Instructions to use kujiale-ai/controlnet-layout with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kujiale-ai/controlnet-layout with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kujiale-ai/controlnet-layout", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
How do you process the input image?
#3
by laidawang - opened
What preprocessing methods did you use to obtain the control_image? When I testing, I found that some of the segmentation and normalmap preprocessing methods I used were very different from the example images you provided. This will lead to differences in the effects.