GoodCase.aiAI News · Radar↗AI Map↗Course · LearnPrompt↗
ProjectsGoodCase.aiAI News Radar ↗AI Map ↗LearnPrompt ↗
GoodCase.aiGoodCase.aiAI Prompt Case Collection
GoodCase.ai
RankingsCasesSkillsFavoritesSubmitDailyJoin us
中文EN
Agent Access →

Projects

AI News · Radar ↗AI Map ↗Course · LearnPrompt ↗
GoodCase.aiGoodCase.aiAI Prompt Case Collection
RankingsCasesSkillsFavoritesSubmitDailyJoin us
中文EN
Agent Access →

Loading…

GoodCase.ai · AI Prompt Case Collection
DSH PluginsChangelogFeedback
ModelsCreatorsSeedance 2.5Seedance 2.0GPT Image 2GeminiNano Banana ProClaudeClaude Opus 5.5Grok ImagineVeoKlingQwen ImageGPT Image 1.5MiniMax H3
Velvet Grapes — Violet Rococo Halftone Poster

Velvet Grapes — Violet Rococo Halftone Poster

Creator · v92388375-gif

AI ImageGitHubAdded 07/31/2026Independently retested#poster#pixel-style-poster
More tags (9)
#halftone#editorial#rococo#fruit#reconstructed-prompt#verified-rerun#github#mitCodex 内置出图
View original source ↗

Prompt

GoodCase reconstructed prompt — derived from the public result image and the creator's public Skill method, then verified with two independent generations. This is not the creator's disclosed original prompt; the original model, seed, and exact prompt are unknown.

Use case: stylized-concept
Asset type: prompt-reconstruction stability test for a vertical editorial poster

Create a vertical 3:4 flat scanned-paper poster on warm cream, lightly aged uncoated stock. Center one abundant bunch of ripe grapes inside a large ornate rococo oval frame or serving-platter border. The grapes and frame should occupy about 76% of the page, with a graceful diagonal stem entering from the upper right. Place the title in a sweeping diagonal arc across the upper-left area, close to the top of the frame.

Render the grapes, stem, cast tonal bed, and elaborate frame entirely in one deep velvet-violet ink. Use fine micro-dot halftone, tiny square-pixel mesh, antique copperplate/engraving linework, stippled highlights, broken ink coverage, and density-based shading. Each grape should remain round and luminous through white paper highlights and dense-to-sparse violet dots, not smooth photography. The rococo border needs symmetrical scrolls, curls, shell motifs, and delicate worn linework. Keep everything flat, printed, slightly misregistered, softly scanned, and tactile with paper fibers and toner dust.

Render the exact title "Velvet Grapes" once, large and sweeping in an elegant calligraphic italic Didone serif across the upper left. Add these exact small monospaced/typewriter captions once each with sparse dotted leader lines: "ripe & bright" at upper right, "cool harvest" at mid-left, "sweet skin" centered along the lower frame, and "07.25" at bottom center. A few tiny ornamental fleuron marks are allowed. No other readable text.

Mood: strange luxurious fruit specimen, antique rococo plate meets modern Japanese editorial bitmap print. Avoid retro game pixel art, chunky pixels, game sprites, sticker art, cartoon fruit, smooth vector fills, watercolor, glossy food photography, multiple ink colors, gold metallic effects, 3D depth, cinematic lighting, dense collage, extra fruit species, extra text, repeated labels, logos, watermark, UI, CTA, product advertisement, and mockup photography.
≡Provenance · verifiedPublished prompts are human-checked against the original post; platform-reconstructed prompts are not accepted.Compare with source ↗

Models & stability

Recommended models

Codex 内置出图
Stability
80 / 100
Cost
Medium
Related SkillsPoster information hierarchy ↗Editorial portrait composition ↗

Independent retest evidence

See what the same prompt generated in our test.

Retest output · not the creator's original
ImageGenerated evidenceAI judged

Grok Imagine

Sep 2, 2026

Retest score80.3
Generated retest result
claude-sonnet-5 · 68.7gpt-5.6-sol · 92gap · 23.3
  • Cross-model retest: the recommended model is Codex 内置出图, and this run used Grok Imagine. The result shows how the same prompt carries over to Grok Imagine; it does not show what the creator got with the original model.
  • The retest score is the mean of two AI judges (0–100) for this single generation. No person has reviewed it, and it is not a success rate.

The requested model is recorded, but the generation receipt did not expose a verifiable underlying model ID.

ImageGenerated evidenceAI judged

GPT Image 2

Aug 9, 2026

Retest score93.3
Generated retest result
claude-sonnet-5 · 89.6gpt-5.6-sol · 97.1gap · 7.5
  • Cross-model retest: the recommended model is Codex 内置出图, and this run used GPT Image 2. The result shows how the same prompt carries over to GPT Image 2; it does not show what the creator got with the original model.
  • The retest score is the mean of two AI judges (0–100) for this single generation. No person has reviewed it, and it is not a success rate.

The requested model is recorded, but the generation receipt did not expose a verifiable underlying model ID.

Keep exploring

Explore related cases.

View all AI Image Case →
Night Lily — Mint Halftone Botanical Poster
AI ImageGitHubAdded 07/31/2026

Night Lily — Mint Halftone Botanical Poster

GoodCase reconstructed this prompt from the public result image and the creator's MIT-licensed Skill method, then ran two independent generations without the source image or a fixed seed. Both runs preserved the mint single-ink halftone, engraved botanical texture, editorial typography, and requested copy; one run drifted from 3:4. A/B stability: 7.8/10. This is not the creator's disclosed original prompt; the original model, seed, and exact prompt are unknown.

Skill · Poster information hierarchySkill · Editorial portrait composition

Prompt

GoodCase reconstructed prompt (not the creator's original): a vertical 3:4 mint-green halftone lily poster with an oversized Didone title and sparse specimen labels.

Source heat · GitHub
—
Stability
81
View case →
Quiet Flight — Deep Teal Butterfly Poster
AI ImageGitHubAdded 07/31/2026

Quiet Flight — Deep Teal Butterfly Poster

GoodCase reconstructed this prompt from the public result image and the creator's MIT-licensed Skill method, then ran two independent generations without the source image or a fixed seed. Both runs preserved the oversized cropped butterfly, deep-teal single ink, bitmap engraving, editorial title, labels, paper texture, and 3:4 ratio. A/B stability: 9.3/10. This is not the creator's disclosed original prompt; the original model, seed, and exact prompt are unknown.

Skill · Poster information hierarchySkill · Editorial portrait composition

Prompt

GoodCase reconstructed prompt (not the creator's original): a vertical 3:4 deep-teal entomological poster with an oversized cropped butterfly and Didone title.

Source heat · GitHub
—
Stability
78
View case →
Half-Photo, Half-Print Travel Portrait Collage
AI ImageXAdded 09/24/2026

Half-Photo, Half-Print Travel Portrait Collage

📸 Upload your photo → paste the prompt → let AI transform it into a stunning poster. GPT Image 2.5 Prompt: Turn this portrait photo into a single high-end half…

Skill · Poster information hierarchySkill · Editorial portrait composition

Prompt

Turn this portrait photo into a single high-end halftone travel-collage poster. Output one poster per uploaded photo — never merge multiple photos into one frame. FORMAT 3:4 vertical canvas. Split i…

Source heat · X
83
Stability
View case →

Each detail page keeps the original result, the prompt, and retest evidence in one reading path.