Image-to-Image
Diffusers
Safetensors
Diffusion Single File
English
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
human face in lora training
#33
by je-suis-tm - opened
Does Flux.2 support human face lora training? I have tried two different datasets. The lora result can replicate the clothing, body posture, composition, lighting, style, hairstyle except the face. That does not make sense as Flux.1 can easily captures the face but not the rest. Is that a deliberate attempt to distort human face lora training? If that is the case, it would be nice to let us know instead of letting us wasting GPU time.