🌐 Github · 👋 Playground · 💬 Discord
--- This repo contains Diffusers-format model weights for SkyReels V1 Text-to-Video models. You can find the inference code on our github repository [SkyReels-V1](https://github.com/SkyworkAI/SkyReels-V1). ## Introduction SkyReels V1 is the first and most advanced open-source human-centric video foundation model. By fine-tuning HunyuanVideo on O(10M) high-quality film and television clips, Skyreels V1 offers three key advantages: 1. **Open-Source Leadership**: Our Text-to-Video model achieves state-of-the-art (SOTA) performance among open-source models, comparable to proprietary models like Kling and Hailuo. 2. **Advanced Facial Animation**: Captures 33 distinct facial expressions with over 400 natural movement combinations, accurately reflecting human emotions. 3. **Cinematic Lighting and Aesthetics**: Trained on high-quality Hollywood-level film and television data, each generated frame exhibits cinematic quality in composition, actor positioning, and camera angles. ## 🔑 Key Features ### 1. Self-Developed Data Cleaning and Annotation Pipeline Our model is built on a self-developed data cleaning and annotation pipeline, creating a vast dataset of high-quality film, television, and documentary content. - **Expression Classification**: Categorizes human facial expressions into 33 distinct types. - **Character Spatial Awareness**: Utilizes 3D human reconstruction technology to understand spatial relationships between multiple people in a video, enabling film-level character positioning. - **Action Recognition**: Constructs over 400 action semantic units to achieve a precise understanding of human actions. - **Scene Understanding**: Conducts cross-modal correlation analysis of clothing, scenes, and plots. ### 2. Multi-Stage Image-to-Video Pretraining Our multi-stage pretraining pipeline, inspired by the HunyuanVideo design, consists of the following stages: - **Stage 1: Model Domain Transfer Pretraining**: We use a large dataset (O(10M) of film and television content) to adapt the text-to-video model to the human-centric video domain. - **Stage 2: Image-to-Video Model Pretraining**: We convert the text-to-video model from Stage 1 into an image-to-video model by adjusting the conv-in parameters. This new model is then pretrained on the same dataset used in Stage 1. - **Stage 3: High-Quality Fine-Tuning**: We fine-tune the image-to-video model on a high-quality subset of the original dataset, ensuring superior performance and quality. ## Model Introduction | Model Name | Resolution | Video Length | FPS | Download Link | |-----------------|------------|--------------|-----|---------------| | SkyReels-V1-Hunyuan-I2V | 544px960p | 97 | 24 | 🤗 [Download](https://huggingface.co/Skywork/SkyReels-V1-Hunyuan-I2V) | | SkyReels-V1-Hunyuan-T2V (Current) | 544px960p | 97 | 24 | 🤗 [Download](https://huggingface.co/Skywork/SkyReels-V1-Hunyuan-T2V) | ## Usage **See the [Guide](https://github.com/SkyworkAI/SkyReels-V1) for details.** ## Citation ```BibTeX @misc{SkyReelsV1, author = {SkyReels-AI}, title = {Skyreels V1: Human-Centric Video Foundation Model}, year = {2025}, publisher = {Huggingface}, journal = {Huggingface repository}, howpublished = {\url{https://huggingface.co/Skywork/SkyReels-V1-Hunyuan-T2V}} } ```