Update README.md

README.md

@@ -1,3 +1,58 @@
----
-license: apache-2.0
----
+---
+language:
+- en
+base_model:
+- tencent/HunyuanVideo
+- stabilityai/stable-video-diffusion-img2vid-xt
+tag: 
+- text-to-video
+- image-to-video
+- video-to-video
+---
+
+# V1: Human-Centric Video Foundation Model
+
+<p align="center">
+<a href="https://github.com/immortalshadow007/V1" target="_blank">🌐 Github</a>
+
+---
+This repo contains Diffusers-format model weights for V1 Text-to-Video, Image-to-Video models, and Video-to-Video. You can find the inference code on our github repository [V1](https://github.com/immortalshadow007/V1).
+
+## Introduction
+V1 is an open-source human-centric video foundation model. By fine-tuning <a href="https://huggingface.co/tencent/HunyuanVideo">HunyuanVideo</a> on O(10M) high-quality film and television clips, V1 offers three key advantages:
+
+## 🔑 Key Features
+
+### 1. Advanced Model Capabilities
+
+1. **Open-Source Leadership**: The 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.
+
+### 2. 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.
+
+### 3. Multi-Stage Image-to-Video Pretraining
+
+Our multi-stage pretraining pipeline, inspired by the <a href="https://huggingface.co/tencent/HunyuanVideo">HunyuanVideo</a> 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 |
+|-----------------|------------|--------------|-----|
+| V1-Hunyuan-I2V  | 544px960p  | 97           | 24  |
+| V1-Hunyuan-T2V  | 544px960p  | 97           | 24  |
+| V1-SVD-V2V      | 544px960p  | 97           | 24  |
+
+## Usage
+**See the [Guide](https://github.com/immortalshadow007/V1) for details.**
+```