Run FLUX.2 on Replicate and Create High-Quality Images

Black Forest Labs has launched FLUX.2, their most advanced image generation model to date. This release brings significant improvements in image quality, editing capabilities, and enterprise-grade efficiency. FLUX.2 is available to run on Replicate today.

The model comes in three variants: FLUX.2 [pro], FLUX.2 [flex], and FLUX.2 [dev]. FLUX.2 [pro] generates images in 6 seconds or 9 seconds with an input image, accepts up to 8 input images, and costs $0.015 per megapixel. FLUX.2 [flex] delivers higher quality images, especially in typography and fine details, generating images in 22 seconds. FLUX.2 [dev] is an open-source, optimized version of FLUX.2 [pro], generating images in 2.5 seconds.

FLUX.2 stands out with its ability to produce realistic image details up to 4MP resolution. The model excels at rendering accurate hands, faces, fabrics, and small objects, making it ideal for creative photography, marketing materials, and interior design. Its enterprise-grade efficiency allows it to tackle complex visual tasks with low latency and predictable costs.

One of FLUX.2's standout features is its ability to reference up to 8 images simultaneously while maintaining consistent identities, products, and styles. This enables the creation of multiple ad variants using the same face or generating product mockups in various contexts. The model offers precise pose control, hex-code color accuracy, and localized editing capabilities.

FLUX.2 also includes structured prompting for programmatic workflows and generative expand/crop capabilities. The model understands context and tone well enough to create engaging posts and visuals from short prompts.

FLUX.2 is designed for anyone generating professional visual content at scale: marketing teams, product designers, content creators, social media managers, and more. With the API launch, users can easily integrate FLUX.2 into their applications using JavaScript or Python.

FLUX.2 represents a significant leap forward in AI image generation and editing. With its combination of photorealistic detail, multi-reference consistency, and enterprise-grade efficiency, it’s ready to handle professional visual content creation at any scale.