Most AI image generators have guardrails to prevent people from creating harmful images. However, BlackForestLabs’s FLUX.1 platform does not, and — combined with its realistic image generations — has inspired viral image creations. Now, the model is getting a massive upgrade.
Also: The best AI image generators: Tested and reviewed
On Thursday, the company announced FLUX.1 Tools, a suite of models that can help users modify images created with its FLUX text-to-image model, offering more options for image control and manipulation. The four features of this suite include Fill, Depth, Canny, and Redux.
With Flux.1 Fill, users can access inpainting and outpainting capabilities on their images, meaning they can seamlessly remove from or add to an image and even expand the image beyond the borders of its original frame. As seen below, the differences are added seamlessly, blending into the background and making it hard to distinguish from the original.
The FLUX. Tools also allow for structural conditioning, which uses canny edge or depth detection to map the elements of an image’s structure and keep the composition and structure in future generations, as seen in the image below.
Lastly, Redux is an adapter for the FLUX.1 models, which enables users to produce a new version of an existing image with slight variations.
BlackForestLabs includes benchmark results for each one of these features; the FLUX 1 Tool outperforms other state-of-the-art models, including Ideogram V2, Stable Diffusion 1.5, Midjourney Retexture, and more, according to the company.
The FLUX.1 Tools are available as open-access models within the FLUX.1 [dev] model series, and in the BFL API supplementing FLUX.1 [pro]. To try out the FLUX.1 generator, you can access it on X via Grok with a Premium or Premium+ subscription, which starts at $7 per month.
Artificial Intelligence
