# Reve Canonical page: https://fuser.studio/models/reve Reve in Fuser generates and edits images from text and references with Reve 2.1, including legible text in the image. Iterate on one canvas. ## Specs | Spec | Value | | --- | --- | | Versions | Reve 2.1, Original | | Inputs | Prompt (text), Image (up to 8) | | Output | image | | Aspect ratios | Square (1:1), Panoramic (4:1), Panoramic (3:1), Cinematic (21:9), Wide (2:1), Wide (17:9), Landscape (16:9), Portrait (9:16), Landscape (4:3), Landscape (5:4), Portrait (4:5), Portrait (3:4), Landscape (3:2), Portrait (2:3), Portrait (1:2), Portrait (1:3), Portrait (1:4) | | Cost | 55–345 credits per run | Posters, packaging and signage where every headline lands crisp, correctly spelled and exactly where you placed it Creator: Reve AI Also known as: Halfmoon [Lay out an image](https://app.fuser.studio) ## How Reve works Write the image like a layout brief, set a tier and a frame, and refine with plain instructions. The same node generates from text, edits one image or remixes several. ### Write a layout brief Describe the subject, where it sits and any literal text in quotes, then attach up to eight reference images if you have them. ### Pick a tier and a frame Choose 2.1 for final typography or Original for cheap drafts, then set the aspect ratio and file format. ### Generate, then edit in place Get a clean, hierarchy-aware composition, then change one element with a plain-language instruction. ## What Reve is good at Reve plans composition, hierarchy and text placement before it renders, which is why its strengths are readable type, spatial logic and edits that leave the rest alone. ### Crisp, correctly spelled type A language-model planner places headlines, labels and signs before rendering, so packaging and posters carry legible copy. Use 2.1 text-to-image when typography and multilingual text matter most. ### Remix up to eight references Give each reference one job — product, person, location, style — and name it by index in the prompt. Remix on 2.1 keeps each reference's identity more reliably than the Original tier. ### One-instruction edits Swap a garment, recolor a background or rewrite a sign's copy, and say 'keep everything else the same' so untouched regions hold steady. Edit takes a single source image and is available on both tiers. ### Layouts from 4:1 to 1:4 From panoramic 4:1 banners to tall 1:4 signage, plus Auto. Describe the layout to match the frame and the composition holds. ## Made with Reve Posters, fashion frames, packaging, film stills and interiors, all with clean focal hierarchy, polished light and tidy spatial relationships. ### Constructivist typographic exhibition poster ### Editorial fashion portrait with saturated color tension ### Minimalist luxury cosmetic packaging hero ### Cinematic music-video visual frame ### Modernist interior spatial study ## What people build with Reve Designers, packaging teams and art directors reach for it when an image has to be laid out as well as rendered, and when copy on the page has to read correctly. ### Poster and album-art designers Lock headline, subline and date exactly where the layout needs them, and get crisp type on the first render instead of retouching glyphs afterward. ### Packaging and e-commerce teams Mock up labels, boxes and product heroes with readable copy, then use edit to swap flavors, colors or claims across a whole line without rebuilding each shot. ### Campaign art directors Brief a clear visual hierarchy and let the planner place hero, headline and negative space. Use 2.1 for the final comp and the Original tier for cheap layout drafts. ### Fashion lookbook builders Remix a garment, a model reference and a location into a single frame, with up to eight references and a stated role for each. ### Concept artists staging scenes Build multi-subject frames with specific spatial relationships — who stands left, what hangs behind, what passes on the right — and keep in-scene signage legible. ## Reve questions ### What's the difference between Reve 2.1 and the Original model? Reve 2.1 is the higher-fidelity tier and the default; the Original is the cheaper, older one. **2.1** is the better choice for final typography, multilingual text and layout precision. **Original** costs several times less, but has weaker typography and fidelity, so use it to explore composition and copy, then finish on 2.1. ### Which Reve variant should I use for edits and remixes? Use 2.1 for final edits and remixes, and the Original for inexpensive tests. Edit takes one source image and works well for swapping an element or changing copy on a sign. Remix takes 2 to 8 references and depends on you stating each reference's role. The Original remix is less reliable at keeping each reference's identity separate. ### What is Halfmoon? Halfmoon is the name under which Reve AI, a Palo Alto lab, first previewed this model in early 2025. It is the same model family that is now released as Reve, so you are in the right place. ### How many images can I give Reve? Up to 8. With no image it generates from text, with one image it edits by instruction, and with two to eight images it remixes. For remix, give each image one job and name it in the prompt. ### What is Reve not good at? It struggles with real-person or celebrity likenesses, where moderation is strict, and with loose painterly or abstract exploration, where results can look over-clean. It has no seed or step control for reproducibility, and it won't guarantee transparent-background cutouts. Very dense text blocks can still misspell, and 2.1 is a poor fit for bulk throwaway drafts. ## Try Reve on Fuser Posters, packaging and signage where every headline lands crisp, correctly spelled and exactly where you placed it [Lay out an image](https://app.fuser.studio) ## Related models - [FLUX.3 Image](https://fuser.studio/models/flux-3-image.md) - [Gemini Image](https://fuser.studio/models/gemini-image.md) - [GPT Image](https://fuser.studio/models/gpt-image.md) - [Seedream](https://fuser.studio/models/seedream.md) - [FLUX.2](https://fuser.studio/models/flux-2.md) - [ESRGAN Upscaler](https://fuser.studio/models/esrgan-upscaler.md) Node reference: [Reve docs](https://docs.fuser.studio/docs/nodes/image/reve.md)