Back to Details

muapi-chibi-collage-effect

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Chibi Collage Effect

Chibi拼贴效果

Turn a real lifestyle photo into a polished "chibi clone sticker diary" image — the original person stays photorealistic, surrounded by 5–8 kawaii chibi mini-clones, scrapbook doodles, and handwritten-style captions that match the scene.
Estimated credits: ~120 per run.
将真实生活照片转化为精致的“Chibi克隆贴纸日记”图片——保留人物的写实风格，周围环绕5–8个kawaii Chibi迷你克隆形象、剪贴画涂鸦以及与场景匹配的手写风格文字说明。
预估消耗点数： 每次运行约120点。

Inputs

输入参数

NameTypeRequiredDefaultDescription
person_image
image_urlyes—A clear lifestyle photo of the person. Setting, outfit, mood, and activity are read from this image and drive the chibi poses and captions.
名称类型是否必填默认值描述
person_image
image_url是—清晰的人物生活照片。场景、穿搭、情绪和活动将从该图片中读取，并指导Chibi的姿势和文字说明。

Steps

步骤

Phase A — Chibi Collage Generation

A阶段——Chibi拼贴生成

If 
{{person_image}}
is not provided, ask the user to upload a lifestyle photo (café, outdoor, cozy at home, travel, etc.). The scene context is what makes the chibi clones feel native to the moment, so a generic studio headshot will give weaker results than a real lifestyle shot.
Once the photo is available, submit the plan with ONE step to generate the chibi collage:
  1. Chibi Collage Generation — 
    muapi image edit
    (model=
    gpt-image-2-image-to-image
    ):
    • Reference Image: 
      {{person_image}}
    • Image size: 
      2160x3840
      (9:16 portrait) — high-resolution social-media-ready output
    • Background: 
      auto
    • Output format: 
      png
    • Quality: 
      auto
    • Moderation: 
      low
    • Prompt: 
      Create a high-quality "chibi clone sticker diary photo" based on the uploaded real-life image. Preserve the original person's identity, face, hairstyle, hair color, outfit, body proportions, pose, lighting, and background. Do not alter facial features or turn the subject into a full illustration—maintain a realistic photo look.
Analyze the uploaded image carefully: identify the setting, mood, activity, clothing style, and overall vibe of the scene. Use this analysis to determine the theme of the chibi stickers, poses, emotions, and text phrases — everything should feel native to the actual moment captured in the photo.
Add 5–8 chibi mini clones of the same person around the subject, designed in a consistent kawaii sticker style (big head, small body, large expressive eyes, clean digital finish). Each clone must clearly resemble the real person (same hair, outfit, colors).
Design each chibi with different actions and emotions that are directly relevant to what the person is doing or feeling in the photo — inferred naturally from the scene (e.g. if they're at a café: sipping coffee, reading, daydreaming, chatting; if outdoors: exploring, laughing, taking photos; if cozy at home: cuddling, reading, relaxing). Ensure all poses are unique and contextually matched to the image.
Render each chibi as a sticker with white outlines, soft shadows, and a slightly floating effect. Arrange them around the subject and edges without covering the face or main body.
Add light hand-drawn doodles (hearts, sparkles, arrows, motion lines, circles, stars) in white with subtle pink accents, keeping a clean scrapbook diary feel. Doodle style should complement the mood of the scene.
Include 5–8 short handwritten-style phrases that match the mood and context of the uploaded photo — cute, expressive, and scene-appropriate. Use mostly white text with slight pink highlights and small decorative marks.
Composition: keep the real person as the central focus, surrounded by chibi stickers and doodles. The result should feel like a polished, playful, high-resolution social media lifestyle diary image — clean, balanced, and visually rich without clutter.
Present the generated chibi collage to the user. Suggest variations they can try: different source photos (travel, café, cozy-at-home), or asking to bias the captions toward a specific tone (cute, sassy, journal-style).
如果未提供
{{person_image}}
，请要求用户上传一张生活照片（咖啡馆、户外、居家温馨场景、旅行等）。场景背景能让Chibi克隆形象更贴合当下情境，因此通用的工作室大头照效果会远不如真实生活照。
获取照片后，提交包含一个步骤的计划来生成Chibi拼贴：
  1. Chibi拼贴生成 —— 
    muapi image edit
    (model=
    gpt-image-2-image-to-image
    ):
    • 参考图片：
      {{person_image}}
    • 图片尺寸：
      2160x3840
      (9:16竖屏) —— 适合社交媒体的高分辨率输出
    • 背景：
      auto
    • 输出格式：
      png
    • 画质：
      auto
    • 内容审核：
      low
    • 提示词： 
      Create a high-quality "chibi clone sticker diary photo" based on the uploaded real-life image. Preserve the original person's identity, face, hairstyle, hair color, outfit, body proportions, pose, lighting, and background. Do not alter facial features or turn the subject into a full illustration—maintain a realistic photo look.
Analyze the uploaded image carefully: identify the setting, mood, activity, clothing style, and overall vibe of the scene. Use this analysis to determine the theme of the chibi stickers, poses, emotions, and text phrases — everything should feel native to the actual moment captured in the photo.
Add 5–8 chibi mini clones of the same person around the subject, designed in a consistent kawaii sticker style (big head, small body, large expressive eyes, clean digital finish). Each clone must clearly resemble the real person (same hair, outfit, colors).
Design each chibi with different actions and emotions that are directly relevant to what the person is doing or feeling in the photo — inferred naturally from the scene (e.g. if they're at a café: sipping coffee, reading, daydreaming, chatting; if outdoors: exploring, laughing, taking photos; if cozy at home: cuddling, reading, relaxing). Ensure all poses are unique and contextually matched to the image.
Render each chibi as a sticker with white outlines, soft shadows, and a slightly floating effect. Arrange them around the subject and edges without covering the face or main body.
Add light hand-drawn doodles (hearts, sparkles, arrows, motion lines, circles, stars) in white with subtle pink accents, keeping a clean scrapbook diary feel. Doodle style should complement the mood of the scene.
Include 5–8 short handwritten-style phrases that match the mood and context of the uploaded photo — cute, expressive, and scene-appropriate. Use mostly white text with slight pink highlights and small decorative marks.
Composition: keep the real person as the central focus, surrounded by chibi stickers and doodles. The result should feel like a polished, playful, high-resolution social media lifestyle diary image — clean, balanced, and visually rich without clutter.
将生成的Chibi拼贴展示给用户。建议他们尝试不同的变体：不同的源照片（旅行、咖啡馆、居家温馨场景），或者要求将文字说明偏向特定风格（可爱、俏皮、日记风）。

Trigger Keywords

触发关键词

chibi collage
, 
chibi sticker diary
, 
mini me stickers
, 
kawaii clone collage
, 
sticker diary photo
, 
scrapbook chibi
chibi collage
, 
chibi sticker diary
, 
mini me stickers
, 
kawaii clone collage
, 
sticker diary photo
, 
scrapbook chibi

Notes for the Executing Agent

执行Agent注意事项

  • This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call 
    muapi
    CLI commands. Use 
    muapi auth configure
    first if 
    MUAPI_API_KEY
    is unset.
  • For model IDs without a CLI alias yet, fall back to the raw endpoint via 
    curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'
    and poll with 
    muapi predict wait <request_id>
    .
  • Substitute 
    {{input_name}}
    placeholders with the user's actual inputs before issuing each call.
  • Source schema reference: 
    gpt-image-v2-edit
    from the EachLabs workflow JSON maps to 
    gpt-image-2-image-to-image
    in the muapi catalog.
  • The output is intentionally 9:16 (2160×3840) so it's ready for IG Stories / Reels / TikTok / YT Shorts without re-cropping.
  • 本流程由LLM编排：阅读每个阶段，向用户收集缺失的输入，然后调用
    muapi
    CLI命令。如果
    MUAPI_API_KEY
    未设置，请先使用
    muapi auth configure
    。
  • 对于尚未有CLI别名的模型ID，回退到原始端点，通过
    curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'
    调用，并使用
    muapi predict wait <request_id>
    轮询。
  • 在发出每个调用前，将
    {{input_name}}
    占位符替换为用户的实际输入。
  • 源架构参考：EachLabs工作流JSON中的
    gpt-image-v2-edit
    对应muapi目录中的
    gpt-image-2-image-to-image
    。
  • 输出尺寸特意设置为9:16（2160×3840），无需裁剪即可直接用于IG Stories / Reels / TikTok / YT Shorts。