Diffusers
Safetensors
Image-to-Image
FLUX
How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("kaiyuyue/FLUX.2-dev-vae", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

intro

fork the subdirectory black-forest-labs/FLUX.2-dev/vae to load only the VAE

usage

from diffusers.models import AutoencoderKL as DiffusersAutoencoderKL

model = DiffusersAutoencoderKL.from_pretrained("kaiyuyue/FLUX.2-dev-vae")

license

FLUX.2-dev LICENSE.md

Downloads last month
1,443
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support