Image2Studio
Prompts

gpt-image-2

{ "instruction" "Using REFERENCE_0 As The Base Design

{ "instruction": "Using REFERENCE_0 as the base design, generate a comprehensive anime character reference sheet (settei) on a clean off-white background. Keep the core character design i...

{ "instruction": "Using REFERENCE_0 as the base design, generate a comprehensive anime character reference sheet (settei) on a clean off-white background. Keep the core character design i...
{ "instruction": "Using REFERENCE_0 as the base design, generate a comprehensive anime character reference sheet (settei) on a clean off-white background. Keep the core character design i...
Prompt

{ "instruction": "Using REFERENCE_0 as the base design, generate a comprehensive anime character reference sheet (settei) on a clean off-white background. Keep the core character design intact but extract and present her in various standard reference formats.", "header": { "character_name": "{argument name=\"character name\" default=\"クロエ・アストラル\"}", "subtitle": "Chloe Astral", "document_title": "キャラクター設定資料", "quote": "{argument name=\"character quote\" default=\"「時の歯車は、今日も私の魔法と踊ってくれる」\"}" }, "layout": { "left_column": { "section_title": "全身イラスト", "description": "The original complex character art from REFERENCE_0, accompanied by vertical descriptive text." }, "top_right": { "section_title": "三面図", "count": 3, "description": "Full-body standing turnaround views (FRONT, SIDE, BACK) of the character, removing the original gear background." }, "far_right": { "section_title": "表情集", "count": 4, "labels": ["通常", "微笑み", "驚き", "考え中"], "description": "Square headshot panels showing different facial expressions." }, "middle_right": { "section_title": "武器・アイテム", "count": 3, "items": ["Scythe from reference", "New starry spellbook addition", "Bird from reference with spread wings"], "description": "Isolated props with accompanying text descriptions." }, "bottom_row": [ { "section_title": "プロフィール", "description": "Data table with 7 stat rows and a short biography paragraph." }, { "section_title": "カラーパレット", "count": 10, "description": "Circular color swatches divided into 5 main colors and 5 accent colors." }, { "section_title": "ディテール", "count": 3, "labels": ["帽子デザイン", "衣装ディテール(柄)", "靴デザイン"], "description": "Close-up rectangular detail crops of the hat, outfit pattern, and shoes." }, { "section_title": "設定メモ", "count": 4, "description": "Text box containing 4 bullet points of design notes." } ] } }

Prompt structure
  • Modelgpt-image-2
  • Use caseavatar
  • Styleminimal, anime, editorial
  • Aspect ratioFlexible
Best used for
  • Use caseavatar
  • Styleminimal, anime, editorial
  • Recommended specs1:1, 4:5, 16:9, or 9:16
  • ModelGPT Image 2
How to customize

Use this { "instruction" "Using REFERENCE_0 As The Base Design prompt as a base. Replace the subject, product details, environment, lighting, brand colors, and output ratio while keeping the avatar intent and minimal, anime, editorial direction stable.

Editable variables
  • SubjectReplace the product, person, scene, interface, or object being generated.
  • Use caseKeep or rewrite the destination as avatar, ad creative, cover image, poster, or ecommerce hero.
  • FrameChoose 1:1, 4:5, 16:9, or 9:16 based on the final placement.
  • Brand cuesAdd colors, materials, props, text-safe space, and the platform where the image will be used.
Recommended specs

Choose the frame for the destination first, then use 1K, 2K, or 4K based on output quality needs. Product images and posters usually benefit from higher resolution.

Pre-generation checklist
  • CheckSubject, lighting, composition, and frame are specific enough to review.
  • CheckText-safe space is included when the image will carry a headline or ad copy.
  • CheckResolution, credit cost, and final destination are checked before generation.
Why this prompt works

{ "instruction" "Using REFERENCE_0 As The Base Design works because it starts from the image job, then controls subject, composition, lighting, style, and frame. It is best for avatar while keeping the minimal, anime, editorial direction stable.

Common questions
  • Can I use it directly?Yes. Replace the subject, brand cues, and frame, then generate in Image2Studio.
  • Which ratio should I use?Choose 1:1, 4:5, 16:9, or 9:16 based on the destination.