LogoAhaPrompt
  • Prompts
  • Featured
  • Models
  • Submit
  • Blog
AhaPromptAhaPrompt

AI Prompts for Images, Video & Audio — Every Model, One Library

Built withLogoNEXTY.DEV
Explore
  • All Prompts
  • Featured Prompts
  • Image Prompts
  • Video Prompts
  • Audio Prompts
  • AI Models
  • Submit a Prompt
  • Blog
Languages
  • English
  • 中文
  • 日本語
  • 한국어

Copyright © 2026 AhaPrompt All rights reserved.

Privacy PolicyTerms of Service
HomeAI Prompt LibraryAI Image PromptsReal Photo Meets Anime Illustration
Real Photo Meets Anime Illustration — AI image prompt — GPT Image 2.5 — Cartoon, Anime - 1
Real Photo Meets Anime Illustration — AI image prompt — GPT Image 2.5 — Cartoon, Anime - 2

Real Photo Meets Anime Illustration

OpenAIGPT Image 2.5OpenAIimage

Create a highly detailed, charming mixed-media illustration using a real mirror selfie as the reference. Show a young woman standing inside a modern elevator, taking a mirror selfie with her smartphone. She has long, dark hair, round glasses, a relaxed expression, and wears a light blue and white striped cropped button-up shirt, loose-fitting blue denim shorts, and chunky white sneakers. Beside her, create a cute 2D hand-drawn anime version of the same woman, matching her hairstyle, outfit, body proportions, phone, and pose. The illustrated character should have oversized expressive eyes, round glasses, rosy cheeks, long messy black hair, and playful proportions. Both versions should pose with one arm resting over their heads in a casual, coordinated mirror-selfie pose. Art style: A beautiful blend of realistic photography and sketchbook-style anime illustration. Use loose black ink outlines, visible pencil strokes, textured watercolor shading, soft pastel colors, hand-drawn highlights, and slightly rough sketch lines. The illustrated character should look as if she has been drawn directly over the original photograph. Background: A realistic elevator with dark metallic walls, reflective panels, visible floor tiles, and small framed children's drawings attached to the walls. Decorate the entire scene with playful hand-drawn doodles, including pink hearts, yellow stars, purple sparkles, a smiling cloud, a cute bunny face, a little flower, and a pink ribbon. Add a black illustrated tote bag with a tiny teddy bear charm beside the cartoon character. Lighting and details: Soft indoor lighting, natural skin tones, realistic denim texture, detailed fabric folds, subtle reflections on the elevator walls, charming imperfections in the sketch lines, and a cozy pastel aesthetic. Keep the real person photorealistic while the illustrated character remains clearly cartoon-like. Composition: Full-body vertical portrait, 4:5 aspect ratio, both the real person and illustrated character visible from head to shoes, standing side by side with matching poses. Keep the doodles scattered naturally around the subjects without covering their faces. High detail, visually balanced, cute Japanese stationery aesthetic, creative social media art, polished mixed-media finish. Important: Preserve the original person's facial features, hairstyle, clothing, pose, and phone placement as closely as possible. Make the cartoon character look like a hand-drawn version of the same person, not a different character. Avoid extra fingers, distorted hands, duplicated phones, blurry faces, and excessive doodles.

Details
Type
AI Image Prompts
Aspect Ratio
941:1672
Updated
Oct 29, 2026
Category
CartoonAnime
Source

How to use this prompt

  1. 1Copy the full prompt with the copy button above.
  2. 2Open GPT Image 2.5 by OpenAI, or any image generator with a similar style range.
  3. 3Paste the prompt, then swap the subject and style keywords to match your idea.
  4. 4Match the example's settings (941:1672 · Cartoon · Anime), then iterate — small wording changes shift the output a lot.

Frequently asked questions

Which AI model generated this image?

This image was generated with GPT Image 2.5 by OpenAI. The prompt on this page is the exact text used to create it.

What settings does this prompt use?

The example was generated with GPT Image 2.5 using: 941:1672 · Cartoon · Anime. Reusing these settings gives the closest match.

How do I get similar results?

Copy the prompt as-is first, then replace only the subject while keeping the style, lighting, and composition keywords. Generate a few variations — outputs differ between runs.

Can I modify this prompt?

Yes. Prompts work best as starting points — adjust descriptors, aspect ratio, or style tags to make the output your own.

More GPT Image 2.5 prompts

Transform every visible person in the uploaded image into a realistic LEGO-style minifigure while pr — AI image prompt — GPT Image 2.5
OpenAIGPT Image 2.5
Transform every visible person in the uploaded image into a realistic LEGO-style minifigure while preserving the original environment, background, composition, lighting, and relationships. Create exactly one separate minifigure for every visible person. Preserve each person’s recognizable identity, expression, hairstyle, hair color, skin tone, proportions, pose, position, clothing, accessories, and held objects. FORMAT LOCK Vertical 3:4 composition. Show every minifigure fully from head to toe without cropping. Preserve the original group arrangement and perspective. Extend the environment naturally only when needed for the 3:4 frame. STYLE TRANSFER Convert only the people into authentic LEGO-style minifigures. Use realistic molded plastic, cylindrical heads, block-shaped torsos, standard arms and hands, short legs, printed facial features, detailed printed clothing, and molded plastic hairpieces matching each person’s hairstyle. Keep the figures seamlessly integrated into the original photograph. DETAIL & COLOR Accurately reproduce each person’s original clothing colors, patterns, layers, sleeves, collars, pants, skirts, shoes, jewelry, glasses, hats, bags and other visible accessories as LEGO prints or molded elements. Preserve original skin tones and facial expressions. Realistic plastic reflections, subtle seams, fine printed details and natural contact shadows. COMPOSITION LOCK Keep the original location, architecture, scenery, furniture, objects, colors, textures, perspective, depth, weather, atmosphere and time of day unchanged. Do not redesign or simplify the background. Preserve all existing objects in their original positions. Objects held or worn by people may be converted into LEGO-style accessories while maintaining their original appearance and color. STYLE Photorealistic LEGO-style minifigure transformation, premium 3D toy photography, realistic molded plastic, subtle glossy finish, physically accurate reflections, natural lighting, cinematic detail, seamless integration with the original scene. NEGATIVE PROMPT No changed background, studio backdrop, LEGO environment, added bricks, removed objects, extra people, missing people, duplicates, merged figures, generic characters, altered outfits, invented accessories, identity loss, wrong hairstyles, cropped bodies, missing limbs, oversized heads, realistic human bodies, real hair, real fabric, anime, cartoon exaggeration, CGI-looking environment, floating figures, excessive reflections, harsh shadows, blur, low resolution, text, logos, watermark.
Details
Create an exceptionally beautiful, stylish original female character for a sophisticated hand-drawn  — AI image prompt — GPT Image 2.5
OpenAIGPT Image 2.5
Create an exceptionally beautiful, stylish original female character for a sophisticated hand-drawn 2D animated romantic film. Adult woman, age 24. FACE DESIGN: Give her a distinctive, unconventional animated beauty. Warm golden-olive skin, a slightly elongated oval face, beautifully defined cheekbones, a delicate angular jawline, a small refined nose and naturally full muted rose-colored lips. Her eyes should be narrow, elongated, expressive almond-shaped hazel-brown eyes with slightly lifted outer corners, elegant dark eyelashes and subtly arched eyebrows. Give her a naturally confident, slightly mischievous expression, with a subtle knowing smile. Her facial design should be stylized, elegant and memorable rather than conventionally doll-like or overly cute. Add subtle warm blush across her cheeks. HAIRSTYLE: A gorgeous glossy dark espresso-brown bob haircut, reaching just below the jawline, with softly curved ends, a slightly uneven side part and delicate wispy strands framing her forehead. The hairstyle should have an elegant, effortlessly fashionable silhouette. OUTFIT: A stunning deep wine-red fitted sleeveless dress with a beautifully tailored waist, elegant neckline and a tasteful side slit. The dress should follow her slender silhouette naturally. Add delicate gold earrings, a thin bracelet and elegant pointed-toe heels. Sophisticated, feminine, bold and luxurious. BODY DESIGN: Tall, slender, elongated animated proportions, long graceful legs, narrow waist, elegant shoulders and a beautifully elongated neck. Her posture should communicate confidence and effortless sophistication. ART STYLE — EXTREMELY IMPORTANT: Traditional hand-drawn 2D animated feature-film aesthetic. Sophisticated European-inspired character animation, expressive stylized anatomy, elongated silhouettes, clean but slightly imperfect hand-inked outlines, painterly cel shading, subtle paper and brush textures, softly blended shadows and warm cinematic color grading. Use expressive animated facial construction, angular yet beautiful features, simplified but sophisticated anatomy and fluid organic shapes. The character must look like a frame from a beautifully illustrated animated movie, NOT a 3D CGI character, NOT Pixar, NOT anime, NOT a fashion doll, NOT a photorealistic human and NOT a glossy digital fashion illustration. COMPOSITION: Full-body character, standing in a relaxed three-quarter pose, one hand resting on her waist, head slightly tilted, looking sideways with a subtle playful smile. Plain warm neutral background, beautifully illustrated soft shadows, entire character visible from head to toe. Original character design, no resemblance to any specific existing character, no text, no watermark.
Details
Cute IP character or Emoji × Land art × Terrain material translation × High-altitude aerial photogra — AI image prompt — GPT Image 2.5
OpenAIGPT Image 2.5
Cute IP character or Emoji × Land art × Terrain material translation × High-altitude aerial photography. For each image, independently select a highly recognizable cute anime, game, or cartoon character, or choose an Emoji as the subject. The selection is open, for example Pikachu, Hello Kitty, Mickey Mouse, Donald Duck, or other fun cute characters and emojis. Translate the subject into a large pattern on the ground, preserving the most recognizable contours, expressions, ears, hair accessories, tails, or other iconic features, simplifying complex details so the character is clearly identifiable. For each image, freely choose a real terrain suitable for creating the artwork, such as gravel desert, sand desert, mature wheat field, salt flat, or other ground with clear texture and color contrast. Based on the chosen terrain, form the pattern in a way that matches the material properties. For example, remove gravel to expose lighter soil layers, leave shallow marks in sand, press down wheat stalks to create directional and light-dark variation, or use the color contrast between salt crust and ground surface for composition. Freely use lines, contours, or simple color planes according to material properties, preserving the natural texture of the ground and a slight sense of irregularity. Beside the subject, using the same ground material and production method, write the character's Traditional Chinese name horizontally. Use the character's commonly seen Traditional Chinese translated name; if the subject is an Emoji, write a short Traditional Chinese emoji name. The text should be complete and clear, smaller than the subject, and kept at an appropriate distance from the pattern. Viewed from high above, the complete pattern, character name, and surrounding terrain are all in frame simultaneously. The pattern and name occupy the main visual area, with sufficient terrain preserved around the edges. Depending on the scene, distant people, vehicles, field ridges, or roads may be added as scale references. For each image, freely adjust the subject's size, position, orientation, and composition based on the theme and terrain. Realistic aerial photography texture, natural lighting, clearly visible ground materials, overall clean and interesting. In the lower-left corner, create a signature using the same terrain material and drawing method as the subject: a dot first, followed by handwritten "DeepBlue." The signature color naturally follows the local material, clearly legible and integrated into the ground. 9:16 vertical format, independent single image. n=10
Details
Create a vertical 9:16 photorealistic aesthetic collage using the uploaded reference image as the la — AI image prompt — GPT Image 2.5
OpenAIGPT Image 2.5
Create a vertical 9:16 photorealistic aesthetic collage using the uploaded reference image as the layout guide. Main Concept: A stylish character collage featuring the same young woman appearing in five different scenes. Arrange four realistic photographs in a 2×2 collage background, with one large illustrated cartoon version of the woman standing in the center. Character Consistency: Use the same person's face, hairstyle, facial features, and skin tone across all five appearances. The central character should be a cute 2D anime-style illustration with large expressive eyes, a gentle smile, clean outlines, and a thick white sticker border. Outfit: A cream-colored oversized knitted cardigan with black geometric patterns and buttons, a long black skirt, white socks, beige sandals, and a cream woven shoulder tote bag. Keep the outfit identical in every scene. Background Scenes: 1. Standing outdoors on a sunny rooftop terrace, holding the woven tote bag. 2. Sitting sideways on a wooden bench beside a brick building. 3. Sitting casually on a wooden bench, raising one hand. 4. Standing near a traditional Korean-style rooftop with a gentle smile. Central Character: A full-body cartoon illustration in the exact same outfit, standing naturally while holding the woven tote bag. Place her prominently over the four background photographs with a thick white die-cut sticker outline. Visual Style: Soft golden-hour sunlight, warm film photography, pastel tones, dreamy atmosphere, natural shadows, subtle vintage aesthetic, realistic photography combined with cute anime illustration. Important: Preserve the original collage composition, clothing, accessories, poses, and background details. Maintain consistent facial identity across every appearance. High-quality details, clean composition, vertical 9:16 aspect ratio.
Details
Stylized 3D cartoon caricature based on the reference face, with a perfectly spherical oversized hea — AI image prompt — GPT Image 2.5
OpenAIGPT Image 2.5
Stylized 3D cartoon caricature based on the reference face, with a perfectly spherical oversized head, impossibly long ultra-thin cylindrical neck, huge round ears, tiny triangular nose, wide capsule eyes with sideways pupils, tiny mischievous smile, thick floating eyebrows, rounded curly hair cap, and glossy black glasses matching the reference. Cute, cheerful, playful expression. Matte clay/silicone skin and hair with subtle pores; only eyes and glasses glossy. Premium animated-film CGI, soft cinematic studio lighting, centered portrait, shallow depth of field.
Details
{  
"aspect_ratio": "9:16",  "style": "beautiful hand-drawn Japanese anime illustration, vintage fan — AI image prompt — GPT Image 2.5
OpenAIGPT Image 2.5
{ "aspect_ratio": "9:16", "style": "beautiful hand-drawn Japanese anime illustration, vintage fantasy manga aesthetic, expressive character art, painterly cel shading, detailed black ink outlines, rich cinematic colors", "prompt": "Create a beautiful, highly detailed vertical anime illustration inspired by classic fantasy manga artwork. A mysterious young adult female magician with short, voluminous golden-blonde hair, large expressive jade-green eyes and delicate round spectacles is sitting on the edge of an old wooden library desk. She wears an elegant black off-shoulder Victorian dress with long fitted sleeves, a delicate emerald pendant and subtle lace details. Her expression is curious and slightly astonished as she looks at an ancient open spellbook resting in her hands. BRILLIANT LUMINOUS EMERALD-GREEN MAGICAL ENERGY pours out from the book, forming beautiful swirling ribbons and glowing magical currents around her shoulders and through the entire room. Tiny sparkling green particles illuminate her face and hair. Several ancient books float mysteriously in midair, their pages opening and turning. Loose handwritten parchment sheets drift dramatically through the atmosphere. An enormous old-fashioned wooden bookshelf fills the left side of the composition, packed with antique books. The background features a mysterious deep forest-green library interior with beautiful architectural details disappearing into shadow. The composition feels intimate, atmospheric and full of magical movement, like an extraordinary frame from a hand-drawn fantasy anime film. COLOR AND CONTRAST: Rich luminous emerald green, bright lime-green magical highlights, warm golden-blonde hair, natural cream parchment, deep olive-green surroundings and elegant black clothing. Strong beautiful color separation. Bright glowing green magic must illuminate the character and surrounding objects. The face must remain clearly visible and beautifully lit. Deep dark background contrasted with vivid
Details
Transform the uploaded photo into a beautiful mixed-media cartoon illustration while preserving the  — AI image prompt — GPT Image 2.5
OpenAIGPT Image 2.5
Transform the uploaded photo into a beautiful mixed-media cartoon illustration while preserving the person's exact facial identity, facial features, hairstyle, expression, and natural skin tone. Art Style: Keep the face photorealistic and natural, while transforming the body, clothing, and arms into a hand-drawn 2D comic illustration. Use thick, clean black ink outlines, smooth cel shading, soft pastel colors, and slightly exaggerated cartoon details. Clothing: Convert the outfit into a stylish oversized light-blue jacket, white inner top, and loose blue trousers, illustrated with bold black outlines and natural fabric folds. Background: Keep the original background photorealistic, with natural lighting and realistic details. Create a beautiful contrast between the realistic background and illustrated character. Cute Details: Add small white cartoon angel wings with thick black outlines near both shoulders and a tiny red heart on one cheek. Important: Maintain the original person's identity and recognizable face. The face must remain realistic, not anime or cartoon. Only the body and clothing should have the hand-drawn comic effect. Make the illustration look like a professionally edited viral social media photo. High quality, clean line art, beautiful pastel blue tones, sharp details, seamless photo and illustration blending.
Details
{
  "aspect_ratio": "9:16",
  "style": "Black and white manga ink sketch, detailed hand-drawn illust — AI image prompt — GPT Image 2.5
OpenAIGPT Image 2.5
{ "aspect_ratio": "9:16", "style": "Black and white manga ink sketch, detailed hand-drawn illustration", "prompt": "A beautiful young anime woman with large expressive eyes, long eyelashes, full lips and a dreamy sideways gaze. Extremely voluminous messy black hair tied in a loose high bun, with wispy bangs and wild flowing flyaway strands. Her head is slightly tilted, resting gently on one hand, with naturally curved fingers supporting her cheek. She wears an oversized black sweater with loose sleeves and detailed fabric folds. Medium close-up portrait, head and upper torso visible, centered composition. Intricate black ink linework, fine cross-hatching, delicate pencil shading on the face, dense black hair strokes with white highlights, expressive sketchy outlines. Pure white paper background with a tiny hand-drawn heart doodle in the upper right corner. Strong black and white contrast, authentic manga illustration, elegant, dreamy and playful.", "negative_prompt": "Color, 3D, photorealism, watercolor, extra fingers, distorted face, messy background, text, watermark, blurry details" }
Details
Browse all GPT Image 2.5 promptsExplore AI Image Prompts