Image-to-Image
Diffusers
Safetensors
ControlNetModel
StableDiffusionXLControlNetInpaintPipeline
ControlNetModel
stable-diffusion-xl
inpainting
light-estimation
relighting
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("pureexe/chromeball-sdxl-ev0", dtype=torch.bfloat16, device_map="cuda")
prompt = "a perfect mirrored reflective chrome ball sphere"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]Chromeball SDXL EV0
THIS IS NOT A PART OF DIFFUSIONLIGHT PAPER
Use a ControlNet to output the chrome ball from SDXL instead of using LoRA which enables the SDXL Turbo to output lighting in one denosing step
If the speed is less of a concern for you and want to focus on the quality. Please check out the LoRA model at DiffusionLight
ControlNet vs LoRA: The SDXL Turbo
TODO: I will explained later that SDXL Turbo makes LoRA impossible to give an input signal in one step. So, we use a control to guide output instead
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Trigger words
| Chromeball | Prompt |
|---|---|
| EV0 | a perfect mirrored reflective chrome ball sphere |
Chromeball generation
TODO: I will update how to generate chrome ball from controlnet in one Unet pass.
PS. This repo is currently supported outing the EV0. We might support different EV in the future.
- Downloads last month
- 19
Model tree for pureexe/chromeball-sdxl-ev0
Base model
stabilityai/stable-diffusion-xl-base-1.0