Black Forest Labs releases Flux.1 tools for advanced image editing

Black Forest Labs last week released four new artificial intelligence (AI) tools for its basic text-to-image Flux.1 AI model. These four AI tools are based on separate models designed to perform specific image editing tasks within the image generator. The company claims that these tools provide detailed control over the output images and let users retain key elements while experimenting with different styles. The editing tools are available separately as open access developer models and pro models.

In one blog postthe AI ​​company has detailed the four new image editing tools for the Flux.1 AI model. Developers can access the four tools in separate models within the dev model series, while users can access the full version via the BFL API.

The Flux.1 Fill is a paint-in/paint-out tool that allows you to edit the details in an image or expand the boundaries of an image using text prompts and a binary mask. Based on internal testing, the company claimed that the pro version of the tool outperforms competing tools like Ideogram 2.0. The developer version of the tool is available under the Flux Dev license and can be found on Cuddle Face and GitHub. The pro version can be accessed via the BFL API.

The Flux.1 Depth and Flux.1 Canny tools allow users to perform structural conditioning of the output during image transformations. The Depth tool preserves the structure of the generated image through depth maps and keeps it intact while users perform a text guide operation. Similarly, the Canny tool preserves structure by accessing the sharp edges of the output. These are useful during retexturing operations.

The company claimed that the tools perform better than similar tools offered by competitors such as Midjourney and InstantX. The full version provides maximum performance, while the Low-rank Adaptation (LoRA) version allows for easier implementation for developers. It can be found here.

Finally, the Flux.1 Redux allows users to generate image variations based on an input image. Black Forest Labs claims that the tool can reproduce the image with minor variation, which can be further refined. It also allows image restyling via prompts. This tool is also supported by the Flux1.1 [pro] Ultra, the company’s flagship image generation model. The model weights can be found here.

All AI models will also be available through third-party platforms such as Fal.ai, Replicate, Together.ai, Freepik and Krea.ai.