Crimson Squat — AI Image Prompt
Prompt
Image 1 = TARGET COMPOSITION REFERENCE. Image 2 = USER IDENTITY. Recreate Image 1 geometry 1:1, but keep identity from Image 2. MANDATORY IDENTITY LOCK (HIGHEST PRIORITY - DO NOT CHANGE - LOCKED): - Use ONLY Image 2 for face identity and skin tone - Preserve exact facial structure from Image 2 (eyes, nose, lips, jawline, cheek volume, forehead) - Keep natural skin texture from Image 2 - No identity drift, no beautification, no face replacement MANDATORY 1:1 GEOMETRY LOCK (HIGHEST PRIORITY - DO NOT CHANGE - LOCKED): - Match Image 1 camera angle, distance, and framing exactly - Vertical frame 4:5 - Strong top-down angle (~35–45° above subject) - Subject centered on X=50% - Face center at Y=35% - Gloves center at Y=56% - Gloves occupy ~48–54% of frame width total - Face size target: ~22–26% of frame height - Knees visible at lower left/right corners - Red heels visible near bottom center - Do NOT zoom out, do NOT move camera back, do NOT change focal distance MANDATORY POSE LOCK (DO NOT CHANGE - LOCKED): - Deep squat - Elbows inside knees - Both gloves pressed forward under chin, touching/near-touching - Tongue out - Head pitched slightly forward toward lens - Expression playful, provocative MANDATORY STYLING LOCK (DO NOT CHANGE - LOCKED): - Red cap - Narrow dark rectangular sunglasses - Red leather jacket - Red boxing gloves - Red pointed heels - Hair visible under cap at sides MANDATORY BACKGROUND LOCK (DO NOT CHANGE - LOCKED): - Pure white seamless studio background only - No props, no shadows from external objects - Remove all text/watermarks/usernames from output MANDATORY LIGHTING LOCK (DO NOT CHANGE - LOCKED): - Bright clean studio light - Soft minimal shadows directly under subject - High clarity on gloves/leather/skin CONSISTENCY LOCK FOR REPEATED GENERATIONS (DO NOT CHANGE - LOCKED): - Keep identical composition/crop across regenerations - No random reframing - No random angle shift - No random distance shift - No random pose variation ANTI-DRIFT PRIORITY ORDER (DO NOT CHANGE - LOCKED): 1) Geometry/camera distance 2) Identity from Image 2 3) Pose/expression 4) Styling colors 5) Background purity NEGATIVE CONSTRAINTS (DO NOT CHANGE - LOCKED): - No eye-level shot - No medium/long shot - No small face in frame - No blonde hair substitution - No color/theme change - No text - No watermark - No logo - No cartoon/anime/CGI
✦ Use this prompt for free
About “Crimson Squat”
This photorealistic, portrait AI image prompt was created by AdX and is available to copy and use for free on PromptSpace. At 396 words, this is a detailed prompt that gives AI models precise instructions for generating the exact image you envision. It falls under the realistic, photography, portrait categories.
How to Use This Prompt
- 1
Copy the prompt
Click the “Copy Prompt” button above to copy the full prompt text to your clipboard.
- 2
Open your AI image generator
Open FLUX, Midjourney and paste the prompt into the text field.
- 3
Generate your image
Hit generate. For best results, use the default settings first and see how the output looks.
- 4
Experiment with variations
Change details like colors, lighting, or composition to make it uniquely yours.
- 5
Want your own face in the image?
Upload a clear, well-lit front-facing photo of yourself directly inside your AI tool (look for Image Reference, Face Swap, or IP-Adapter options) — then paste this prompt alongside it to generate images with your own face.
Recommended Settings
Aspect Ratio
2:3 (Portrait)
Quality
High / HD
Best For
FLUX, Midjourney
Style
Photorealistic, Portrait
Why This Prompt Works
The high word count gives the model rich context, reducing ambiguity and producing more consistent results. The photorealistic and portrait aesthetic signals are specific enough that the model can lock onto a distinct visual language. Explicit lighting direction (a leading signal in prompt engineering) significantly improves photo-realism and composition. Well-crafted prompts like this one combine subject precision, style vocabulary, and rendering hints — the three pillars of reliable AI image generation.
Best Model
FLUX is strongly recommended for this prompt. FLUX 1.1 Pro excels at photorealism and handles complex lighting instructions more accurately than older models.