Image-to-Image
Diffusers
Safetensors
Diffusion Single File
English
Flux2Pipeline
image-generation
image-editing
flux
Instructions to use black-forest-labs/FLUX.2-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use black-forest-labs/FLUX.2-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.2-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.2-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
Demo . 4bit.
#15
by sccssc - opened
wdym?
I can see that they used a 4-bit version of it. This is easily findable. Fp4 reduces the precision a LOT. Which is why, in image 1, the cabinet has a window, and the paper towel is clipped into a wall. However, in the second image, it seems all is fine. So if I had to guess, they used and demo'd a 4-bit model.
how on 2 gpu kagle????

