Instructions to use black-forest-labs/FLUX.1-Kontext-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use black-forest-labs/FLUX.1-Kontext-dev 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("black-forest-labs/FLUX.1-Kontext-dev", 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] - Diffusion Single File
How to use black-forest-labs/FLUX.1-Kontext-dev with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Inference
- Notebooks
- Google Colab
- Kaggle
Kontext "Add Edit Model Step" defaults
Like many users, I have my Flux files stored in subdirectories, so when I add a "FLUX.1 Kontext Image Edit" node, I have to specify the extra paths to the clip_name1, name2, and vae.
Once I have the paths specified, and I use the new "Add Edit Model Step" button to create a subsequent node, it should NOT do what it does now (assume the default file names and paths). Instead it should copy the file names and paths already specified in the previous Kontext Image Edit node.
Your new "Add Edit Model Step" is meant to be used quickly and conveniently, but it partially fails by users having to reenter all the file paths every time they create a new node.
It should also carry across the Steps, Sampler_name, Scheduler, and the other tunable parameters, in case the user has changed those for some reason.