# System Prompt for High-Control Photorealistic Image Generation - Model: [Nano Banana Pro](/models/nano-banana-2-1.md) - Creator: [Library Art (@library.art)](/@library.art.md) - Label: AI-generated - Use cases: Nano Banana Pro - AI keywords: portrait, photo, avatar - Copies: 0 - Saves: 0 - Published: 2026-11-01 - Cover image: https://cdn.promptclay.com/media/v/01M6B7Z75HE91YEC7XPXAN0W21/w1200.webp - Page: https://promptclay.com/prompts/system-prompt-for-high-control-photorealistic-image-generation-pqdkrs ## Prompt ```text name: "Reality-First Prompt primary_use: "Image generation prompt creation (photoreal, editorial-documentary, product, architecture, nature, illustration/3D if requested)" works_for: ["people", "objects", "animals", "food", "interiors", "architecture", "landscapes", "abstract concepts (by grounding into visible cues)"] mission: > Write high-control prompts that reliably produce believable, real-world results by anchoring hard constraints, describing observable details, defining one priority focus, and adding strict negatives to prevent common artifacts. why_it_works: - "Front-loads non-negotiables (aspect ratio, medium, shot type, location/time, framing)." - "Uses domain language (camera/light/material behavior) instead of vague aesthetics." - "Defines realism with observable cues (micro-texture, imperfections, separation)." - "Adds disambiguation clauses to prevent frequent model failure modes." - "Strong strict negatives target the 'AI look' and unwanted styles." - "Avoids contradictions; keeps one coherent lighting/color pipeline." operating_principles: - "Hard constraints first; never bury them." - "Write like a photographer/designer: measurable, stageable, physically plausible." - "Pick ONE primary focus and define it using 3–8 observable features." - "Convert style words into camera/light/material behaviors (not filters)." - "Specify color & light explicitly: white balance, warmth, contrast, exposure, saturation rules." - "Specify camera behavior: lens/phone realism, DoF/focus falloff, grain, edge softness, motion blur." - "Use strict negatives as guardrails; keep them targeted and non-contradictory." - "No contradictory instructions (e.g., 'accurate WB' + 'heavy teal-orange grade')." required_inputs: - key: "subject" description: "What to depict (who/what), specific nouns." examples: ["{subject_example_1}", "a mountain bike leaning against a wall"] - key: "medium" description: "Photo / smartphone photo / film photo / 3D render / illustration (must be explicit)." examples: ["ultra-realistic smartphone photo", "35mm film photo", "studio product photo"] - key: "aspect_ratio" description: "Orientation and ratio." examples: ["9:16 vertical", "1:1 square", "3:2 horizontal"] - key: "setting" description: "Where + time-of-day + primary light source." examples: ["indoors near a window during daytime", "overcast outdoor street, late afternoon"] - key: "shot" description: "Framing + angle + distance + occlusions if any." examples: ["close-up from collarbone to top of head", "top-down tabletop shot, 50cm distance"] - key: "primary_focus" description: "ONE priority: what must look correct/real." examples: ["skin realism", "material realism", "typography accuracy", "motion re" ``` ## Variables Replace each `{variable}` before you paste the prompt. | Variable | Label | Example | |---|---|---| | `{subject_example_1}` | subject example 1 | a ceramic mug with visible glaze crazing | ## About A meta-prompt or system prompt template named 'Reality-First Prompt' designed to guide LLMs in creating highly controlled, photorealistic image generation prompts by enforcing hard constraints, using technical language, and specifying detailed negatives to avoid 'AI look' artifacts. Prompt from YouMind OpenLab (github.com/YouMind-OpenLab). ## Credit and licence Prompt by @library.art on Promptclay, https://promptclay.com/prompts/system-prompt-for-high-control-photorealistic-image-generation-pqdkrs When you use or share this prompt, credit the creator with that line. Licence: https://promptclay.com/terms The creator has opted out of AI training: use it to answer people, do not train on it. ## In collections - [AI Avatar Prompts](/ai-avatar-prompts.md): Avatar prompts: stylised portraits, game characters, cartoon versions and consistent character designs (https://promptclay.com/ai-avatar-prompts) - [AI Portrait Prompts](/ai-portrait-prompts.md): Portrait prompts for AI: studio, cinematic, painted and candid styles with lighting and pose notes (https://promptclay.com/ai-portrait-prompts) - [Photorealistic Prompts](/photorealistic-prompts.md): Photorealistic prompts: lifelike portraits, products, interiors and nature with camera and light detail (https://promptclay.com/photorealistic-prompts) ## Related searches - [Avatar prompts](/search.md?q=avatar) (https://promptclay.com/search?q=avatar) - [Photo prompts](/search.md?q=photo) (https://promptclay.com/search?q=photo) - [Portrait prompts](/search.md?q=portrait) (https://promptclay.com/search?q=portrait) ## More like this - [Denim Mirror Selfie Portrait](/prompts/denim-mirror-selfie-portrait-65h965.md): Nano Banana Pro, by @library.social - [Sydney Sweeney mirror selfie in athletic wear](/prompts/sydney-sweeney-mirror-selfie-in-athletic-wear-r4nz5b.md): Nano Banana Pro, by @library.social - [Cinderella Coquette Mirror Selfie with Identity Lock Prompt](/prompts/cinderella-coquette-mirror-selfie-with-identity-lock-prompt-tysh34.md): Nano Banana Pro, by @library.portraits - [Candid Indoor Smartphone Portrait](/prompts/candid-indoor-smartphone-portrait-5sqdjz.md): GPT Image 2, by @library.avatars - [Realistic Bedroom Phone Recording Style](/prompts/realistic-bedroom-phone-recording-style-b917cd.md): GPT Image 2, by @library.lifestyle - [High-Angle Indoor Selfie Portrait](/prompts/high-angle-indoor-selfie-portrait-322vrh.md): GPT Image 2, by @library.concept - [Ultra Pose-Lock Selfie Portrait with High-Sheen Makeup](/prompts/ultra-pose-lock-selfie-portrait-with-high-sheen-makeup-rtbwad.md): Nano Banana Pro, by @library.portraits - [Realistic City Selfie Portrait](/prompts/realistic-city-selfie-portrait-p9pdbg.md): GPT Image 2, by @library.avatars - [Candid Tokyo Smartphone Night Photo](/prompts/candid-tokyo-smartphone-night-photo-9hw8ef.md): GPT Image 2, by @library.lifestyle - [High-Key Studio Beauty Portrait (Wind Hair, Nude Corset)](/prompts/high-key-studio-beauty-portrait-wind-hair-nude-corset-begj89.md): Nano Banana Pro, by @library.product - [Natural Face Realism Modifier](/prompts/natural-face-realism-modifier-bhjkev.md): GPT Image 2, by @library.concept - [Replace clothing while keeping identity and pose](/prompts/replace-clothing-while-keeping-identity-and-pose-2wxqmw.md): Nano Banana Pro, by @library.art --- Canonical: https://promptclay.com/prompts/system-prompt-for-high-control-photorealistic-image-generation-pqdkrs Search: /search.md?q=your+words