
Loading…
Loading…

Creator · varts_works
View original source ↗Use the attached image as the most important reference.
The uploaded character must be the main subject.
Preserve the face, hairstyle, hair color, eyes, outfit, body type, accessories, art style, and apparent age.
Create {argument name="名前" default="⭐️"} as a gigantic three-dimensional object.
━━━━━━━━━━━━━━━━━━
【Text Design】
━━━━━━━━━━━━━━━━━━
・Turn the entire name into one gigantic three-dimensional object
・Design the font to match the character’s atmosphere
・Create a cute, stylish, luxurious three-dimensional form
・Use thick, substantial 3D lettering with a strong presence
・Automatically select the material best suited to the character, such as glossy, glass, matte, metal, candy, crystal, plush, cloud, or floral materials
・Automatically determine colors that match the character
・Ensure the name is easy to read
━━━━━━━━━━━━━━━━━━
【Character】
━━━━━━━━━━━━━━━━━━
Have the character pose naturally on top of the text object.
Randomly select a cute pose such as:
・Lying down
・Sitting
・Dangling their legs
・Reclining
・Jumping
・Standing
・Leaning against the text
・Making a heart shape
・Waving
・Looking toward the viewer with a smile
Naturally balance the size of the text with the scale of the character.
━━━━━━━━━━━━━━━━━━
【Background】
━━━━━━━━━━━━━━━━━━
Automatically generate a background that matches the character’s world and aesthetic.
Examples
・Pastel
・Fantasy
sculpture
・Outer space
・Flower field
・Neon
・Starry sky
・Gothic
・Candy land
・World of ice
・Japanese style
・Forest
・Underwater
・Above the clouds
Unify the background color, lighting, effects, decorations, props, and atmosphere to match the character.
━━━━━━━━━━━━━━━━━━
【Framing】
━━━━━━━━━━━━━━━━━━
・Landscape orientation (4:3)
・Include the full body
・Do not crop any part of the name
・Center both the character and the text
・Polished enough for use as a social media icon or profile image
━━━━━━━━━━━━━━━━━━
【Image Quality】
━━━━━━━━━━━━━━━━━━
Ultra-high quality
Ultra-high definition
Cute
Social-media-ready
Beautiful lighting
Cinematic-quality lighting
Sharp
Vibrant
Intricately detailed
Professional quality
No text other than the name objectModels & stability
Recommended models
Independent retest evidence
Sep 2, 2026

The requested model is recorded, but the generation receipt did not expose a verifiable underlying model ID.
Keep exploring

A prompt for creating animation-ready pixel art sprites. It tells the model to produce a 16-frame grid of combat actions such as punches and kicks from a character image reference.
Prompt
このキャラクターの戦闘モーションのスプライトシートを作って。{argument name="サイズ" default="128px"}の簡略化された{argument name="画風" default="pixelart"}、4x4=16コマ、背景は透過。{argument name="アクション内容" default="構え4/パンチ4/キック4/被弾4
A three-layer reference sheet — nine body angles, nine expressions, fourteen fine-grained identity anchors — built to feed an image model a locked character identity, paired with an exhaustive negative-prompt list to stop identity drift.
Prompt
Based on the attached original character image, create a "Character Identity Fixed Reference Chart": landscape orientation 16:10, light gray-white background, professional visual reference board layout. The primary goal is for all panels to

A GPT Image 2 prompt that transforms each uploaded photo into a split-screen design, with the original image on top and a vintage watercolor illustration below.
Prompt
Turn each photo I upload into a separate premium design poster. Do not combine multiple images; output each photo separately. Use an overall 3:4 vertical composition divided into two regions with a strict 1:1 height ratio, each occupying 50
Same model
A Scene Paired in Photography and Minimalist Ink WashAI Image · GPT Image 2.5 · 2026-10-13
老屋微缩模型提示词AI Image · GPT Image 2.5 · 2026-10-11
Portrait of a Woman in Black Lace Under a Blue SkyAI Image · GPT Image 2 · 2026-10-10
极简涂鸦构图提示词AI Image · GPT Image 2 · 2026-10-09
Split Poster with Original Photo and Subject Crossing a Color FieldAI Image · GPT Image 2.5 · 2026-10-09
Black-and-White Portrait of a Woman with Half Her Face in ShadowAI Image · GPT Image 2 · 2026-10-09Each detail page keeps the original result, the prompt, and retest evidence in one reading path.