| license: cc-by-nc-sa-4.0 | |
| tags: | |
| - image-generation | |
| - diffusion | |
| - lora | |
| - CatVTON | |
| # CatVTON LoRA Model | |
| ## Model Description | |
| This is a LoRA fine-tuned model based on the CatVTON pipeline for virtual try-on tasks. It uses a pre-trained Stable Diffusion inpainting model combined with attention mechanisms from CatVTON. | |
| ## Training | |
| - **Base Model**: `booksforcharlie/stable-diffusion-inpainting` | |
| - **Attention Checkpoint**: `zhengchong/CatVTON` | |
| - **LoRA Rank**: 4 | |
| - **Epochs**: 10 | |
| - **Batch Size**: 8 | |
| - **Learning Rate**: 1e-4 | |
| ## Usage | |
| ```python | |
| from peft import PeftModel, LoraConfig | |
| from diffusers import StableDiffusionInpaintPipeline | |
| base_model = StableDiffusionInpaintPipeline.from_pretrained("booksforcharlie/stable-diffusion-inpainting") | |
| lora_model = PeftModel.from_pretrained(base_model.unet, "Coldbrew9/wheel-CatVTON") |