Text to Image

Handmade Collectible Male Doll — AI Image Prompt

A creative prompt to turn a reference photo into a high-fidelity handmade fabric doll interacting with a giant candy bar in a macro diorama style. - AIPinMaker

GPT Image 23D CGIText to Image
Handmade Collectible Male Doll
Text to Image

Prompt

Use the uploaded photo as the sole reference for identity. Maintain maximum facial resemblance, preserving facial features, proportions, expression, hairstyle, skin tone, and natural asymmetries with extreme accuracy. Create an adorable handmade premium collectible male doll with a slightly oversized head, a small slender body, soft felt and fabric textures, realistic 3D facial details, lifelike glass eyes, and handcrafted stitching. The tiny doll tightly hugs a giant {argument name="candy bar" default="KitKat bar"} almost as large as himself, with several bite marks already taken from it. He wears a playful, satisfied smile with {argument name="detail" default="chocolate smudges"} around his lips, cheeks, and fingertips. A few drops of melted chocolate are scattered on the floor beneath him. A giant human finger gently lifts him by the back of his shirt collar, but he stubbornly refuses to let go of the KitKat, creating a humorous and adorable scene. Emphasize dramatic size contrast, warm bright lighting, a clean minimalist background, premium diorama craftsmanship, macro photography, shallow depth of field, ultra-realistic textures, and exceptional facial fidelity to the uploaded reference photo.

Prompt breakdown

Subject
Handmade male doll with oversized head and slender body hugging giant KitKat bar showing bite marks, chocolate smudges on lips/cheeks/fingertips, melted drops on floor, lifted by giant finger at shirt collar
Style
Premium collectible doll made of soft felt and fabric, realistic 3D facial details, lifelike glass eyes, handcrafted stitching, ultra-realistic textures, macro photography, premium diorama craftsmanship
Lighting
Warm bright lighting
Composition
Dramatic size contrast between tiny doll and oversized candy, clean minimalist background, shallow depth of field, exceptional facial fidelity to reference photo
Mood
Humorous and adorable with playful satisfied smile

Remix ideas

  • Change the KitKat to a different oversized candy like a Reese’s cup while keeping the bite marks and chocolate smudges
  • Alter the lifting finger to a pair of tweezers or a spoon for a new intervention method
  • Increase the number of chocolate drops on the floor and add a small puddle beneath the doll’s feet

Reference images

Handmade Collectible Male Doll reference
Text to Image

How to use this AI Image prompt template

  1. AiVideo Maker stepOne1
    Copy the prompt — grab this template’s prompt and negative prompt.
  2. iVideo Maker stepTwo2
    Pick a model — choose a recommended AI model for the best match.
  3. AiVideo Maker stepThree3
    Generate — open the studio with one click and create your result.

Related templates

Cinematic Sci-Fi Delivery Game Screenshot
GPT Image 2

Cinematic Sci-Fi Delivery Game Screenshot

{ "type": "video game screenshot", "style": "photorealistic, cinematic, post-apocalyptic sci-fi", "scene": { "character": "A {argument name=\"character face\" default=\"middle-aged Asian man resembling Richard Liu\"} in a futuristic black tactical delivery suit with blue glowing accents and a 'JD' logo on the shoulder. He is looking off into the distance with a serious expression.", "equipment": "Carrying a massive, heavy-duty red and black mechanical cargo backpack. The backpack features the text '{argument name=\"company logo\" default=\"京东秒送 JD Express\"}' and a graphic of a {argument name=\"mascot\" default=\"cartoon white dog\"}.", "environment": "Bleak, rocky, overcast wasteland with dark volcanic soil, a distant body of water, and a futuristic industrial facility in the background under a cloudy, moody sky." }, "ui_overlay": { "top_left": "Quest tracker with three lines of text indicating chapter progress, current objective, and delivery order details.", "top_right": "Network status with a star icon and text indicating network coverage and region.", "center_right": "Waypoint marker pointing to a distant facility with text indicating destination and distance of 1328m.", "bottom_left": "Abstract futuristic HUD status icons including circles, squares, and directional arrows.", "bottom_center": "Cinematic subtitles reading '{argument name=\"subtitle text\" default=\"刘强东:不管多远的路,京东秒送,使命必达。\"}'.", "bottom_right": "Game logo reading '{argument name=\"game title\" default=\"DEATH STRANDING 2 ON THE BEACH\"}'." } }3c:T663,{ "type": "video game screenshot", "st

cyberpunkmanphotorealistic
Text to Image
3D Collectible Toy Diorama
GPT Image 2

3D Collectible Toy Diorama

Create a highly detailed 3D collectible toy diorama of a stylish young couple sitting at an outdoor café table (subject), inspired by a real-life reference photo. Transform both people into premium designer vinyl figures (style) with smooth glossy plastic surfaces, articulated toy-joint details, oversized expressive eyes, realistic facial features, and fashionable outfits. The female figure has dark braided hair, black sunglasses, gold earrings, layered gold necklaces, and a white V-neck blouse. She rests her chin on her hand while smiling at her companion. The male figure has thick wavy dark hair, black sunglasses, a white t-shirt, and a silver wristwatch while drinking coffee from a white ceramic cup. Both figures sit at a wooden café table with coffee cups, saucers, and spoons. The setting is an elegant European-style outdoor café (location) with warm beige architecture, large windows, blue umbrellas, lush green trees, and softly blurred background guests. Style: Pixar-inspired collectible toy, premium vinyl figure, designer toy aesthetic, ultra-realistic 3D render, glossy plastic texture, toy photography, shallow depth of field, cinematic lighting, warm golden-hour sunlight, photorealistic materials, high-end commercial product photography, sharp focus, ultra detailed, 8K resolution. Composition: Front-facing medium shot, both characters centered, natural poses, café ambiance, depth and realism, professional advertisement quality. Render Quality: Octane Render, Unreal Engine 5, ray tracing, global illumination, realistic reflections, HDR lighting, highly detailed textures, collectible figurine showcase.36:T

manwomanphotorealistic
Text to Image
Pixar-Style Earbuds Miniature Scene
GPT Image 2

Pixar-Style Earbuds Miniature Scene

Create an ultra-detailed 3D Pixar-style miniature scene using the uploaded reference image as the exact face and hairstyle reference for the character. A cute young man with the same face, hairstyle, skin tone, and overall appearance as the uploaded image is relaxing inside an open wireless earbuds charging case placed on a wooden desk. He has long open black hair, soft expressive eyes, and a gentle natural smile. He is wearing the exact same outfit from the uploaded reference image. The character is lying comfortably inside the earbuds case in a relaxed pose, resting his head on one hand while one leg is casually placed over the other. Next to the charging case, a modern smartphone is placed vertically on a stand displaying a clean minimal music player UI. The screen shows the song name ‘ordinary (song name)’ with elegant album art, a play button, and a progress bar. Two wireless earbuds are casually placed near the charging case on the desk. The environment has soft warm natural window lighting creating a cozy cinematic atmosphere. Background should be softly blurred with aesthetic bokeh and a minimal modern desk setup. Style should look like a premium cinematic 3D render with smooth textures, soft shadows, depth of field, ultra realistic lighting, highly detailed materials, and adorable Pixar-inspired proportions. High resolution, realistic reflections, cozy mood, centered composition, professional product-advertisement quality.39:T

manmacroultra-detail
Text to Image
Real Hiker in Minecraft Forest
GPT Image 2

Real Hiker in Minecraft Forest

Create a cinematic Minecraft-style screenshot of a lone real human hiker walking away from the camera through a dense blocky forest. The person should remain realistic rather than voxelized: an adult man seen from behind, wearing a light beige wide-brim hiking hat, muted teal short-sleeve shirt, dark gray shorts, black hiking shoes, and a large black backpack, centered slightly left on a dirt-and-stone trail. Transform the entire environment into a vivid Minecraft world made of cubes: tall square-trunk trees with pixelated bark, cubic leafy canopies, stepped grassy dirt banks on both sides, blocky gray stone cubes, pixelated tall grass, and a winding path of brown dirt and cobblestone blocks leading into the distance. Use bright midday sunlight filtering through the trees, strong dappled shadows, saturated greens, blue sky with blocky white clouds visible through the canopy, high detail, wide-angle adventure-game composition, realistic lighting with voxel geometry, no text, no UI, no watermark. Customize the subject as adult male hiker (main subject), clothing as beige hiking hat, muted teal T-shirt, dark gray shorts, black backpack (outfit), setting as dense Minecraft forest trail (environment), lighting as bright midday sun with dappled shadows (lighting), and camera view as rear view, eye-level wide shot (camera view).

manpixel-artphotorealistic
Text to Image
GTA-Style Dialogue Screenshot
GPT Image 2

GTA-Style Dialogue Screenshot

{ "type": "video game screenshot", "style": "{argument name=\"art style\" default=\"Grand Theft Auto VI aesthetic, realistic 3D graphics\"}", "setting": "balcony overlooking a coastal city at sunset, palm trees, skyscrapers, warm lighting", "characters": [ { "role": "NPC", "description": "{argument name=\"npc description\" default=\"Omni-Man, muscular older man with a mustache and grey temples, wearing a red and white superhero suit\"}", "position": "center-left, facing camera" }, { "role": "Player", "description": "man wearing a backwards dark baseball cap and light grey t-shirt", "position": "right foreground, back to camera" } ], "ui_elements": { "type": "dialogue menu", "position": "bottom center", "speaker_name": "{argument name=\"speaker name\" default=\"OMNI-MAN\"}", "dialogue_text": "{argument name=\"npc dialogue\" default=\"This planet isn't yours to protect. Viltrumite rule is inevitable.\"}", "choices_count": 3, "choices": [ "1. {argument name=\"choice 1\" default=\"You're not taking over anything.\"}", "2. What do you want from me?", "3. I don't care about your politics." ], "highlight": "Choice 1 has a translucent purple background bar" } }

photorealisticgolden-hourman
Text to Image
3D Figure Emerging from Pencil Sketch
GPT Image 2

3D Figure Emerging from Pencil Sketch

A high-angle, top-down perspective of a surreal mixed-media artwork on a wooden desk, where a middle-aged man (subject) , having the uploaded face as reference, is dramatically emerging from a large sheet of white paper. His upper body is a photorealistic 3D figure dressed in a sharp black suit jacket and an open-collar white shirt (clothing), while his lower body seamlessly transitions into a detailed 2D graphite pencil sketch on the paper. He presses his hands against the torn, ripped edges of the paper as if climbing out of the drawing. Scattered around the paper on the wooden table are oversized wooden drawing pencils and white erasers, creating a sense of scale. The bottom of the paper features a stylized handwritten signature that reads "Mr. Dilshad (signature)" accompanied by a small gold crown and a lightning bolt. The scene is illuminated by warm, dramatic overhead lighting that casts soft shadows and creates a golden rim light behind his shoulders. The composition uses a shallow depth of field, focusing sharply on the man's realistic features while the surrounding desk elements are softly blurred, blending photorealism with classic sketching in a stunning trompe-l'œil illusion.3

top-downmanphotorealistic
Text to Image

Explore more prompts

Browse more AI image and video prompts by category.

FAQ

How do I keep the doll’s face identical to my reference photo?
The prompt explicitly directs the model to treat the uploaded photo as the sole identity reference and preserve every facial proportion, expression, hairstyle, skin tone, and natural asymmetry with extreme accuracy.
Can the doll hold something other than a KitKat?
Yes, swap the candy bar description for any other giant treat while retaining the bite marks, chocolate evidence, and refusal-to-let-go action to preserve the humorous scale contrast.