Select AI Model
{ "prompt": "A hyper-realistic, wide shot of creative street art on a white building wall. A mural of a beautiful woman with an anime-style face, pale skin, and delicate features is painted on the wall. A real, massive, vibrant {argument name="flower color" default="purple"} flowering bush (possibly Crepe Myrtle or Jacaranda) growing from behind the wall is perfectly positioned to look the woman's massive, voluminous afro-style hair. She is wearing a painted {argument name="dress color" default="purple"} dress that matches the flowers. The setting is a paved street with traditional Asian-style tiled roofs visible. Sunny day, blue sky, cinematic lighting, resolution, trompe-l'œil optical illusion.", "negative_prompt": "blurry, low quality, distorted, ugly, pixelated, text, watermark, bad anatomy, bad perspective, gloom, dark", "aspect_ratio": "3:4", "style": "Photorealistic, Street Art Photography" }, Extreme macro close-up focusing on intricate micro-textures, captured on Arri Alexa Mini LF with Cooke Anamorphic /i Prime 40mm lens, High-key crisp editorial studio lighting with subtle catchlights in eyes, authentic skin micro-textures, true-to-life surface physics, 8K ultra-detailed editorial photography
Master Version
Prompt Architecture & Anatomy
🧠 Prompt Engineering & Structural Breakdown
- Core Intent: Achieve precise task completion with zero conversational filler and maximum actionable depth
- Role & Persona: Domain expert practitioner with specialized technical insight and pedagogical clarity
- Context & Assumptions: Clear input parameters, defined audience proficiency, and stated foundational assumptions
- Constraints & Boundary Rules: Strict negative constraints: no vague advice, no unsupported claims, adherence to requested format
- Output Structure & Format: Hierarchical markdown organization with bold callouts, ordered steps, and clean tabular data where applicable
- Verification & Quality Checks: Self-correcting validation step ensuring all prompt constraints and sub-questions are fully addressed