Instructions to use black-forest-labs/FLUX.2-klein-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use black-forest-labs/FLUX.2-klein-9B 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-klein-9B", 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-klein-9B 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
- AMD Developer Cloud
We need Lora support, please update.
First of all, thank you very much for the great model. It is really more than just great and completely replaces Zimage for me. However, what is missing is Lora support. We would appreciate an update so that we can create Loras. Thank you very much.
Even 9b is faster than winter!
The encoder is also smarter than zimage!
But there is a big but! It's realistic, Zimage wins here, no offense. The model is really very cool. I do not know which is better than zimage or flux2, they are equal. What one has, the other does not have, and vice versa.
both go full realistic, zimage loses a bit detail to be a bit faster. My opinion, you get the same with the nvidia version unet.
Both can go fast and details. as far as i know zimage has slightly better body composition consistence and flux2 sometimes makes monsters