| license: openrail++ | |
| base_model: stabilityai/stable-diffusion-xl-base-1.0 | |
| tags: | |
| - stable-diffusion-xl | |
| - lora | |
| - diffusers | |
| - text-to-image | |
| widget: | |
| - text: 'a photo of RunchatShell style' | |
| output: | |
| url: "placeholder.jpg" | |
| # SDXL LoRA: RunchatShell | |
| This is a LoRA (Low-Rank Adaptation) model for Stable Diffusion XL fine-tuned on images with the trigger word `RunchatShell`. | |
| ## Usage | |
| ```python | |
| from diffusers import StableDiffusionXLPipeline | |
| import torch | |
| # Load base model | |
| pipe = StableDiffusionXLPipeline.from_pretrained( | |
| "stabilityai/stable-diffusion-xl-base-1.0", | |
| torch_dtype=torch.float16 | |
| ) | |
| # Load LoRA weights | |
| pipe.load_lora_weights("runchat/lora-533d7b31-63fd-42a0-be75-b68de7db171f-RunchatShell") | |
| pipe = pipe.to("cuda") | |
| # Generate image | |
| prompt = "a photo of RunchatShell style" | |
| image = pipe(prompt, num_inference_steps=25, guidance_scale=7.5).images[0] | |
| image.save("output.png") | |
| ``` | |
| ## Training Details | |
| - Base model: stabilityai/stable-diffusion-xl-base-1.0 | |
| - Training steps: 1000 | |
| - Learning rate: 0.0001 | |
| - Batch size: 1 | |
| - LoRA rank: 32 | |
| - Trigger word: `RunchatShell` | |