--- title: "Muse Image Prompts: 6 Tested Examples | Made" description: "Copy 6 tested Muse Image 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/muse-image/prompts --- [Models](https://www.made.app/models) / [Muse Image](https://www.made.app/models/muse-image) / Prompts # Muse Image prompts that actually ran Every prompt below was generated with Muse Image 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 Muse Image](https://www.made.app/models/muse-image) [Muse Image pricing: 0.1 credits / image](https://www.made.app/price-sheet/muse-image) Original results ## Muse Image prompts and their outputs These examples use media produced for Made. Prompts are included when the production record allows them. ![sunlit living room corner generated with Muse Image in Made](https://www.made.app/images/models/muse-image/living-corner.jpg) ### Muse Image: Living room corner “Sunlit living room corner with a boucle armchair, a small olive tree and limewashed terracotta walls. 35mm film still, soft natural light, muted earth tones with one olive accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![bedroom in morning light generated with Muse Image in Made](https://www.made.app/images/models/muse-image/linen-bedroom.jpg) ### Muse Image: Morning bedroom “Bedroom with rumpled white linen, morning light through sheer curtains, a book on the nightstand. 35mm film still, soft natural light, muted earth tones with one dusty rose accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![open kitchen shelving with ceramics generated with Muse Image in Made](https://www.made.app/images/models/muse-image/kitchen-shelf.jpg) ### Muse Image: Kitchen shelving “Open kitchen shelving with handmade ceramics, glass jars and fresh herbs, soft daylight. 35mm film still, soft natural light, muted earth tones with one terracotta accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![balcony garden at dusk generated with Muse Image in Made](https://www.made.app/images/models/muse-image/balcony-garden.jpg) ### Muse Image: Balcony garden “Small balcony garden with potted plants and a bistro set at dusk, string lights just turning on. 35mm film still, soft natural light, muted earth tones with one warm yellow accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![sculptural vase with dried grasses generated with Muse Image in Made](https://www.made.app/images/models/muse-image/sculptural-vase.jpg) ### Muse Image: Vase on plinth “Sculptural ceramic vase with dried grasses on a plaster plinth against a warm grey wall. 35mm film still, soft natural light, muted earth tones with one terracotta accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ![dinner table set for friends generated with Muse Image in Made](https://www.made.app/images/models/muse-image/summer-table.jpg) ### Muse Image: Dinner table “Long dining table set for friends on a late summer evening, candles, linen and shared plates. 35mm film still, soft natural light, muted earth tones with one amber accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.” ## How to write a Muse Image prompt 1. **Write a precise brief** Describe the subject, composition, and any exact display text in quotes. 2. **Add references for edits** Upload one image to edit, or several to compose from — then describe the change. 3. **Pick a format** Choose from nine aspect ratios, from 21:9 banners to 9:21 portrait. 4. **Iterate in turns** Muse keeps edits coherent across turns — refine one instruction at a time. ## What Muse Image responds well to ### Prompt for these jobs - Precise edits that leave the rest of the image untouched - Composing one image from multiple references - Readable typography, plots, and even QR codes - High-volume generation at 1 credit per image ### Check the output for - It is a brand-new model line; style range is less proven than mature families like FLUX or Seedream. - Made returns PNG output; other formats need a conversion step. Iteration is cheap here: Muse Image costs 0.1 credits / image, so rewriting a prompt and rerunning it is a normal part of the workflow, not a budget decision. See the [full Muse Image pricing breakdown](https://www.made.app/price-sheet/muse-image). Questions, answered ## Muse Image prompts FAQ Need a specific answer? [Contact support](mailto:support@made.app) ### What is Muse Image? It is Meta’s first image generation model, hosted on fal, focused on precise instruction-based editing, multi-reference composition, and accurate text rendering. ### How much does it cost? 0.1 credits per image, among the cheapest capable image models in the library. The exact price appears before you generate. ### Can it edit an existing image? Yes. Add reference images and describe the change; Made routes the request to the edit endpoint at the same price. ### Is it good at text? Accurate rendered text is one of its documented strengths — including charts and QR codes. Verify dense small copy before use. ### How many reference images can I use? Up to ten per request for multi-reference composition. ### When should I choose another model? Choose Nano Banana Pro or GPT Image 2 for the most demanding hero images, or a Kontext model for strict source-preserving edits. More tested prompts across all models live in the [prompt library](https://www.made.app/prompts), and the full Muse Image capability rundown is on the [model page](https://www.made.app/models/muse-image). --- Markdown version of https://www.made.app/models/muse-image/prompts. Every public Made page has one at its URL plus .md (https://www.made.app/models/muse-image/prompts.md). Site summary for AI assistants: https://www.made.app/llms.txt