Skip to main content
FLUX.1 Kontext is a professional image-to-image editing model developed by Black Forest Labs, focusing on intelligent understanding of image context and precise editing. It can perform various editing tasks without complex descriptions, including object modification, style transfer, background replacement, character consistency editing, and text editing. The core advantage of Kontext lies in its excellent context understanding ability and character consistency maintenance, ensuring that key elements such as character features and composition layout remain stable even after multiple iterations of editing. Currently, ComfyUI has supported two models of Flux.1 Kontext:
  • Kontext Pro is ideal for editing, composing, and remixing.
  • Kontext Max pushes the limits on typography, prompt precision, and speed.

​
What Flux.1 Kontext is good at

  • Versatile editing without complex descriptions: Object modification, style transfer, background replacement, character consistency editing, and text editing
  • Context understanding: Intelligent understanding of image context enables precise, targeted edits
  • Character consistency: Character features and composition layout remain stable even after multiple iterations of editing
  • Multiple image input: The Image Stitch node stitches multiple images into a single image for editing with Flux.1 Kontext
  • Two model tiers: Kontext Pro for editing, composing, and remixing; Kontext Max for typography, prompt precision, and speed

​
Example outputs

Editing a stitched multi-image input (a girl, a dog, and a sofa combined into one scene): Flux.1 Kontext multiple image input example Image editing with Kontext Pro, ideal for editing, composing, and remixing: Flux.1 Kontext Pro image editing example Image editing with Kontext Max, which pushes the limits on typography, prompt precision, and speed: Flux.1 Kontext Max image editing example

​
Use it in ComfyUI

Flux.1 Kontext workflows

Run the multiple image input, Kontext Pro, and Kontext Max image editing workflows in ComfyUI, locally or on Comfy Cloud