Create model card and add metadata

README.md

@@ -0,0 +1,46 @@
+---
+library_name: transformers
+pipeline_tag: text-to-image
+license: other
+---
+
+# InstanceControl: Sa2va-Instance-4B (Stage 1)
+
+This repository contains the `Sa2va-Instance-4B` checkpoint, which serves as **Stage 1** (Instance Parsing Model) for **InstanceControl**, presented in the paper [InstanceControl: Controllable Complex Image Generation without Instance Labeling](https://huggingface.co/papers/2606.31924).
+
+* **Project Page:** [InstanceControl Homepage](https://instancecontrol.github.io/InstanceControl/)
+* **GitHub Repository:** [InstanceControl GitHub](https://github.com/liuxiaoyu1104/InstanceControl)
+* **Paper:** [arXiv:2606.31924](https://huggingface.co/papers/2606.31924)
+
+## Model Description
+
+InstanceControl is a multi-instance controllable generation method that eliminates the need for manual instance labeling. It uses a Vision-Language Model (VLM)—specifically this `Sa2va-Instance-4B` model—to automatically parse instance descriptions from text prompts and predict instance masks based on visual conditions (such as Canny edges, depth, or HED).
+
+## Usage
+
+For detailed instructions on setup, environment installation, and running the inference pipeline, please refer to the [official GitHub repository](https://github.com/liuxiaoyu1104/InstanceControl).
+
+### Predict Instance Masks (Stage 1)
+
+You can run the model to predict instance masks using the following command:
+
+```bash
+python stage1_Sa2VA/projects/llava_sam2/evaluation/gcg_eval_our_folders.py \
+  --model_path /path/to/Sa2va-Instance-4B \
+  --image_dir ./example/canny \
+  --json_dir ./example/json \
+  --save_dir ./results/json_pred_canny
+```
+
+## Citation
+
+If you find this project useful, please cite the authors' work:
+
+```bibtex
+@article{liu2026instancecontrol,
+  title={InstanceControl: Controllable Complex Image Generation without Instance Labeling},
+  author={Xiaoyu Liu and Huan Wang and Fan Li and Zhixin Wang and Jiaqi Xu and Ming Liu and Wangmeng Zuo},
+  journal={arXiv preprint arXiv:2606.31924},
+  year={2026}
+}
+```