Add SGMD paper info and improve model card metadata

README.md

@@ -1,20 +1,22 @@
 ---
-license: apache-2.0
-tags:
-  - diffusion-single-file
-  - comfyui
-  - distillation
-  - LoRA
-  - video
-  - video genration
 base_model:
-  - Wan-AI/Wan2.2-I2V-A14B
-pipeline_tags: 
-  - image-to-video
-  - text-to-video
+- Wan-AI/Wan2.2-I2V-A14B
 library_name: diffusers
+license: apache-2.0
+tags:
+- diffusion-single-file
+- comfyui
+- distillation
+- LoRA
+- video
+- video generation
+- SGMD
+pipeline_tag: image-to-video
 ---
-# 🎬 Wan2.2 Distilled Models
+
+# 🎬 Wan2.2 Distilled Models (SGMD)
+
+This repository contains distilled versions of the Wan2.2 models using **SGMD (Score Gradient Matching Distillation)**, as presented in the paper [SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation](https://huggingface.co/papers/2605.30116).
 
 ### ⚡ High-Performance Video Generation with 4-Step Inference
 
@@ -34,6 +36,45 @@ library_name: diffusers
 
 - 2026.04.12: We are excited to release the [Wan2.2-I2V-A14B-4step-720p-high](https://huggingface.co/lightx2v/Wan2.2-Distill-Models/blob/main/wan2.2_i2v_A14b_high_noise_lightx2v_4step_720p_260412.safetensors) and [Wan2.2-I2V-A14B-4step-720p-low](https://huggingface.co/lightx2v/Wan2.2-Distill-Models/blob/main/wan2.2_i2v_A14b_low_noise_lightx2v_4step_720p_260412.safetensors) models. Compared to previous iterations, this version was trained on a high-quality 720p dataset and features an optimized low-noise training algorithm. These enhancements significantly boost the model's performance in fine-grained detail rendering and visual texture.
 
+## 🚀 Quick Usage (Python)
+
+To use these models with the [LightX2V](https://github.com/ModelTC/LightX2V) framework for 4-step inference:
+
+```python
+from lightx2v import LightX2VPipeline
+
+# Initialize pipeline for Wan2.2 I2V task
+pipe = LightX2VPipeline(
+    model_path="lightx2v/Wan2.2-Distill-Models",
+    model_cls="wan2.2_moe",
+    task="i2v",
+)
+
+# Enable offloading to reduce VRAM usage
+pipe.enable_offload(
+    cpu_offload=True,
+    offload_granularity="block",
+    text_encoder_offload=True,
+)
+
+# Create generator for 4-step inference
+pipe.create_generator(
+    attn_mode="sage_attn2",
+    infer_steps=4,
+    height=480,
+    width=832,
+    num_frames=81,
+    guidance_scale=[1.0, 1.0],
+)
+
+# Generate video
+pipe.generate(
+    seed=42,
+    image_path="path/to/your/image.jpg",
+    prompt="A cinematic shot of a sunset over the ocean",
+    save_result_path="output.mp4",
+)
+```
 
 ## 🌟 What's Special?
 
@@ -115,94 +156,13 @@ Generate videos from text descriptions
 | 🎯 **INT8** | `int8_lightx2v_4step` | ~15 GB | LightX2V | ⭐⭐⭐⭐ Fast & Efficient |
 | 🔷 **FP8 ComfyUI** | `scaled_fp8_e4m3_lightx2v_4step_comfyui` | ~15 GB | ComfyUI | ⭐⭐⭐ ComfyUI Ready |
 
-### 📝 Naming Convention
-
-```bash
-# Format: wan2.2_{task}_A14b_{noise_level}_{precision}_lightx2v_4step.safetensors
-
-# I2V Examples:
-wan2.2_i2v_A14b_high_noise_lightx2v_4step.safetensors                       # I2V High Noise - BF16
-wan2.2_i2v_A14b_high_noise_scaled_fp8_e4m3_lightx2v_4step.safetensors      # I2V High Noise - FP8
-wan2.2_i2v_A14b_low_noise_int8_lightx2v_4step.safetensors                  # I2V Low Noise - INT8
-wan2.2_i2v_A14b_low_noise_scaled_fp8_e4m3_lightx2v_4step_comfyui.safetensors  # I2V Low Noise - FP8 ComfyUI
-
-```
-> 💡 **Browse All Models**: [View Full Model Collection →](https://huggingface.co/lightx2v/Wan2.2-Distill-Models/tree/main)
-
 ---
 
-## 🚀 Usage
-
-### Method 1: LightX2V (Recommended ⭐)
-
-**LightX2V is a high-performance inference framework optimized for these models, approximately 2x faster than ComfyUI with better quantization accuracy. Highly recommended!**
-
-#### Quick Start
-
-1. Download model (using I2V FP8 as example)
-```bash
-huggingface-cli download lightx2v/Wan2.2-Distill-Models \
-    --local-dir ./models/wan2.2_i2v \
-    --include "wan2.2_i2v_A14b_high_noise_scaled_fp8_e4m3_lightx2v_4step.safetensors"
-```
-
-```bash
-huggingface-cli download lightx2v/Wan2.2-Distill-Models \
-    --local-dir ./models/wan2.2_i2v \
-    --include "wan2.2_i2v_A14b_low_noise_scaled_fp8_e4m3_lightx2v_4step.safetensors"
-```
-
-> 💡 **Tip**: For T2V models, follow the same steps but replace `i2v` with `t2v` in the filenames
-
-2. Clone LightX2V repository
-
-```bash
-git clone https://github.com/ModelTC/LightX2V.git
-cd LightX2V
-```
-
-3. Install dependencies
-
-```bash
-pip install -r requirements.txt
-```
-Or refer to [Quick Start Documentation](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/getting_started/quickstart.html) to use docker
-
-4. Select and modify configuration file
-
-Choose appropriate configuration based on your GPU memory:
-
-**80GB+ GPUs (A100/H100)**
-- I2V: [wan_moe_i2v_distill.json](https://github.com/ModelTC/LightX2V/blob/main/configs/wan22/wan_moe_i2v_distill.json)
-
-**24GB+ GPUs (RTX 4090)**
-- I2V: [wan_moe_i2v_distill_4090.json](https://github.com/ModelTC/LightX2V/blob/main/configs/wan22/wan_moe_i2v_distill_4090.json)
-
-
-5. Run inference (using [I2V]((https://github.com/ModelTC/LightX2V/blob/main/scripts/wan22/run_wan22_moe_i2v_distill.sh)) as example)
-```bash
-cd scripts
-bash wan22/run_wan22_moe_i2v_distill.sh
-```
-
-> 📝 **Note**: Update model paths in the script to point to your Wan2.2 model. Also refer to [LightX2V Model Structure Documentation](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/getting_started/model_structure.html)
-
-
-#### LightX2V Documentation
-- **Quick Start Guide**: [LightX2V Quick Start](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/getting_started/quickstart.html)
-- **Complete Usage Guide**: [LightX2V Model Structure Documentation](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/getting_started/model_structure.html)
-- **Configuration File Instructions**: [Configuration Files](https://github.com/ModelTC/LightX2V/tree/main/configs/distill)
-- **Quantized Model Usage**: [Quantization Documentation](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/method_tutorials/quantization.html)
-- **Parameter Offloading**: [Offload Documentation](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/method_tutorials/offload.html)
-
----
-
-### Method 2: ComfyUI
+## 🚀 Alternative Usage Methods
 
+### Method 1: ComfyUI
 Please refer to [workflow](https://huggingface.co/lightx2v/Wan2.2-Distill-Models/blob/main/wan2.2_moe_i2v_scale_fp8_comfyui.json)
 
-
-
 ## ⚠️ Important Notes
 
 **Other Components**: These models only contain DIT weights. Additional components needed at runtime:
@@ -211,14 +171,11 @@ Please refer to [workflow](https://huggingface.co/lightx2v/Wan2.2-Distill-Models
    - VAE encoder/decoder
    - Tokenizer
 
-   Please refer to [LightX2V Documentation](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/getting_started/model_structure.html) for instructions on organizing the complete model directory.
-
+Please refer to [LightX2V Documentation](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/getting_started/model_structure.html) for instructions on organizing the complete model directory.
 
 ## 🤝 Community
 
 - **GitHub Issues**: https://github.com/ModelTC/LightX2V/issues
 - **HuggingFace**: https://huggingface.co/lightx2v/Wan2.2-Distill-Models
 
-If you find this project helpful, please give us a ⭐ on [GitHub](https://github.com/ModelTC/LightX2V)
-
-</div>
+If you find this project helpful, please give us a ⭐ on [GitHub](https://github.com/ModelTC/LightX2V)