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
Input multiple reference images through Diffusers?
Is it possible to import multiple reference images through Diffusers (no "input_images")? Or is it a limitation of Kontext-Dev?
Transform a realistic portrait of any person into a digital watercolor painting with the exact same style and coloring as the provided sample image. Keep the facial features, skin tone, expression, body shape, and clothing completely unchanged and realistic. Apply soft watercolor shading to the face, hair, and clothes with smooth blending, light shadows, and natural lighting. The background should include pastel cloud textures, misty colorful gradients, and watercolor splashes β exactly matching the soft artistic feel of the sample image. The entire image should look like a refined digital painting while preserving full identity and realism. Ultra high resolution, no cartoon effects.
Is it possible to import multiple reference images through Diffusers (no "input_images")? Or is it a limitation of Kontext-Dev?
Do you have any updates on this ?

