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
Redphase Survey Prompt Generator

Redphase Survey Prompt Generator

Creator · IamEmily2050

AI ImageX2026-07-20Added 07/28/2026Independently retestedNano Banana Pro
View original source ↗
Source ♥ 60

Prompt

Convert a user's short image request, attached image, or combination of text and images into one finished prompt for GPT Image Gen V2 or Nano Banana Pro.

Apply the Redphase Survey visual system defined below. Do not explain the system, show analysis, or add commentary. Return only the finished image prompt in the selected model's format.

Use the model named by the user or supplied by the host application. If neither names one, use GPT Image Gen V2.

For GPT Image Gen V2, return natural language prose only.

For Nano Banana Pro, return one valid JSON object only.

When both are explicitly requested, return the GPT prompt first under the line "GPT IMAGE GEN V2", then the JSON under the line "NANO BANANA PRO". Add no other text.

Write prompt content in the user's language unless another language is requested. Keep Nano Banana Pro keys in English. Preserve exact in-image text in its required script.

CORE LOGIC

Every image contains two simultaneous records.

The survey record describes what occupies the scene. It uses observed geometry, dry line, hatching, reserved paper, and a restricted set of local colors.

The red phase describes what is active through the scene. It uses one red spectral range, deep black, limited bloom, rapid falloff, and selective loss of ordinary color and detail.

The survey record answers: What is present?

The red phase answers: What is acting, passing, gathering, or changing?

Do not average the two records into red-tinted illustration. Give each record a separate job.

Before writing the final prompt, silently determine:

1. The literal subject and setting.
2. The stable material structure that belongs to the survey record.
3. One active condition that belongs to the red phase.
4. The source of that condition.
5. The path or relation through which it travels.
6. The receiving subject, object, region, or surface.
7. The visible consequence.
8. Two or three transition sites where the records meet.

Choose the active condition from the user's request. It may be physical, social, temporal, or perceptual. Valid causes include heat, movement, wind, electric current, pressure, recent touch, reflected light, sound, gaze, attention, occupancy, growth, chemical change, distance, or another condition that can be shown through visible evidence.

If the request names no active condition, use the strongest existing process already implied by the subject or action. Do not invent danger, desire, trauma, memory, menace, or supernatural activity without evidence.

Red is a measurement channel, not a mood label. Do not equate red with violence, horror, romance, or urgency unless the user's content establishes that meaning.

The active condition must have one source, one route or relation, and one consequence. Do not scatter red accents without a causal structure.

CONTENT CONTROL

Preserve the user's explicit subject, count, identity requirements, action or state, setting, era, clothing, objects,
≡Provenance · verifiedPublished prompts are human-checked against the original post; platform-reconstructed prompts are not accepted.Compare with source ↗

Models & stability

Recommended models

Nano Banana Pro
Stability
65 / 100
Cost
Medium

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 score64.5
Generated retest result
claude-sonnet-5 · 84.7gpt-5.6-sol · 44.2gap · 40.5
  • Cross-model retest: the recommended model is Nano Banana Pro, 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 score78
Generated retest result
claude-sonnet-5 · 82.9gpt-5.6-sol · 73gap · 9.9
  • Cross-model retest: the recommended model is Nano Banana Pro, 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 →
Creative Doodle Poster Generator
AI ImageXAdded 08/30/2026

Creative Doodle Poster Generator

A prompt for creating stylized posters that combine original photography with charming black-line doodle characters. It processes uploaded images by dividing the layout into an upper photographic section and a lower reimagined doodle section, capturing the visual essence and narrative quality of the original photo.

Skill · Poster information hierarchy

Prompt

Apply the same treatment: Turn each photo I upload into a separate premium-designed poster. Do not combine multiple images; output each photo separately. Use an overall 3:4 vertical composition, with the upper and lower sections in a strict

Source heat · X
91
Stability
69
View case →
General AI Character Sheet Generator
AI ImageXAdded 07/28/2026

General AI Character Sheet Generator

A comprehensive system prompt designed to create a high-quality, highly consistent character sheet, including multi-angle views, facial details, and architectural environment references.

Skill · Character and style consistency

Prompt

【Input Items】 Outfit type: [{argument name="Outfit type" default="Business / polished date outfit"}] Color direction: [{argument name="Color direction" default="Navy / red"}] If left blank, use “Business” and “Navy.” 【Reference Used】 One f

Source heat · X
6
Stability
72
View case →
Anime Character Sheet Generator
AI ImageXAdded 07/28/2026

Anime Character Sheet Generator

A comprehensive prompt for creating a standardized 2D anime character sheet from a reference image, including front, side, and back views plus design guidelines.

Skill · Character and style consistency

Prompt

Use reference: {argument name="reference image" default="one full-body reference image attached together with this instruction sheet"} Supports either a live-action person or an illustrated person. Main text: Use the single attached full-b

Source heat · X
7
Stability
70
View case →

Same creator

More from @IamEmily2050 →

  • MiniMax H3 15-Second Sci-Fi War Short: Storyboard Prompt for a Mud-Stained Wasteland Pilot and a Damaged Mechanical HeadAI Video · MiniMax H3 · 2026-09-06
  • Blackglass Ascendant System PromptAI Image · Nano Banana Pro · 2026-09-11

Same model

Latest with Nano Banana Pro →

  • 动漫定格粉彩艺术AI Image · Nano Banana Pro · 2026-11-07
  • 女子手持甜甜圈遮眼AI Image · Nano Banana Pro · 2026-11-07
  • 黄金时刻情侣肖像AI Image · Nano Banana Pro · 2026-11-07
  • 服装参考人像AI Image · Nano Banana Pro · 2026-11-07
  • Woman in a bedroom covers her face, then talks to the cameraAI Video · Seedance 2.5 · 2026-11-07
  • Woman in white on a tropical restaurant terrace with iced teaAI Image · Nano Banana · 2026-11-07

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