gimina EP 209

Use the uploaded reference image as the strict identity and outfit reference. Preserve the exact facial identity, facial proportions, eyes, nose, lips, skin tone, hairstyle, hair color, visible hair accessories, outfit, styling, and overall recognizable vibe. Infer all identity, clothing, and accessories only from the reference image. Do not hardcode any traits not present.

Create a high-quality mixed-media vertical portrait featuring:

• A realistic full-body (or nearly full-body) version of the referenced subjects.

• A black hand-drawn doodle-shadow of the same subjects drawn directly on the wall beside them.

The real person and the doodle-shadow share the same playful mischievous pose concept. The real person performs a natural, photorealistic, slightly shy or embarrassed version with a cute expression ("Why am I doing this with my shadow?"), while the doodle-shadow performs a much more exaggerated, energetic, chaotic cartoon version of the same idea. The real person actively joins the pose without looking stiff.

The doodle-shadow must be black sketch line-art only, not a realistic second person, normal shadow, reflection, anime character, or full-color illustration. It should resemble the real person through hairstyle silhouette, outfit silhouette, accessories, and pose. Add manga-style motion lines, sparkles, hearts, stars, or comic marks when appropriate.

Random pose system (mandatory):

Generate a different mischievous pose every time. Never reuse fixed poses, repeated pointing, finger guns, mirrored standing poses, or identical compositions. The real person and doodle-shadow should follow the same general pose idea without matching perfectly. Inspiration may include playful idol poses, goofy dance, ta-da, peekaboo, dramatic reactions, sneaking, balancing, victory, heart poses, tiptoe, overconfident, or other fresh playful concepts.

Composition:

Vertical 9:16. Place the real person on one side and the doodle-shadow on a clean wall beside them. Show full-body or nearly full-body. Keep enough space to clearly display both figures. The doodle-shadow should be about the same height or slightly taller. Their interaction should be immediately obvious.

Background:

Minimal indoor studio or clean room corner with a white, cream, or light gray wall and clean floor. Soft natural sunlight patches or gentle wall shadows are acceptable. Keep the background uncluttered.

Lighting:

Soft natural studio lighting. Bright, clean, polished, playful mood with the face clearly visible.

Style:

Photorealistic human, strong identity resemblance, faithful outfit from the reference, black doodle-shadow, cute stylish mixed-media portrait, social-media-friendly, clean composition, no obvious AI artifacts.

Negative prompt:

Do not invent hairstyles, hair colors, accessories, outfits, or props not shown in the reference. No realistic second person, normal reflection, ordinary shadow, monster/horror shadow, anime or full-color cartoon, weak resemblance, unrelated sketch, cluttered background, repeated poses, stiff pose, mirrored pose, text, watermark, logo, distorted anatomy, extra limbs, extra fingers, or bad hands.

Use the uploaded reference image as the strict identity and outfit reference. Preserve the exact facial identity, facial proportions, eyes, nose, lips, skin tone, hairstyle, hair color, visible hair accessories, outfit, styling, and overall recognizable vibe. Infer all identity, clothing, and accessories only from the reference image. Do not hardcode any traits not present.

Create a high-quality mixed-media vertical portrait featuring:

• A realistic full-body (or nearly full-body) version of the referenced subjects.

• A black hand-drawn doodle-shadow of the same subjects drawn directly on the wall beside them.

The real person and the doodle-shadow share the same playful mischievous pose concept. The real person performs a natural, photorealistic, slightly shy or embarrassed version with a cute expression ("Why am I doing this with my shadow?"), while the doodle-shadow performs a much more exaggerated, energetic, chaotic cartoon version of the same idea. The real person actively joins the pose without looking stiff.

The doodle-shadow must be black sketch line-art only, not a realistic second person, normal shadow, reflection, anime character, or full-color illustration. It should resemble the real person through hairstyle silhouette, outfit silhouette, accessories, and pose. Add manga-style motion lines, sparkles, hearts, stars, or comic marks when appropriate.

Random pose system (mandatory):

Generate a different mischievous pose every time. Never reuse fixed poses, repeated pointing, finger guns, mirrored standing poses, or identical compositions. The real person and doodle-shadow should follow the same general pose idea without matching perfectly. Inspiration may include playful idol poses, goofy dance, ta-da, peekaboo, dramatic reactions, sneaking, balancing, victory, heart poses, tiptoe, overconfident, or other fresh playful concepts.

Composition:

Vertical 9:16. Place the real person on one side and the doodle-shadow on a clean wall beside them. Show full-body or nearly full-body. Keep enough space to clearly display both figures. The doodle-shadow should be about the same height or slightly taller. Their interaction should be immediately obvious.

Background:

Minimal indoor studio or clean room corner with a white, cream, or light gray wall and clean floor. Soft natural sunlight patches or gentle wall shadows are acceptable. Keep the background uncluttered.

Lighting:

Soft natural studio lighting. Bright, clean, polished, playful mood with the face clearly visible.

Style:

Photorealistic human, strong identity resemblance, faithful outfit from the reference, black doodle-shadow, cute stylish mixed-media portrait, social-media-friendly, clean composition, no obvious AI artifacts.

Negative prompt:

Do not invent hairstyles, hair colors, accessories, outfits, or props not shown in the reference. No realistic second person, normal reflection, ordinary shadow, monster/horror shadow, anime or full-color cartoon, weak resemblance, unrelated sketch, cluttered background, repeated poses, stiff pose, mirrored pose, text, watermark, logo, distorted anatomy, extra limbs, extra fingers, or bad hands.