FLUX.2 small decoder

FLUX.2 small decoder from black-forest-labs. Source-based hardware guidance from its published configuration.

EstimatedRepository opened Apr 6, 2026Source checked 9/24/2026Version: a3efc24f

LOCALRENTED GPUOPEN WEIGHTS

At a glance

Parameters: 0.06B
Architecture: unknown
License: apache-2.0
Software: Diffusers

View the model source

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Ways to run it

Diffusers · See official guide

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

import torch
from diffusers import Flux2KleinPipeline, AutoencoderKLFlux2

device = "cuda"
dtype = torch.bfloat16

vae = AutoencoderKLFlux2.from_pretrained("black-forest-labs/FLUX.2-small-decoder", torch_dtype=dtype)
pipe = Flux2KleinPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-4B", vae=vae, torch_dtype=dtype)
pipe.enable_model_cpu_offload()

prompt = "A black cat holding a sign that says 'hello world' in typewriter font"
image = pipe(
    prompt=prompt,
    height=1024,
    width=1024,
    guidance_scale=1.0,
    num_inference_steps=4,
    generator=torch.Generator(device=device).manual_seed(0)
).images[0]
image.save("flux-klein-small-decoder.png")

Official instructions

Explore its uses

SAFETENSORS

Keep exploring

Images

Qwen

Qwen-Image 2.1

Generate and edit images, including transparent images and edits guided by reference images.

MODEL SIZE7B visual generator

LOCALRENTED GPU

Repository opened Sep 14, 2026

Images

Black Forest Labs

FLUX.1 schnell

A 12-billion-parameter image model designed for generation in one to four steps.

FLUX.2 Klein · 4B

A compact open image model for local generation and image editing, with official ComfyUI templates and downloadable weights.

MODEL SIZE4B

LOCALRENTED GPU

Released Jan 15, 2026