BLACK FOREST LABS · AI IMAGE EDITING
Upload an image and say what to change: a new background, a different color, winter instead of summer. FLUX.1 Kontext edits in context, keeping the subject, layout and camera angle you did not mention. It can also create images from text.
Review results, manage assets and access generation history in AI Studio.
Every example below was actually generated with FLUX.1 Kontext on ImgAI, with the original prompt and settings. Click "Use this example" to load it into the creator.
FLUX.1 Kontext Pro · 1:1
Input: the mint robot from our Nano Banana 2 page. Body turned yellow and a red scarf added, with face, parcel and street kept. Pro.
Change the robot's body color to warm sunflower yellow and wrap a small red knitted scarf around its neck. Keep its face, pose, the parcel and the street background exactly the same.
FLUX.1 Kontext Pro · 4:3
Input: a glass house made with FLUX.1 Schnell. Snow and warm window light added; the house kept its shape, though the wall texture changed. Pro.
Turn this scene into a snowy winter evening: snow on the roof and pine trees, light snowfall, warm light glowing from the windows. Keep the house's architecture and camera angle identical.
FLUX.1 Kontext Max · 1:1
Input: the mug from our GPT Image 2 page. Background swapped for a café counter, mug and beans untouched. Max.
Replace the background with a cozy cafe counter and softly blurred warm bokeh lights. Keep the mug, the coffee beans and the lighting on the mug unchanged.
FLUX.1 Kontext Max · 16:9
Input: the loft from our Nano Banana 2 page. Restyled as Japandi; the shelves, sofa, table and window stay where they were. Max.
Restyle this living room as a Japandi interior: dark walnut furniture, a paper pendant lamp, a low wooden coffee table and beige textiles. Keep the same room layout, window and camera position.
FLUX.1 Kontext Pro · 3:2
Text-to-image: a faded 35mm film look on a windy cliff. Pro.
Vintage 35mm film photo of a white lighthouse on a grassy cliff on a windy afternoon, faded colors, soft grain, a few seagulls in the sky.
FLUX.1 Kontext Max · 4:3
Text-to-image: layered paper with soft shadows in blue and orange. Max.
Layered paper-cut illustration of a fox sleeping under a crescent moon in a forest, soft shadows between paper layers, deep blue and orange palette.
FLUX.1 Kontext is a Black Forest Labs model that combines text-to-image generation with context-aware editing: it reads the image you provide and changes only what your instruction asks for. That makes it suited to iterative edits — recolor a product, swap a background, then adjust the light — without the subject drifting.
On ImgAI you can add up to 4 reference images and pick from 9 aspect ratios. Write instructions in any language; they are translated into English before generation. Kontext Pro costs 50 credits per image and Kontext Max 95. BFL now recommends its newer FLUX.2 for new projects, but on ImgAI Kontext remains the FLUX option for editing with reference images.
Based on the model's published capabilities and what we actually generated, to help you judge whether it fits your task.
Put a product or person in a new setting while keeping their look and lighting.
Show a product or character in a different color or outfit without redrawing it.
Turn a summer photo into a snowy evening while keeping the architecture identical.
Restyle a room in a new design language while keeping layout, windows and viewpoint.
The tiers in this series share one page — switch between them in the creator's model menu.
Fast, reliable edits for most jobs at a lower price. Up to 4 reference images.
Higher quality and consistency for detailed edits, faces and small text. Up to 4 reference images.
Specs come from the configuration currently available on this site; the creator always shows the live price. Failed generations are refunded automatically.
| FLUX.1 Kontext Pro | FLUX.1 Kontext Max | |
|---|---|---|
| Input | Text + up to 4 reference images | Text + up to 4 reference images |
| Prompt length limit | 3,000 characters | 3,000 characters |
Supported aspect ratios
| Tier | Per image |
|---|---|
| FLUX.1 Kontext Pro | 50 |
| FLUX.1 Kontext Max | 95 |
These come from real generations — read them alongside the original prompts in the examples.
End the instruction with "keep the face, pose and background unchanged". Explicit is safer than implied.
Chain simple edits instead of one long instruction; feed each result back in as the new reference.
"a snowy winter evening with warm window light" works better than "add snow and darken".
When small details or faces must survive the edit, Max holds them better than Pro.
FLUX.1 Kontext is a Black Forest Labs image model that both generates images from text and edits existing images based on a plain-language instruction, changing only what you ask for.
Pro handles most edits well at a lower price. Max gives higher quality and better consistency for detailed edits, faces and small text.
On ImgAI, Kontext Pro costs 50 credits per image and Kontext Max 95. Failed generations are refunded automatically.
Up to 4 reference images per request. For most edits one image is enough; extra images can supply a style or an object to add.
Yes. ImgAI translates instructions into English automatically before sending them to the model.
For pure text-to-image, FLUX.2 gives more detail and higher resolution. For editing an image you already have, use Kontext — on ImgAI FLUX.2 does not take reference images yet.
Sign up and generate with credits. Results are saved to your library, ready to download or keep editing.