---
license: apache-2.0
datasets:
- yuvalkirstain/pickapic_v2
language:
- en
pipeline_tag: text-to-image
---
**Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation** (https://huggingface.co/papers/2402.10210)


![image/png](https://cdn-uploads.huggingface.co/production/uploads/657be24e8d360b690d5b665f/uzhoFO22ZdQ5XjBxxDA1a.png)

# SPIN-Diffusion-iter1

This model is a self-play fine-tuned diffusion model at iteration 1 from [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) using synthetic data based on the winner images of the [yuvalkirstain/pickapic_v2](https://huggingface.co/datasets/yuvalkirstain/pickapic_v2) dataset. We have also made a Gradio Demo at [UCLA-AGI/SPIN-Diffusion-demo-v1](https://huggingface.co/spaces/UCLA-AGI/SPIN-Diffusion-demo-v1).

## Model Details

### Model Description

- Model type: An diffusion model with unet fine-tuned, based on the strucure of stable diffusion 1.5
- Language(s) (NLP): Primarily English
- License: Apache-2.0
- Finetuned from model: runwayml/stable-diffusion-v1-5

### Training hyperparameters
The following hyperparameters were used during training:

- learning_rate: 2.0e-05
- train_batch_size: 8
- distributed_type: multi-GPU
- num_devices: 8
- train_gradient_accumulation_steps: 32
- total_train_batch_size: 2048
- optimizer: AdamW 
- lr_scheduler: "linear"
- lr_warmup_steps: 200
- num_training_steps: 500

  
## Citation
```
@misc{yuan2024self,
      title={Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation}, 
      author={Yuan, Huizhuo and Chen, Zixiang and Ji, Kaixuan and Gu, Quanquan},
      year={2024},
      eprint={2402.10210},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}
```