🤖 image-to-image

FLUX.2-klein-base-4b-fp8

black-forest-labs/FLUX.2-klein-base-4b-fp8

Get AI Model →
72.5K
Downloads
❤️
30
Likes
🏷️
8
Tags
📦
diffusion-single-file
Library
Model Details
Full Model IDblack-forest-labs/FLUX.2-klein-base-4b-fp8
Pipeline / Taskimage-to-image
Librarydiffusion-single-file
Downloads (all-time)72.5K
Likes30
Last Modified2/24/2026
Author / Orgblack-forest-labs
PrivateNo — public
⚡ Quick Usage (Python)

Using the 🤗 Transformers library. Install with pip install transformers

from transformers import pipeline

# Load the model
pipe = pipeline("image-to-image", model="black-forest-labs/FLUX.2-klein-base-4b-fp8")

# Run inference
result = pipe("Your input here")
print(result)
🏷️ Tags
diffusion-single-filetext-to-imageimage-editingfluximage-to-imageenlicense:apache-2.0region:us
More image-to-image Models
See all →
FLUX.2-klein-base-4B

black-forest-labs/FLUX.2-klein-base-4B

1.5M❤️ 126
Get AI Model →
stable-diffusion-xl-refiner-1.0

stabilityai/stable-diffusion-xl-refiner-1.0

244.9K❤️ 2.0K
Get AI Model →
FLUX.2-klein-4B

black-forest-labs/FLUX.2-klein-4B

244.2K❤️ 628
Get AI Model →
🚀 Use This Model

Access model files, inference API, and full documentation on Hugging Face.

Open on Hugging Face →Browse Model Files ↗← Browse All Models
🤖 Task: image-to-image

This model is designed for the image-to-image task. Explore more models for this use case.

All image-to-image Models →
📊 Popularity
Downloads72.5K
❤️ Community Likes30
🛠️ Requirements
  • Install: pip install diffusion-single-file
  • Python 3.8+ recommended for Transformers.
  • GPU (CUDA) speeds up inference significantly.
  • Use model.half() for fp16 on limited VRAM.
👋 Need help with code?