black-forest-labs / flux-dev

A 12 billion parameter rectified flow transformer capable of generating images from text descriptions

replicate.com
Total runs: 11.0M
24-hour runs: 100.0K
7-day runs: 600.0K
30-day runs: 2.5M
Github
Model's Last Updated: Diciembre 20 2024

Introduction of flux-dev

Model Details of flux-dev

Readme

FLUX.1 [dev] Grid

FLUX.1 [dev] 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, second only to our state-of-the-art model FLUX.1 [pro] .
  2. Competitive prompt following, matching the performance of closed source alternatives .
  3. Trained using guidance distillation, making FLUX.1 [dev] more efficient.
  4. Open weights to drive new scientific research, and empower artists to develop innovative workflows.
  5. Generated outputs can be used for personal, scientific, and commercial purposes as described in the flux-1-dev-non-commercial-license .

Usage

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

ComfyUI

FLUX.1 [dev] 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.

License

This model falls under the FLUX.1 [dev] Non-Commercial License .

Runs of black-forest-labs flux-dev on replicate.com

11.0M
Total runs
100.0K
24-hour runs
200.0K
3-day runs
600.0K
7-day runs
2.5M
30-day runs

More Information About flux-dev replicate.com Model

flux-dev replicate.com

flux-dev replicate.com is an AI model on replicate.com that provides flux-dev's model effect (A 12 billion parameter rectified flow transformer capable of generating images from text descriptions), which can be used instantly with this black-forest-labs flux-dev model. replicate.com supports a free trial of the flux-dev model, and also provides paid use of the flux-dev. Support call flux-dev model through api, including Node.js, Python, http.

black-forest-labs flux-dev online free

flux-dev replicate.com is an online trial and call api platform, which integrates flux-dev's modeling effects, including api services, and provides a free online trial of flux-dev, you can try flux-dev online for free by clicking the link below.

black-forest-labs flux-dev online free url in replicate.com:

https://replicate.com/black-forest-labs/flux-dev

flux-dev install

flux-dev is an open source model from GitHub that offers a free installation service, and any user can find flux-dev on GitHub to install. At the same time, replicate.com provides the effect of flux-dev install, users can directly use flux-dev installed effect in replicate.com for debugging and trial. It also supports api for free installation.

flux-dev install url in replicate.com:

https://replicate.com/black-forest-labs/flux-dev

flux-dev install url in github:

https://github.com/replicate/cog-flux

Url of flux-dev

Provider of flux-dev replicate.com

black-forest-labs
ORGANIZATIONS

Other API from black-forest-labs

replicate

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

Total runs: 217.7M
Run Growth: 28.5M
Growth Rate: 13.15%
Updated: Febrero 02 2025
replicate

Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.

Total runs: 14.6M
Run Growth: 4.5M
Growth Rate: 31.03%
Updated: Febrero 04 2025
replicate

State-of-the-art image generation with top of the line prompt following, visual quality, image detail and output diversity.

Total runs: 9.2M
Run Growth: 900.0K
Growth Rate: 9.78%
Updated: Febrero 04 2025
replicate

FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.

Total runs: 5.5M
Run Growth: 1.9M
Growth Rate: 34.55%
Updated: Febrero 04 2025
replicate

The fastest image generation model tailored for fine-tuned use

Total runs: 378.5K
Run Growth: 200.1K
Growth Rate: 54.21%
Updated: Diciembre 03 2024
replicate

A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference

Total runs: 242.2K
Run Growth: 132.6K
Growth Rate: 55.37%
Updated: Diciembre 03 2024
replicate

Professional inpainting and outpainting model with state-of-the-art performance. Edit or extend images with natural, seamless results.

Total runs: 189.6K
Run Growth: 100.3K
Growth Rate: 54.93%
Updated: Febrero 05 2025
replicate

Open-weight inpainting model for editing and extending images. Guidance-distilled from FLUX.1 Fill [pro].

Total runs: 99.3K
Run Growth: 43.4K
Growth Rate: 44.56%
Updated: Enero 30 2025
replicate

Professional edge-guided image generation. Control structure and composition using Canny edge detection

Total runs: 79.8K
Run Growth: 39.5K
Growth Rate: 50.58%
Updated: Febrero 05 2025
replicate

Open-weight depth-aware image generation. Edit images while preserving spatial relationships.

Total runs: 53.9K
Run Growth: 27.4K
Growth Rate: 53.20%
Updated: Noviembre 21 2024
replicate

Professional depth-aware image generation. Edit images while preserving spatial relationships.

Total runs: 50.5K
Run Growth: 25.6K
Growth Rate: 52.03%
Updated: Febrero 05 2025
replicate

Open-weight edge-guided image generation. Control structure and composition using Canny edge detection.

Total runs: 37.1K
Run Growth: 14.7K
Growth Rate: 40.05%
Updated: Noviembre 21 2024
replicate

Open-weight image variation model. Create new versions while preserving key elements of your original.

Total runs: 36.9K
Run Growth: 15.1K
Growth Rate: 42.06%
Updated: Noviembre 21 2024
replicate

Fast, efficient image variation model for rapid iteration and experimentation.

Total runs: 18.1K
Run Growth: 4.8K
Growth Rate: 26.67%
Updated: Noviembre 21 2024