Instructions to use InstantX/FLUX.1-dev-Controlnet-Canny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use InstantX/FLUX.1-dev-Controlnet-Canny with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("InstantX/FLUX.1-dev-Controlnet-Canny", 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
ComfyUI Compatibility
#4
by orabazes - opened
The 1024x1024 Canny Lora does not load in ComfyUI. A supported version would be very much appreciated.
The union ControlNet performs great but is a bit heavy for large workflows. Would be nice to have this one implemented to ComfyUI too (Xlabs ControlNets are very lacking compared to those).
That's great news, gonna test it right away.
EDIT : It works great ! I can finally use it without overloading my VRAM with Union. Thanks, you made my day !

