Today we're releasing FLUX.1 Kontext - a suite of generative flow matching models that allow you to generate and edit images.
Unlike traditional text-to-image models, Kontext understands both text AND images as input, enabling true in-context generation and editing.
Four things make Kontext special:
Character consistency: Preserve elements across scenes
Local editing: Target specific parts without affecting the rest
Style reference: Generate new scenes in existing styles
Interactive speed: Iterate with minimal latency
Two models available:
FLUX.1 Kontext [pro]: Pioneer for fast iterative editing. First model to build upon previous edits while maintaining characters, identities, styles & features consistent across scenes
FLUX.1 Kontext [max]: Maximum performance at high speed – improved prompt adherence, typography & premium consistency
🔓 FLUX.1 Kontext [dev]: Open-weights variant of our most advanced generative image editing model. Available in private beta.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
In-context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → editing holds character identity and style stable across chained edits, which is the part that degrades when you loop text-to-image calls. Reachable through the BFL API and partners including fal and Replicate.
Read the full thread on X ↗
