Instructions to use neuralvfx/LibreFlux-SAM-ControlNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use neuralvfx/LibreFlux-SAM-ControlNet with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("neuralvfx/LibreFlux-SAM-ControlNet", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
ComfyUI workflow?
This looks great, can I use it in Comfyui? which models to download for Comfyui use? does it work with Z-Image or Flux 2 or Flux Klein 9b? Thanks
Thanks!
This ControlNet is built specifically for LibreFlux (a de-distilled version of Flux.1.dev), so it won’t directly work with standard Flux models like Flux 1, Flux 2, or Klein. If you want to use it in ComfyUI, I’ve put together custom nodes here (the page includes instructions on exactly which models to download): https://github.com/NeuralVFX/LibreFLUX-ComfyUI
If you're looking for something that works more easily in ComfyUI, I’d recommend using my Z-Image version instead: https://huggingface.co/neuralvfx/Z-Image-SAM-ControlNet
That one:
- Works with readily available nodes (a workflow is included)
- Generally gives better results out of the box