veryCoolTimo/imagegen-skills / skills/image-prompt
image-prompt
FlaggedUse when the user wants to turn a short idea into a rich, production-grade image-generation prompt — posters, landing-page or UI mockups, ads, editorial layouts, photoreal scenes, game screenshots, logos, or illustrations. Builds ONE structured, copy-paste-ready prompt optimized for OpenAI GPT Image 2.6 by default, following proven layered-composition patterns (named zones, hex palette, real font references, mood/finish, IP-safety). Triggers on requests like "сделай крутой промт для постера", "нужна картинка/постер/лендинг для…", "generate a prompt for a landing hero", "prompt for an ad / logo / game screenshot".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.4 KB |
| references/anatomy.md | markdown | 7.5 KB |
| references/archetypes.md | markdown | 8.6 KB |
| references/edit-remix.md | markdown | 6.5 KB |
| references/fonts-palettes.md | markdown | 3.9 KB |
| references/generation.md | markdown | 3.1 KB |
| references/gold-examples.md | markdown | 23.2 KB |
| references/models/flux.md | markdown | 3.8 KB |
| references/models/gemini.md | markdown | 4.4 KB |
| references/models/gpt-image.md | markdown | 10.5 KB |
| references/models/ideogram.md | markdown | 3.3 KB |
| references/models/midjourney.md | markdown | 3.7 KB |
| references/models/recraft.md | markdown | 4.7 KB |
| references/models/reve.md | markdown | 3.9 KB |
| references/models/universal.md | markdown | 2.0 KB |
| references/styles.md | markdown | 5.2 KB |
references/models/reve.md
View on GitHub# Model adapter — Reve (Reve 2.0)
Top-tier model (~#2 on Artificial Analysis, mid-2026). Defining trait: it resolves the prompt
into a structured **layout** ("images as code") before rendering native 4K — so its edge is
**prompt adherence + layout/element editing** and **legible typography**. Output is prompt text
only.
## Prompt style
- **Plain, direct natural-language prose** — not keyword salad, not overly poetic. Describe
subject, composition, mood, style, lighting in a clear paragraph; Reve derives the layout.
- **Be specific and concrete** — name **position, lighting source, and medium**; that improves
adherence more than piling on adjectives.
- **Structured simplicity — one clear intent, minimal modifiers.** Mixing several art styles
degrades results. Reve's thesis: "ambiguity is the enemy of control."
- Note: "Enhance" is on by default in the app (rewrites your prompt); 2.0 can occasionally drop
a prompt element — verify output and fix via a layout edit rather than re-rolling.
## Text in images
- Quote the exact copy: `the sign reads "KELLERMAN'S HARDWARE — SINCE 1931"`.
- Describe font/weight/case/placement ("bold condensed sans-serif masthead, top-centered, all
caps"). Good for mastheads, packaging, poster headlines, UI labels.
- Keep text short/prominent; very small/dense text can garble or typo — verify spelling; fix a
bad string via layout edit.
## Editing / references (its strength)
- **Instruct edit:** input image + plain instruction. **"Change X, keep the rest"** works well —
state what changes AND what to preserve ("move this object, shrink that text block, keep the
subject, adjust the background, preserve the structure").
- **Layout/region edit:** select any element and edit its node (position, size, text) without
redrawing the scene — the layout is the persistent source of truth.
- **Remix / multi-reference:** feed **1–4 reference images** as ingredients; Reve borrows
character / lighting / material / environment from each and merges. More descriptive style
text + a stronger reference = more accurate.
- **Weakness:** real-photo multi-subject **identity preservation** is less exact than Nano
Banana Pro — recognizable, not pixel-faithful. For strict likeness, prefer gpt-image-2.6 /
Nano Banana Pro.
## Aspect ratios / resolution
- **7 ratios:** `16:9 9:16 3:2 2:3 4:3 3:4 1:1` (API default `3:2`).
- Native **2048×2048**, upscalable to **4096×4096 (4K)**. Output PNG/JPEG/WebP.
- Prompt budget ~**2560 characters**.
## Params / API
Base `https://api.reve.com/v1/` — operations **Create / Edit / Remix** (+ upscale, background
removal, resize, saved effects). Third-party aggregator IDs (unconfirmed as native):
`reve/create-image` (`prompt`, `aspect_ratio` def `3:2`), `reve/edit-image` (`image_url` +
`prompt`), `reve/remix-edit-image` (`image_urls` 1–4). No documented `seed`/`negative_prompt`/
`width-height` in that schema — verify against the native API.
## Output template
```
[Subject + key attributes], [composition & where each element sits]. [In-image text in quotes] rendered as [font/weight/case], [placement]. Style: [one coherent medium/aesthetic]. Lighting: [single clear source/direction]. Palette: [2–3 colours or mood]. [aspect ratio], 4K.
```
Editing: `Keep [everything to preserve] exactly as is; change only [X] to [Y].`
Remix: `Combine these references: use [ref 1] for the character, [ref 2] for lighting/environment; render as [style]. [scene].`
**Report in assumptions:** `model=reve · aspect=<…> · 4K`.
## Sources
blog.reve.com (Reve 2.0 announcement, "The Layout Bet", editing model), help.reve.com (API — 403 to bots), app.reve.com; Artificial Analysis leaderboard; reputable reviews (Decrypt, Morphic, WaveSpeed). Uncertain: official prompt docs are thin (product/philosophy pages, not a formal guide); model IDs + 2560-char limit are from a third-party aggregator, not confirmed native.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |