Improve model card: Add pipeline tag, description, GitHub link, and sample usage

This PR significantly enhances the model card for the GAS model by:
- Adding the `pipeline_tag: unconditional-image-generation` to the metadata, enabling better discoverability on the Hugging Face Hub.
- Providing a comprehensive description of the model, summarizing its core contributions from the paper.
- Including a direct link to the GitHub repository for easy access to the code.
- Adding a "How to use" section with an official inference code snippet, making it easier for users to get started with the trained model.

Please review and merge this update.

README.md

@@ -1,11 +1,39 @@
 ---
-license: mit
 datasets:
 - bayes-group-diffusion/GAS-teachers
+license: mit
 tags:
 - arxiv:2510.17699
+pipeline_tag: unconditional-image-generation
 ---
 
+# GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver
+
+This repository contains the implementation for **GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver**, a method presented in the paper [GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver](https://arxiv.org/abs/2510.17699).
+
+The work introduces a novel approach to accelerate sampling in diffusion models without compromising generation quality. The **Generalized Solver (GS)** offers a simpler parameterization of the ODE sampler, and when combined with adversarial training, forms the **Generalized Adversarial Solver (GAS)**, which enhances detail fidelity and mitigates artifacts. This method aims to reduce the computational cost of diffusion model sampling from dozens to just a few function evaluations.
+
+![Teaser image](https://github.com/3145tttt/GAS/raw/main/docs/teaser_1920.jpg)
+
+For detailed code, setup instructions, and examples, please refer to the official GitHub repository: [https://github.com/3145tttt/GAS](https://github.com/3145tttt/GAS)
+
+## How to use
+
+To generate images from a trained **GS** checkpoint, you can use the `generate.py` script. Set the `--checkpoint_path` option to the path of your trained model checkpoint.
+
+```bash
+# Generate 50000 images using 2 GPUs and a checkpoint from checkpoint_path
+torchrun --standalone --nproc_per_node=2 generate.py \
+	--config=configs/edm/cifar10.yaml \
+	--outdir=data/teachers/cifar10 \
+	--seeds=50000-99999 \
+	--batch=1024 \
+	--steps=4 \
+	--checkpoint_path=checkpoint_path
+```
+
+For a fair comparison and to avoid leakage of test seeds into the training dataset, we recommend using seeds 50000-99999 for all datasets except MS-COCO, which should use seeds 30000-59999.
+
 ## Citation
 
 ```bibtex