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
Midjourney Fantasy Landscape Set: Places That Do Not Exist, Prompts Printed in the Art

Midjourney Fantasy Landscape Set: Places That Do Not Exist, Prompts Printed in the Art

Creator · Elias.

AI Image抖音2026-08-13Added 08/19/2026Independently retested#landscape
More tags (3)
#folk-art#seriesMidjourney
View original source ↗
Source ♥ 457

Prompt

A panoramic twilight lake viewed from a flowered bank, framed by a moss-covered hut on the far left and a huge weeping willow on the right. Four black cats appear as simple silhouettes across the foreground, quietly watching the opposite shore. A calm indigo lake stretches horizontally through the middle, reflecting faint crimson light. Beyond it, misty blue-violet trees surround a distant gothic castle with slender irregular spires. A flat vermilion moon hangs in the upper-right lavender sky. Enchanted yet slightly uncanny, dense foreground against an open luminous distance, naïve folk-art composition, oil pastel and wax crayon on rough paper, scratched sgraffito marks, layered grain, broken outlines, matte pigments, tactile handmade imperfections

--ar 4:1 --style raw --stylize 250 --chaos 4 --no people, realistic cats, photorealism, glossy 3D rendering, text
≡Provenance · verifiedPublished prompts are human-checked against the original post; platform-reconstructed prompts are not accepted.Compare with source ↗

Models & stability

Recommended models

Midjourney
Stability
76 / 100
Cost
Low

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 score75.8
Generated retest result
claude-sonnet-5 · 60.3gpt-5.6-sol · 91.4gap · 31.1
  • Cross-model retest: the recommended model is Midjourney, 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.

Keep exploring

Explore related cases.

View all AI Image Case →

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