Instructions to use alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" 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] - Notebooks
- Google Colab
- Kaggle
Denoise of 1.0?
#11
by Hesajon - opened
When inpainting I'm used to specifying a denoise value less than 1, thus keeping some of the original image in the masked area. But it seems that with this controlnet we have to keep the denoise at 1.0? Using a value less than 1 just produces noise in the masked area.
yeah i notice this too