Add model card for VGT

This PR adds a comprehensive model card for the VGT (Visual Generation Tuning) model, based on the official paper and GitHub repository.

The updates include:
- A clear description of the model and its capabilities.
- Links to the paper ([Visual Generation Tuning](https://huggingface.co/papers/2511.23469)) and the official GitHub repository ([https://github.com/hustvl/VGT](https://github.com/hustvl/VGT)).
- The `pipeline_tag: text-to-image` metadata for improved discoverability on the Hugging Face Hub, reflecting the model's core functionality.
- Verbatim installation instructions and inference code snippets from the GitHub README to help users get started quickly, ensuring no code is made up.
- Integration of key highlights, a "What is VGT?" summary, a table of pretrained models, and the citation information.
- Visual examples from the GitHub repository.

Please review and merge this PR.

README.md

@@ -1,3 +1,125 @@
----
-license: mit
----
+---
+license: mit
+pipeline_tag: text-to-image
+---
+
+<div align="center">
+  <img src="https://github.com/hustvl/VGT/raw/main/asserts/vgt_logo.png" alt="VGT" width="200">
+  <h2>🚀 VGT: Visual Generation Tuning</h2>
+  **_Unleashing Visual Generation Capabilities from Any Pretrained VLM_**
+</div>
+
+This repository hosts models from the paper [Visual Generation Tuning](https://huggingface.co/papers/2511.23469).
+
+**VGT (Visual Generation Tuning)** is a groundbreaking paradigm designed to stimulate the underlying capabilities of visual generation within any pretrained Vision-Language Model (VLM). It significantly mitigates alignment costs and accelerates the convergence of autoregressive modeling in the continuous space, enabling efficient and high-quality image generation from text descriptions.
+
+*   **Paper**: [Visual Generation Tuning](https://huggingface.co/papers/2511.23469)
+*   **Code**: [https://github.com/hustvl/VGT](https://github.com/hustvl/VGT)
+
+<div align="center">
+  <img src="https://github.com/hustvl/VGT/raw/main/asserts/case_show.png" alt="VGT Generated Images">
+</div>
+
+---
+
+## ✨ Highlights
+
+-   **🎯 Novel Paradigm**: Transform ANY pretrained Vision-Language Model into a powerful image generator through efficient visual generation tuning
+-   **⚡ 20× Speedup**: Achieve dramatically faster convergence compared to vanilla VAE-based autoregressive models
+-   **📊 SOTA Performance**: GenEval **0.83** and DPG-Bench **81.28** with minimal training data
+-   **🚀 Extreme Data Efficiency**: Reach GenEval 0.55 in just 10K iterations, 0.60 in 30K iterations
+-   **🔄 Parallel Inference**: QueryAR mechanism enables 16× parallel decoding while maintaining high-quality generation
+-   **🎨 Superior Reconstruction**: 26.67 PSNR and 0.50 rFID at 28× compression ratio, outperforming specialized VAEs
+
+---
+
+## 💡 What is VGT?
+
+**VGT (Visual Generation Tuning)** is a groundbreaking paradigm that answers a fundamental question:
+
+*Can we directly leverage the well-aligned semantic representations in pretrained VLMs to enable visual generation capabilities?*
+
+VGT bridges this gap through two key innovations:
+
+**1. VGT-AE (Visual Generation Tuning - AutoEncoder)**
+-   Aligns semantic encoders from pretrained VLMs with latent representations of pixel decoders
+-   Achieves **26.67 PSNR** and **0.50 rFID** at **28× compression**, outperforming specialized VAEs
+
+**2. VGT-AR (Visual Generation Tuning - AutoRegressive)**
+-   Position-query mechanism for autoregressive formulation with partial parallel decoding
+-   Dramatically accelerates convergence (**20× speedup**) compared to vanilla VAE-based models
+
+---
+
+## 🚀 Getting Started
+
+### Installation
+
+```bash
+# Clone the repository
+git clone https://github.com/hustvl/VGT.git
+cd VGT
+
+# Install dependencies
+conda create -n vgt python=3.10
+conda activate vgt
+pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/cu121
+pip install mmengine xtuner tqdm timm
+pip install diffusers transformers==4.57.1
+pip install flash-attn --no-build-isolation
+```
+
+### Pretrained Models
+
+We provide VGT-tuned models based on Qwen2.5-VL and InternVL3 (448px):
+
+| Model | Base Model | GenEval | DPG-Bench | Download |
+|:------|:-----------|:-------:|:---------:|:--------:|
+| VGT-InternVL3-1.6B-Pretrain | InternVL3-1.6B | 0.58 | 73.05 | [🤗 HuggingFace](https://huggingface.co/hustvl/vgt_internvl3_1_6B_pretrain) |
+| VGT-InternVL3-1.6B-SFT | InternVL3-1.6B | 0.83 | 76.33 | [🤗 HuggingFace](https://huggingface.co/hustvl/vgt_internvl3_1_6B_sft) |
+| VGT-Qwen2.5-VL-2B-Pretrain | Qwen2.5-VL-2B | 0.63 | 78.02 | [🤗 HuggingFace](https://huggingface.co/hustvl/vgt_qwen25vl_2B_pretrain) |
+| VGT-Qwen2.5-VL-2B-SFT | Qwen2.5-VL-2B | 0.83 | 81.28 | [🤗 HuggingFace](https://huggingface.co/hustvl/vgt_qwen25vl_2B_sft) |
+
+### Inference
+
+Download the sft model checkpoint:
+
+```bash
+cd VGT
+mkdir ckpts
+hf download hustvl/vgt_qwen25vl_2B_sft --repo-type model --local-dir ckpts/hustvl/vgt_qwen25vl_2B_sft
+hf download hustvl/vgt_internvl3_1_6B_sft --repo-type model --local-dir ckpts/hustvl/vgt_internvl3_1_6B_sft
+```
+
+Generate images from text prompts:
+
+```bash
+export PYTHONPATH=./:$PYTHONPATH
+
+# use InternVL3-1.6B generate
+python scripts/sample_text_list_vgt_intervl3_0.6B.py
+```
+
+> Note: We found that under the same training method, VGT-Qwen2.5-VL-2B performs better in face generation, while VGT-InternVL3-1.6B performs better in generating landscapes, light and shadow, and animals. You can explore on your own.
+
+---
+
+## 📝 Citation
+
+If you find our work useful, please cite our paper:
+
+```bibtex
+@misc{guo2025vgt,
+      title={Visual Generation Tuning}, 
+      author={Jiahao Guo and Sinan Du and Jingfeng Yao and Wenyu Liu and Bo Li and Haoxiang Cao and Kun Gai and Chun Yuan and Kai Wu and Xinggang Wang},
+      year={2025},
+      eprint={2511.23469},
+      archivePrefix={arXiv},
+}
+```
+
+---
+
+## 📄 License
+
+This project is released under the MIT License. See [LICENSE](LICENSE) for details.