Update README.md

README.md

@@ -1,8 +1,46 @@
 ---
 license: mit
+pipeline_tag: text-to-image
+tags:
+- diffusion
+- efficient
+- quantization
+- Diffusers
+- StableDiffusionXLPipeline
 ---
 
-set up the environment for mixdq:
+# MixDQ Model Card
+
+## Model Description
+
+MixDQ is a mixed precision quantization methods that compress the memory and computational usage of text-to-image diffusion models while preserving genration quality.
+It supports few-step diffusion models (e.g., SDXL-turbo, LCM-lora) to construct both fast and tiny diffusion models. Efficient CUDA kernel implemention is provided for practical resource savings.
+
+<img src="https://github.com/A-suozhang/MyPicBed/raw/master/img/mixdq_model_card_0.jpg" width="600">
+
+
+## Model Sources
+
+for more information, please refer to:
+
+- Project Page: [https://a-suozhang.xyz/mixdq.github.io/](https://a-suozhang.xyz/mixdq.github.io/).
+- Arxiv paper: [https://arxiv.org/abs/2405.17873](https://arxiv.org/abs/2405.17873)
+- Github Repository: [https://github.com/A-suozhang/MixDQ](https://github.com/A-suozhang/MixDQ)
+
+## Evaluation
+
+We evaluate the MixDQ model using various metrics, including FID (fidelity), CLIPScore (image-text alignment), and ImageReward (human preference). MixDQ can achieve W8A8 quantization without performance loss. The differences between images generated by MixDQ and those generated by FP16 models are negligible.
+
+| Method     | FID (↓) | ClipScore | ImageReward |
+|------------|---------|-----------|-------------|
+| FP16       | 17.15   | 0.2722    | 0.8631      |
+| MixDQ-W8A8 | 17.03   | 0.2703    | 0.8415      |
+| MixDQ-W5A8 | 17.23   | 0.2697    | 0.8307      |
+
+## Usage
+
+
+install the prerequisite for Mixdq:
 ```shell
   pip install -i https://pypi.org/simple/ mixdq-extension --upgrade
 ```
@@ -47,7 +85,10 @@ run the pipeline:
   image.save('mixdq_pipeline.png')
 ```
 
+
+
 Performance tested on NVIDIA 4080:
+
 | UNet Latency (ms) | No CUDA Graph | With CUDA Graph |
 |-------------------|---------------|-----------------|
 | FP16 version      | 44.6          | 36.1            |