Log inSign Up
Open Hedra

Flux Kontext Pro

All models
Image modelBlack Forest Labs

Overview

Flux Kontext Pro is an instruction-based image editing model developed by Black Forest Labs. It allows creators to modify existing images using natural language prompts rather than manual masking or inpainting. The model is especially good for professional workflows requiring precise, context-aware transformations—such as rebuilding environments or adding objects—while strictly preserving the original image's structure and photorealistic details. For users needing the highest possible performance, Black Forest Labs also offers Flux Kontext Max.

Best of Flux Kontext Pro

A wide-angle, 21:9 aspect ratio image showing a massive, blue-tinted iceberg calving into a dark ocean. A huge splash of white water and ice rises at the base of the towering glacial wall. This text-to-image generation was created at 1568x672 resolution using the Flux Kontext Pro model.Colossal Iceberg Calving into the Ocean — Flux Kontext ProA close-up horizontal portrait of a Japanese snow monkey with light fur and a pink face holding a small pastry. Visible steam rises from its breath against a cold, snowy, out-of-focus background. This image was generated using the Flux Kontext Pro model at 1568x672 resolution.Snow Monkey Eating Pastry — Flux Kontext ProA 21:9 digital illustration of a cheerful, cartoon-style black and white cow wearing a red apron, generated using the Flux Kontext Pro model at 1568x672 resolution. The cow has large green eyes, a pink nose, small horns, and a friendly smile, standing against a solid gray background.Cartoon Mascot Cow, Generated by Flux Kontext ProAn image-to-image generation using Flux Kontext Pro at 1568x672 resolution. It features a muscular, anthropomorphic parakeet with a yellow head, green feathers, and a backwards baseball cap running down a city street. A massive orange and yellow explosion with flying debris erupts behind him.Parakeet Action Hero Running From Explosion — Flux Kontext ProA digital image generated with Flux Kontext Pro at 1568x672 resolution. It shows a young woman with a short black bob and red lipstick sitting in the driver's seat of a car. She wears a black leather jacket and looks directly at the camera. The background features blurred city lights through a wet windshield.Flux Kontext Pro: Woman in Leather Jacket DrivingA high-resolution 1568x672 image of a smiling Black man sitting at a podcast desk with his hands clasped. He wears a grey t-shirt. Two microphones flank him, and water bottles sit on the desk. This image was generated using the Flux Kontext Pro model.Flux Kontext Pro: Podcast Host Smiling at DeskA 3D animated character of a cheerful young woman with curly pink hair, wearing an orange t-shirt with a yellow winking smiley face. Her hands are raised in a waving gesture. The background features pastel pink and purple swirls. Generated at 1024x1024 resolution using Flux Kontext Pro.Cheerful Girl with Pink Hair, Rendered by Flux Kontext ProA vertical high-speed photograph of a bright green apple splashing into clear water, creating a dynamic splash with droplets and ripples. Two small green leaves float near the stem. The image, generated using Flux Kontext Pro at 672x1568 resolution, features a clean, soft blue background.Green Apple Splash — Flux Kontext Pro

What is Flux Kontext Pro best used for?

Flux Kontext Pro is designed for instruction-based image editing and style transfer using natural language. Instead of relying on manual masking or traditional inpainting, users can tell the model what to change—such as adding an object, swapping an outfit, or altering a scene's weather. The model preserves the original image's character consistency and untouched details, making it useful for rapid prototyping and iterative visual adjustments.

Who developed Flux Kontext Pro and when was it released?

Flux Kontext Pro was developed by Black Forest Labs and announced in May 2025. It builds upon the text-to-image architecture of earlier models like Flux 1.1 Pro and Flux 1.1 Ultra by introducing native multimodal editing capabilities. It launched alongside an open-weights Dev version and the premium Flux Kontext Max, which provides higher fidelity for complex tasks like typography. The company later advanced this lineage with the Flux.2 [pro] series.

How can I get the best results when editing with Flux Kontext Pro?

Take advantage of the model's visual consistency by using multi-turn editing. Rather than packing complex changes into a single prompt, refine your image through successive, isolated instructions—for example, changing the background in one step and modifying clothing in the next. When integrating the model into automated workflows, explicitly configure your requests to match the input image's aspect ratio to prevent unwanted cropping. For more advanced implementations, refer to the official inference repository.

Similar models

Flux Kontext MaxBlack Forest LabsFlux.2 [flex]Black Forest LabsFlux.2 [klein] 9BBlack Forest LabsFlux.2 [max]Black Forest LabsFlux.2 [pro]Black Forest Labs

Prompt tips

  • Use conversational instructions: Write direct commands like "Change the orange flowers to a bouquet of roses" rather than traditional comma-separated keywords.

  • Explicitly preserve elements: State what should remain untouched (e.g., "maintain the background" or "keep the facial features identical") to prevent the model from hallucinating unwanted changes.

  • Choose verbs carefully: The model reacts differently to specific action words; "change," "replace," and "transform" will yield varying degrees of structural alteration.

  • Iterate in steps: Break complex transformations into smaller, sequential edits rather than overloading a single prompt, taking advantage of the model's multi-turn capabilities.