Use the uploaded character reference image as the strict identity and outfit reference.
Fields you can change: character reference, pose, expression.
Full prompt
Use the {argument name="character reference" default="uploaded character reference image"} as the strict identity and outfit reference. Preserve the reference character’s: face identity, facial proportions, eye shape, nose, lips, skin tone, hairstyle, hair color, visible hair accessories, overall recognizable vibe, outfit and styling shown in the reference image. Do not hardcode any specific character traits that are not present in the uploaded reference. All identity, hairstyle, accessories, and clothing details must be inferred directly from the uploaded reference image. Create a high-quality mixed-style vertical portrait showing: 1. a realistic full-body version of the uploaded character/person 2. a black hand-drawn doodle-shadow version of the same character/person on the wall beside them. Core concept: The real person and their doodle-shadow are doing a {argument name="pose" default="playful mischievous pose"} together. The real person performs a cute realistic version of the pose, while the doodle-shadow performs a much more exaggerated, chaotic, cartoonish version of the same pose idea. The mood should feel cute, playful, mischievous, stylish, funny, and social-media-friendly. Real person: Must remain realistic and photogenic, wear the same outfit style and key visible details from the uploaded reference image. Expression should be {argument name="expression" default="cute, slightly confused, mildly embarrassed, playful"}, as if thinking: “Why am I doing this with my shadow?” Doodle-shadow: Must be a black hand-drawn sketch version of the same person, drawn directly on the wall. Black sketch line-art only. Should resemble the person through hairstyle silhouette, accessories, outfit silhouette, and pose structure. Add manga-like motion lines, hearts, stars, sparkles, and comic marks around the doodle if helpful. Create a different mischievous pose each time. Possible pose directions: playful idol pose, silly dance pose, leaning sideways with one arm curved overhead.
{
"prompt_configuration": {
"type": "Ultra Photorealistic Portrait",
"style": "Cinematic Reality",
"resolution": "8K"
},
"subject": {
"demographics": "{argument name="subject" default="Billie Eilish"}, athletic build, fit physique, pale complexion",
"hair": "Dark brown to black hair, pulled back into a messy high ponytail, loose sweaty strands framing the face",
"skin_texture": "Hyper-realistic skin details, intense post-workout sheen, glistening with heavy sweat, visible pores, slight flush on cheeks",
"facial_expression": "Exhaling slightly, mouth slightly open in a 'phew' expression, focused gaze, tired but accomplished"
},
"apparel": {
"outfit_style": "Monochromatic pastel pink gym set, athleisure",
"top": "Tight cropped pink camisole/tank top with spaghetti straps, rolled up slightly",
"bottoms": "Loose-fitting pink sweatpants with visible drawstring and elastic waistband, soft cotton texture",
"accessories": "Thin silver necklace"
},
"pose_and_action": {
"perspective": "Three-quarter side profile view facing left",
"action": "Body checking in a gym mirror, left hand pressing against the mirror surface, right hand lifting the hem of the shirt to reveal defined abdominal muscles (six-pack)",
"reflection": "Partial reflection of the arm visible in the mirror on the left edge"
},
"environment": {
"location": "Commercial gym interior",
"background_elements": "Blurred gym equipment, weight racks, cable machines, dumbbells, other gym-goers faintly visible in the distance",
"flooring": "Black speckled rubber gym flooring"
},
"lighting_and_atmosphere": {
"lighting_type": "Overhead artificial gym lighting",
"quality": "Warm tungsten tones",
"mood": "Intense, raw, fitness-focused, candid moment"
},
"technical_specifications": {
"camera": "DSLR, 85mm portrait lens",
"aperture": "f/2.8",
"focus": "Sharp focus on subject's face and abs, creamy bokeh background",
"render_details": "Unreal Engine 5, Octane Render, ray tracing, subsurface scattering on skin, volumetric lighting"
}
}
Generate a 9-image “photo dump” grid of this person’s weekend: a mirror selfie, a café shot, friends at dinner, a blurry party photo, a walking shot, a laptop-and-coffee work shot, a pet moment, a sunset, and a candid laugh.