FLUX.1 Redux [dev] is an adapter for all FLUX.1 base models for image variation generation. Given an input image, FLUX.1 Redux can reproduce the image with slight variation, allowing to refine a given image. It naturally integrates into more complex workflows unlocking image restyling. Restyling via text is also available through our API by providing an image plus a language prompt. For more information, please read our blog post.
Usage
We provide a reference implementation of FLUX.1 Redux [dev], as well as sampling code, in a dedicated github repository.
API Endpoints
FLUX.1 Redux [pro] is available in our API bfl.ml. In addition to the [dev] adapter, the API endpoint allows users to modify an image given a textual description.
The feature is supported in our latest model FLUX1.1 [pro] Ultra, allowing for combining input images and text prompts to create high-quality 4-megapixel outputs with flexible aspect ratios.
Diffusers
To use FLUX.1 Redux [pro] with the 🧨 diffusers python library, first install or upgrade diffusers
pip install -U diffusers
Then you can use FluxPriorReduxPipeline along with FluxPipeline to generate images from images.
import torch
from diffusers import FluxPriorReduxPipeline, FluxPipeline
from diffusers.utils import load_image
pipe_prior_redux = FluxPriorReduxPipeline.from_pretrained("black-forest-labs/FLUX.1-Redux-dev", torch_dtype=torch.bfloat16).to("cuda")
pipe = FluxPipeline.from_pretrained(
"black-forest-labs/FLUX.1-dev" ,
text_encoder=None,
text_encoder_2=None,
torch_dtype=torch.bfloat16
).to("cuda")
image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
pipe_prior_output = pipe_prior_redux(image)
images = pipe(
guidance_scale=2.5,
num_inference_steps=50,
generator=torch.Generator("cpu").manual_seed(0),
**pipe_prior_output,
).images
images[0].save("flux-dev-redux.png")
To learn more check out the diffusers 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.
- Outputs are heavily influenced by the input image.
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.