--- title: "Flux Kontext Max Prompts: 6 Tested Examples | Made" description: "Copy 6 tested Flux Kontext Max prompts with the actual outputs they produced in Made, plus how to write your own: settings, strengths, and pitfalls." url: https://www.made.app/models/flux-kontext-max/prompts --- [Models](https://www.made.app/models) / [Flux Kontext Max](https://www.made.app/models/flux-kontext-max) / Prompts # Flux Kontext Max prompts that actually ran Every prompt below was generated with Flux Kontext Max in Made, and the output next to it is what came back — not a curated stock image. Copy a prompt as a starting point, then use the guide underneath to adapt it. [Try Flux Kontext Max](https://www.made.app/models/flux-kontext-max) [Flux Kontext Max pricing: 0.8 credits / image](https://www.made.app/price-sheet/flux-kontext-max) Original results ## Flux Kontext Max prompts and their outputs These examples use media produced for Made. Prompts are included when the production record allows them. Input ![Source image before flux kontext max: glaze color edit](https://www.made.app/images/models/edit-sources/mug-plinth.jpg) Output ![ceramic mug reglazed in cobalt blue with Flux Kontext Max in Made](https://www.made.app/images/models/flux-kontext-max/mug-glaze.jpg) ### Flux Kontext Max: Glaze color edit “Change only the mug glaze to deep glossy cobalt blue. Keep the mug shape, speckles, plinth, wall, light and shadows unchanged.” Input Output ![mug moved onto a marble counter with Flux Kontext Max in Made](https://www.made.app/images/models/flux-kontext-max/mug-marble.jpg) ### Flux Kontext Max: Background replacement “Replace only the background with a white marble kitchen counter and soft morning window light. Keep the mug and its shadow unchanged.” Input ![Source image before flux kontext max: wardrobe edit](https://www.made.app/images/models/edit-sources/cafe-portrait.jpg) Output ![café portrait with a dark wool blazer with Flux Kontext Max in Made](https://www.made.app/images/models/flux-kontext-max/cafe-overcoat.jpg) ### Flux Kontext Max: Wardrobe edit “Change only the navy crewneck into a dark wool blazer over a white T-shirt. Keep his face, hair, pose, window and light unchanged.” Input Output ![café portrait with a rainy street outside with Flux Kontext Max in Made](https://www.made.app/images/models/flux-kontext-max/cafe-rain.jpg) ### Flux Kontext Max: Scene change “Change only the view outside the window to a rainy evening street with blurred city lights. Keep the man, his clothing and the interior unchanged.” Input ![Source image before flux kontext max: add one object](https://www.made.app/images/models/edit-sources/sunlit-kitchen.jpg) Output ![kitchen fruit bowl filled with lemons with Flux Kontext Max in Made](https://www.made.app/images/models/flux-kontext-max/kitchen-lemons.jpg) ### Flux Kontext Max: Add one object “Fill the empty fruit bowl with bright lemons and a few leaves. Keep the cabinets, counter, light and camera angle unchanged.” Input Output ![kitchen cabinets painted forest green with Flux Kontext Max in Made](https://www.made.app/images/models/flux-kontext-max/kitchen-green.jpg) ### Flux Kontext Max: Material edit “Change only the cabinet fronts to deep forest green paint. Keep the counter, bowl, light and perspective unchanged.” ## How to write a Flux Kontext Max prompt 1. **Upload the cleanest source** Start with an image where the subject and the area to change are clearly visible. 2. **Name one main edit** State the intended change first, using precise object, color, material, or background language. 3. **Protect the rest** List the identity, composition, lighting, objects, and textures that should remain unchanged. 4. **Compare before and after** Inspect protected regions at full size before downloading or asking for a narrower revision. ## What Flux Kontext Max responds well to ### Prompt for these jobs - Product color, material, and background changes - Portrait wardrobe or environment edits - Adding one controlled object to an existing scene - Edits where source composition and identity matter ### Check the output for - Even a targeted prompt can subtly change an unmentioned texture, reflection, facial detail, or object position. - Pixel-perfect masks, exact brand graphics, and production retouching still need a manual image editor. Iteration is cheap here: Flux Kontext Max costs 0.8 credits / image, so rewriting a prompt and rerunning it is a normal part of the workflow, not a budget decision. See the [full Flux Kontext Max pricing breakdown](https://www.made.app/price-sheet/flux-kontext-max). Questions, answered ## Flux Kontext Max prompts FAQ Need a specific answer? [Contact support](mailto:support@made.app) ### What does Flux Kontext Max do? It applies natural-language edits to an uploaded image, with an emphasis on preserving context and delivering the highest-quality Kontext workflow. ### Does Flux Kontext Max require an image? The provider can generate from text, but this Made page is intentionally configured for its reference-based editing use case and requires one source image. ### How do I keep most of the image unchanged? Describe one main change and explicitly list the subject identity, framing, lighting, materials, and objects that must stay fixed. ### What format does Made return? The current Made workflow is configured for PNG output. ### Is this a replacement for manual masking? No. It is faster for instruction-based edits, but exact edges, brand assets, and pixel-level composites still benefit from manual masking. ### How does Max differ from Kontext Pro? Max is positioned for the strongest edit quality and prompt handling; Pro is the lower-cost option when faster iteration is the priority. More tested prompts across all models live in the [prompt library](https://www.made.app/prompts), and the full Flux Kontext Max capability rundown is on the [model page](https://www.made.app/models/flux-kontext-max). --- Markdown version of https://www.made.app/models/flux-kontext-max/prompts. Every public Made page has one at its URL plus .md (https://www.made.app/models/flux-kontext-max/prompts.md). Site summary for AI assistants: https://www.made.app/llms.txt