A detailed system prompt for creating structured image prompts based on the Redphase Survey visual system, using dual tracking logic for scene occupancy and active state.
View original source ↗
Prompt · Original / Translation
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,
Reusable method
Reusable structure
Extract “target result → the subject, scene, material, and color palette → constraints” as a reusable template for similar work.
Retest criteria
Run single-variable comparisons around subject description, style intensity, lighting, and material constraints. Record the model, cost, and failures; turn it into a Skill only after it repeats reliably.
Recommended models
Keep exploring

A detailed prompt for generating a whimsical alphabet set in a 1970s graphic style, featuring playful rounded lettering, bold outlines, and bright soft-toned decorations.
Prompt
A collection of alphabet letters, {argument name="letters" default="A through Z"} and decorative elements are arranged in rows against a {argument name="background color" default="white background"}. The letters are in a playful, rounded font with thick black outlines and vibrant, pastel colors. Many of the letters are stylized with accompanying graphics: flowers, starbursts, hearts, bows, sparkles. There are also scattered floral and starburst elements throughout the composition. The overall style is reminiscent of {argument name="design era" default="1970s"} graphic design, with a cheerful and whimsical aesthetic.

Creator
Emily focuses on AI image making and is active on X. “Tea and Blood Orange Still Life in Sunlight” is the current representative case, built with GPT Image 2 awaiting a stability retest.

A bird-themed art prompt combining digital decay, fragmented pixels, and cinematic lighting effects.
Prompt
Exploding {argument name="subject" default="Song Thrush"} with regression degradation glitch distortion digital decay and broken fragmented pixels, white background, cinematic --ar 16:9 --raw --stylize 300 --hd --preview --v 8.1

A warm and natural portrait prompt depicting a young man laughing heartily in a cozy, rustic cafe.
Prompt
This vertical portrait captures a {argument name="subject" default="charming, handsome young man with wavy dark hair"}, laughing heartily while engaged in a lively conversation at a {argument name="setting" default="rustic, cozy cafe"}. He is dressed in a casual {argument name="clothing" default="olive green linen shirt"} and is seated at a worn wooden table, where a freshly brewed cup of coffee rests beside a notebook. The warm, inviting atmosphere is enhanced by soft ambient lighting, string lights glowing in the background, and the blurred silhouettes of other patrons, creating an authentic and candid sense of a relaxed afternoon spent with a friend.