
Flux-dev text to image model, 12 billion parameter rectified flow transformer.

FLUX.1 Kontext [dev] is a development version of the state-of-the-art image editing model that lets you edit images using text prompts. It makes editing intuitive by understanding the relationship between visuals and language.

Fast FLUX.1 Kontext [dev] endpoint with LoRA support for rapid image editing using pre-trained adapters for brand and style. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

FLUX.1 [schnell] is fastest image generation model tailored for local development and personal use, a 12 billion parameter rectified flow transformer.

FLUX.2 Flex Edit is a professional image editing model specialized for typography, fine detail preservation, and production workflows. It provides adjustable inference steps and guidance scale, with multi-reference support for up to 8 images, delivering precise control over photorealistic editing results up to 4MP.

FLUX.2 Flex is a professional text-to-image generation model specialized for typography, fine detail preservation, and production workflows requiring precise customization. It provides adjustable inference steps (1–50) and guidance scale (1.5–10) for fine-grained control, delivering high-quality output up to 4MP.

FLUX.2 Pro Edit is a professional image editing model that accepts a text prompt alongside one or more reference images, enabling targeted edits, subject replacement, style transfer, and multi-reference identity-consistent generation — all without fine-tuning. It supports up to 8 reference images per request with high visual consistency.

FLUX.2 Pro is a state-of-the-art text-to-image generation model that raises the bar for photorealistic quality, prompt fidelity, and production reliability. Built on a multimodal flow matching architecture, it delivers up to 4MP coherent scenes with realistic lighting, spatial logic, and fine detail that close the gap with professional photography.

Rapid, high-quality image generation with FLUX.1 [dev] and LoRA support for personalized styles and brand-specific outputs.
Join the Discord community for the latest model updates, prompts, and support.