README.md

---
language:
- en
license: other
license_name: flux-1-dev-non-commercial-license
license_link: LICENSE.md
extra_gated_prompt: >-
  By clicking "Agree", you agree to the [FluxDev Non-Commercial License
  Agreement](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)
  and acknowledge the [Acceptable Use
  Policy](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/POLICY.md).
tags:
- text-to-image
- image-generation
- flux
widget:
- text: >-
    An authentic winter photograph capturing the serene beauty of a small rural
    village after an overnight snowfall. In the foreground, uneven snow blankets
    a dirt path, with scattered footprints leading toward a cluster of old
    wooden houses. The rooftops are imperfectly covered in snow, with some areas
    exposed, revealing weathered shingles underneath. A crooked wooden fence
    lines the path, parts of it buried under snowdrifts, while a rusty metal
    bucket and a broken sled lie abandoned near the side of the road. Bare tree
    branches, heavy with frost and patches of clinging snow, frame the scene,
    their shapes irregular and natural.  The middle ground shows a small frozen
    stream partially covered in thin, cracked ice, with tufts of dried grass
    poking through the edges. The snow is not uniformly white; traces of dirt
    and fallen leaves are visible where the wind has swept the surface clean.
    Shadows cast by the trees and houses are long and faintly tinged with blue,
    consistent with the low angle of the pale winter sun.  In the background, a
    faint haze softens the view of distant rolling hills and a few scattered
    trees. Smoke curls lazily from a chimney, dissipating into the cold, crisp
    air. The soft golden light of the morning sun filters through a thin veil of
    clouds, highlighting the texture of the snow and creating subtle contrasts
    between the illuminated and shaded areas. This meticulously detailed and
    slightly imperfect composition captures the natural, unpolished charm of a
    real-life winter scene.
  output:
    url: images/example_dtwn0muaz.png

---

![FLUX.1 [dev] Grid](./dev_grid.jpg)

`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](https://blackforestlabs.ai/announcing-black-forest-labs/).

# 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](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).

# Usage
We provide a reference implementation of `FLUX.1 [dev]`, as well as sampling code, in a dedicated [github repository](https://github.com/black-forest-labs/flux).
Developers and creatives looking to build on top of `FLUX.1 [dev]` are encouraged to use this as a starting point.

## API Endpoints
The FLUX.1 models are also available via API from the following sources
- [bfl.ml](https://docs.bfl.ml/) (currently `FLUX.1 [pro]`)
- [replicate.com](https://replicate.com/collections/flux)
- [fal.ai](https://fal.ai/models/fal-ai/flux/dev)
- [mystic.ai](https://www.mystic.ai/black-forest-labs/flux1-dev)

## ComfyUI
`FLUX.1 [dev]` is also available in [Comfy UI](https://github.com/comfyanonymous/ComfyUI) for local inference with a node-based workflow.

## Diffusers

To use `FLUX.1 [dev]` with the 🧨 diffusers python library, first install or upgrade diffusers

```shell
pip install -U diffusers
```

Then you can use `FluxPipeline` to run the model

```python
import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload() #save some VRAM by offloading the model to CPU. Remove this if you have enough GPU power

prompt = "A cat holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=3.5,
    num_inference_steps=50,
    max_sequence_length=512,
    generator=torch.Generator("cpu").manual_seed(0)
).images[0]
image.save("flux-dev.png")
```

To learn more check out the [diffusers](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux) documentation

---
# 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](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).