/Wan-Alpha_ComfyUI/blob/main/epoch-13-1500_changed.safetensors)
+- Our RGB VAE Decoder: [wan_alpha_2.1_vae_rgb_channel.safetensors.safetensors](https://huggingface.co/htdong/Wan-Alpha_ComfyUI/blob/main/wan_alpha_2.1_vae_rgb_channel.safetensors.safetensors)
+- Our Alpha VAE Decoder: [wan_alpha_2.1_vae_alpha_channel.safetensors.safetensors](https://huggingface.co/htdong/Wan-Alpha_ComfyUI/blob/main/wan_alpha_2.1_vae_alpha_channel.safetensors.safetensors)
+
+2. Copy the files into the `ComfyUI/models` folder and organize them as follows:
+
+```
+ComfyUI/models
+├── diffusion_models
+│   └── wan2.1_t2v_14B_fp16.safetensors
+├── loras
+│   ├── epoch-13-1500_changed.safetensors
+│   └── lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16.safetensors
+├── text_encoders
+│   └── umt5_xxl_fp8_e4m3fn_scaled.safetensors
+├── vae
+│   ├── wan_alpha_2.1_vae_alpha_channel.safetensors.safetensors
+│   └── wan_alpha_2.1_vae_rgb_channel.safetensors.safetensors
+```
+
+3. Install our custom RGBA video previewer and PNG frames zip packer. Copy the file [RGBA_save_tools.py](comfyui/RGBA_save_tools.py) into the `ComfyUI/custom_nodes` folder.
+
+- Thanks to @mr-lab for an improved WebP version! You can find it in this [issue](https://github.com/WeChatCV/Wan-Alpha/issues/4).
+
+4. Example workflow: [wan_alpha_t2v_14B.json](comfyui/wan_alpha_t2v_14B.json)
+
+<img src="comfyui/comfyui.jpg" style="margin:auto;"/>
+
+
+## 🤝 Acknowledgements
+
+This project is built upon the following excellent open-source projects:
+* [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) (training/inference framework)
+* [Wan2.1](https://github.com/Wan-Video/Wan2.1) (base video generation model)
+* [LightX2V](https://github.com/ModelTC/LightX2V) (inference acceleration)
+* [WanVideo_comfy](https://huggingface.co/Kijai/WanVideo_comfy) (inference acceleration)
+
+We sincerely thank the authors and contributors of these projects.
+
+---
+
+## ✏ Citation
+
+If you find our work helpful for your research, please consider citing our paper:
+
+```bibtex
+@misc{dong2025wanalpha,
+      title={Wan-Alpha: High-Quality Text-to-Video Generation with Alpha Channel}, 
+      author={Haotian Dong and Wenjing Wang and Chen Li and Di Lin},
+      year={2025},
+      eprint={2509.24979},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2509.24979}, 
+}
+```
+
+---
+
+## 📬 Contact Us
+
+If you have any questions or suggestions, feel free to reach out via [GitHub Issues](https://github.com/WeChatCV/Wan-Alpha/issues) . We look forward to your feedback!

decoder.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec6b6107d8033c0d1b40a7d64e7c09e1594725f56ba60cb40ffd8be8b926e89
+size 635538952

epoch-13-1500.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0f54c4655589eb0862c617221902c53123447690ef4d4fac703030ccf23644
+size 311645240