black-forest-labs / flux-schnell

The fastest image generation model tailored for local development and personal use

  • Public
  • 150.6M runs
  • GitHub
  • Weights
  • License

Blog post: Learn about training with Flux Read the blog

Pricing

This model is priced by how many images are generated.

Check out our docs for more information about how per-image pricing works on Replicate.

Readme

FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post.

Key Features

  1. Cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives.
  2. Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps.
  3. Released under the apache-2.0 licence, the model can be used for personal, scientific, and commercial purposes.

Usage

We provide a reference implementation of FLUX.1 [schnell], as well as sampling code, in a dedicated github repository. Developers and creatives looking to build on top of FLUX.1 [schnell] are encouraged to use this as a starting point.

ComfyUI

FLUX.1 [schnell] is also available in Comfy UI for local inference with a node-based workflow.

Limitations

  • This model is not intended or able to provide factual information.
  • As a statistical model this checkpoint might amplify existing societal biases.
  • The model may fail to generate output that matches the prompts.
  • Prompt following is heavily influenced by the prompting-style.

Out-of-Scope Use

The model and its derivatives may not be used

  • In any way that violates any applicable national, federal, state, local or international law or regulation.
  • For the purpose of exploiting, harming or attempting to exploit or harm minors in any way; including but not limited to the solicitation, creation, acquisition, or dissemination of child exploitative content.
  • To generate or disseminate verifiably false information and/or content with the purpose of harming others.
  • To generate or disseminate personal identifiable information that can be used to harm an individual.
  • To harass, abuse, threaten, stalk, or bully individuals or groups of individuals.
  • To create non-consensual nudity or illegal pornographic content.
  • For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation.
  • Generating or facilitating large-scale disinformation campaigns.

Accelerated Inference

We provide a go_fast flag within the API which toggles a version of flux-schnell optimized for inference. Currently this version is a compiled fp8 quantization with an optimized attention kernel. We’ll update the model and this documentation as we develop further enhancements.