FLUX.1 Kontext Pro vs Max: Image Editing Models

We’re excited to bring FLUX.1 Kontext, a suite of generative flow matching models that can generate and edit images, to Fireworks. Unlike the text-to-image models, the FLUX.1 Kontext family can perform in-context image generation, allowing you to prompt with both text and images, and seamlessly extract and modify visual concepts to produce new, coherent renderings.

What is FLUX.1 Kontext?

FLUX.1 Kontext models are developed by Black Forest Labs (BFL) and mark a significant expansion of classic text-to-image models by unifying instant text-based image editing and text-to-image generation. As a multimodal flow model, it combines state-of-the-art character consistency, context understanding and local editing capabilities with strong text-to-image synthesis.

As part of the FLUX.1 Kontext suite, we bring two new in-context image models to the Fireworks API:

FLUX.1 Kontext Pro
- Support local editing, generative in-context modifications and classic text-to-image generation.
- Handle both text and reference images as inputs and enable precise region edits and full-scene transformations.
- Maintains style, characters, identities across multiple editing turns and distinctive features consistent across different scenes and viewpoints.
FLUX.1 Kontext Max
- Kontext Max is the new experimental model from BFL.
- Greatly improves prompt adherence and typography generation, and high consistency for editing without compromise on speed.

The Core Capabilities of FLUX.1 Kontext

Character Consistency

Kontext can preserve unique elements of an image, such as a reference character or object in a picture, across multiple scenes and environments.

(left: input image; middle: edit from input: “change the collar color from green to orange”, right: “extract the cat and make it a keychain toy and put it in a palm of the hand.”)

Local Editing

Kontext can also make targeted modifications of specific elements in an image without affecting the rest. For example, you can change the text while preserving the others in the image.

(left: input image; right: “change the word YOU HAD ME AT BEER to FLUX KONTEXT AT FIREWORKS” )

Style References

Kontext can generate novel scenes while preserving unique styles from a reference image, directed by text prompts.

left: input image; middle: edit from input: "transform to Claymation style”, right: “this character is now picking up weeds in a garden”

Try It on Fireworks

Ready to start building with FLUX.1 Kontext?

Build with Fireworks API: You can get started right away using our simple and production-ready API.
Use Fireworks Playground: Visit our UI playground to try FLUX.1 Kontext Pro and FLUX.1 Kontext Max instantly.
Join Our Community: Join our Discord channel to connect with other developers and the Fireworks team.