Update README.md

README.md

@@ -12,20 +12,29 @@ pipeline_tags:
 library_name: diffusers
 pipeline_tag: image-to-video
 ---
+
 # Hy1.5-Quantized-Models
 
-This repository contains quantized models for [HunyuanVideo-1.5](https://huggingface.co/tencent/HunyuanVideo-1.5) optimized for use with [LightX2V](https://github.com/ModelTC/LightX2V). These quantized models significantly reduce memory usage while maintaining high-quality video generation performance.
+<img src="https://raw.githubusercontent.com/ModelTC/LightX2V/main/assets/img_lightx2v.png" width="75%" />
+
+---
+
+🤗 [HuggingFace](https://huggingface.co/lightx2v/Hy1.5-Quantized-Models) | [GitHub](https://github.com/ModelTC/LightX2V) | [License](https://opensource.org/licenses/Apache-2.0)
+
+---
+
+This repository contains quantized models for HunyuanVideo-1.5 optimized for use with LightX2V. These quantized models significantly reduce memory usage while maintaining high-quality video generation performance.
 
 ## 📋 Model List
 
 ### DIT (Diffusion Transformer) Models
 
-- **`hy15_720p_i2v_fp8_e4m3_lightx2v.safetensors`** - 720p Image-to-Video quantized DIT model
-- **`hy15_720p_t2v_fp8_e4m3_lightx2v.safetensors`** - 720p Text-to-Video quantized DIT model
+* **`hy15_720p_i2v_fp8_e4m3_lightx2v.safetensors`** - 720p Image-to-Video quantized DIT model
+* **`hy15_720p_t2v_fp8_e4m3_lightx2v.safetensors`** - 720p Text-to-Video quantized DIT model
 
 ### Encoder Models
 
-- **`hy15_qwen25vl_llm_encoder_fp8_e4m3_lightx2v.safetensors`** - Quantized text encoder (Qwen2.5-VL LLM Encoder)
+* **`hy15_qwen25vl_llm_encoder_fp8_e4m3_lightx2v.safetensors`** - Quantized text encoder (Qwen2.5-VL LLM Encoder)
 
 ## 🚀 Quick Start
 
@@ -195,9 +204,9 @@ pipe.generate(
 
 These models use **FP8-E4M3** quantization with the **SGL (SGLang) kernel** scheme (`fp8-sgl`). This quantization format provides:
 
-- **Significant memory reduction**: Up to 50% reduction in VRAM usage
-- **Maintained quality**: Minimal quality degradation compared to full precision models
-- **Faster inference**: Optimized kernels for accelerated computation
+* **Significant memory reduction**: Up to 50% reduction in VRAM usage
+* **Maintained quality**: Minimal quality degradation compared to full precision models
+* **Faster inference**: Optimized kernels for accelerated computation
 
 ### Requirements
 
@@ -220,22 +229,22 @@ For more details on quantization schemes, please refer to the [LightX2V Quantiza
 
 Using quantized models provides:
 
-- **Lower VRAM Requirements**: Enables running on GPUs with less memory (e.g., RTX 4090 24GB)
-- **Faster Inference**: Optimized quantized kernels accelerate computation
-- **Quality Preservation**: FP8 quantization maintains high visual quality
+* **Lower VRAM Requirements**: Enables running on GPUs with less memory (e.g., RTX 4090 24GB)
+* **Faster Inference**: Optimized quantized kernels accelerate computation
+* **Quality Preservation**: FP8 quantization maintains high visual quality
 
 ## 🔗 Related Resources
 
-- [LightX2V GitHub Repository](https://github.com/ModelTC/LightX2V)
-- [LightX2V Documentation](https://lightx2v-en.readthedocs.io/en/latest/)
-- [HunyuanVideo-1.5 Original Model](https://huggingface.co/tencent/HunyuanVideo-1.5)
-- [LightX2V Examples](https://github.com/ModelTC/LightX2V/tree/main/examples)
+* [LightX2V GitHub Repository](https://github.com/ModelTC/LightX2V)
+* [LightX2V Documentation](https://lightx2v-en.readthedocs.io/en/latest/)
+* [HunyuanVideo-1.5 Original Model](https://huggingface.co/tencent/HunyuanVideo-1.5)
+* [LightX2V Examples](https://github.com/ModelTC/LightX2V/tree/main/examples)
 
 ## 📝 Notes
 
-- **Important**: All advanced configurations (including `enable_quantize()`) must be called **before** `create_generator()`, otherwise they will not take effect.
-- The original HunyuanVideo-1.5 model weights are still required. These quantized models are used in conjunction with the original model structure.
-- For best performance, we recommend using SageAttention 2 (`sage_attn2`) as the attention mode.
+* **Important**: All advanced configurations (including `enable_quantize()`) must be called **before** `create_generator()`, otherwise they will not take effect.
+* The original HunyuanVideo-1.5 model weights are still required. These quantized models are used in conjunction with the original model structure.
+* For best performance, we recommend using SageAttention 2 (`sage_attn2`) as the attention mode.
 
 ## 🤝 Citation
 
@@ -254,4 +263,4 @@ If you use these quantized models in your research, please cite:
 
 ## 📄 License
 
-This model is released under the Apache 2.0 License, same as the original HunyuanVideo-1.5 model.
+This model is released under the Apache 2.0 License, same as the original HunyuanVideo-1.5 model.