longcat-image/edit
Advanced image editing model for detailed, consistent image transformation.
Advanced image editing model for detailed, consistent image transformation.
Precision visual editing tool for consistent, photorealistic brand assets
Advanced concept-driven image editing with unified segmentation and detection for creators.
Replace a photo’s background with a new scene using Ideogram 3.
Nail the art of text and vector imagery.
Fast, photorealistic image repair and refinements for product visuals.
Flux Kontext is an AI model for image-to-image generation and editing. It lets you modify existing images with text prompts, change styles, swap objects, or even edit text directly inside the image. You can use it to remaster images, apply art styles, or transform subjects while preserving context, layout, and character identity.
Flux.1 Kontext uses both an image and a text prompt to understand the visual context and perform edits. It can change specific objects, modify backgrounds, alter text, or even restyle the whole image—without affecting unrelated areas. The model understands local details and lets you make multiple edits step by step.
Yes, Flux Kontext preserves character identity, clothing, and style across different scenes and edits. If you want consistency, describe the subject clearly and say what should stay the same. This allows you to evolve a character while keeping them recognizable throughout.
FLUX.1 Kontext is exceptionally fast: around 3.2 seconds for 1024x1024 text-to-image and 3.8 seconds for image-to-image edits. This is 8x faster than GPT-Image and significantly quicker than previous models. On the specialized KontextBench, it ranks top in text editing and local editing, and leads in character preservation. It performs excellently across all context image generation tasks and shows strong overall quality in aesthetics, prompt following, text generation, and realism.
Flux Kontext stands out with its ability to handle both text-to-image and in-context image edits. It supports consistent character tracking, localized changes, fast iteration, and strong style preservation—all while delivering competitive speed and accuracy compared to leading models.
With Flux.1 Kontext, clarity is key. Use specific descriptions like colors, styles, or actions. Say exactly what to change and what to keep. For best results, write in steps, name visual elements directly, and avoid vague terms like "make it better." This helps the model follow your intent closely.
The FLUX Kontext suite includes two models:
Crucially, FLUX.1 Kontext Pro (an image editing suite, May 29, 2025) is distinct from FLUX 1.1 Pro (a text-to-image model, October 2, 2024).
FLUX Kontext is primarily accessible via API, available through Black Forest Labs’ API (endpoint: black-forest-labs/FLUX.1-kontext-pro). An open-source version isn’t released yet. The API accepts both text prompts and reference image URLs (Base64 data URIs or hosted file URLs) as input.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.