Back to Details

muapi-multi-angle-reshoot

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Multi-Angle Reshoot

多角度重拍

Re-render a subject or scene from multiple dramatic camera angles, such as fish-eye, bird's-eye, low-angle, and macro, while maintaining consistent identity and detail.
Estimated credits: ~150 per run.
从鱼眼、鸟瞰、低角度、微距等多种戏剧性拍摄角度重新渲染主体或场景，同时保持主体特征和细节的一致性。
预估消耗点数： 每次运行约150点。

Inputs

输入参数

NameTypeRequiredDefaultDescription
subject_description
textyes—Description of the subject or scene (e.g. "a professional woman in a black suit holding a laptop").
reference_image
image_urlno—Optional reference image to maintain consistency across angles.
名称类型是否必填默认值描述
subject_description
文本是—主体或场景的描述（例如：“一位身穿黑色西装、手持笔记本电脑的职业女性”）。
reference_image
图片URL否—可选参考图片，用于在不同角度间保持一致性。

Steps

步骤

Phase A — Subject Establishment

阶段A — 主体确立

If 
{{reference_image}}
is not provided, submit the plan with ONE step to create the base subject:
  1. Subject Generation — 
    muapi image generate
    (model=
    nano-banana-pro
    ):
    • Prompt: 
      A high-quality, professional photograph of {{subject_description}}. Clean studio lighting, sharp focus, realistic textures, cinematic quality.
    • Aspect ratio: 3:4 or 1:1
Present the base image to the user for approval.
如果未提供
{{reference_image}}
，提交包含以下单个步骤的方案以创建基础主体：
  1. 主体生成 — 
    muapi image generate
    （模型=
    nano-banana-pro
    ）：
    • 提示词：
      A high-quality, professional photograph of {{subject_description}}. Clean studio lighting, sharp focus, realistic textures, cinematic quality.
    • 宽高比：3:4或1:1
将基础图片提交给用户确认。

Phase B — Multi-Angle Reshoot

阶段B — 多角度重拍

Once the subject is established, submit the plan using 
muapi image edit
(model=
nano-banana-2-edit
) to generate the requested angles. Use the approved image from Phase A as the reference for ALL steps.
  1. Bird's Eye View
    • Reference: Base Image
    • Prompt: 
      A dramatic bird's eye view (from directly above) of the same subject. High-angle perspective, wide shot, looking down. Maintain exact clothing, face, and setting consistency.
  2. Fish Eye Lens
    • Reference: Base Image
    • Prompt: 
      A high-distortion fish-eye lens photograph of the same subject. Ultra-wide angle, curved edges, dramatic perspective, immersive feel. Maintain exact clothing and face consistency.
  3. Low Angle (Hero Shot)
    • Reference: Base Image
    • Prompt: 
      A low-angle "hero shot" looking up at the subject. Makes the subject appear powerful and dominant. Maintain exact clothing and face consistency.
  4. Dutch Angle
    • Reference: Base Image
    • Prompt: 
      A stylized Dutch angle (tilted horizon) photograph of the same subject. Cinematic, slightly uneasy or dramatic vibe. Maintain exact clothing and face consistency.
  5. Macro Close-up
    • Reference: Base Image
    • Prompt: 
      An extreme macro close-up focused on a specific detail of the subject (e.g., eyes, texture of the suit, or a feature of the laptop). Shallow depth of field, incredible detail. Maintain exact colors and textures.
  6. Worm's Eye View
    • Reference: Base Image
    • Prompt: 
      A worm's eye view from ground level looking straight up at the subject. Dramatic vertical perspective. Maintain exact clothing and face consistency.
After generating the variations, present the multi-angle gallery to the user. You can also offer to generate specific individual angles based on their feedback.
主体确立后，使用
muapi image edit
（模型=
nano-banana-2-edit
）提交方案以生成所需角度。使用阶段A中用户确认的图片作为所有步骤的参考。
  1. 鸟瞰视角
    • 参考图：基础图片
    • 提示词：
      A dramatic bird's eye view (from directly above) of the same subject. High-angle perspective, wide shot, looking down. Maintain exact clothing, face, and setting consistency.
  2. 鱼眼镜头
    • 参考图：基础图片
    • 提示词：
      A high-distortion fish-eye lens photograph of the same subject. Ultra-wide angle, curved edges, dramatic perspective, immersive feel. Maintain exact clothing and face consistency.
  3. 低角度（英雄镜头）
    • 参考图：基础图片
    • 提示词：
      A low-angle "hero shot" looking up at the subject. Makes the subject appear powerful and dominant. Maintain exact clothing and face consistency.
  4. 倾斜角度
    • 参考图：基础图片
    • 提示词：
      A stylized Dutch angle (tilted horizon) photograph of the same subject. Cinematic, slightly uneasy or dramatic vibe. Maintain exact clothing and face consistency.
  5. 微距特写
    • 参考图：基础图片
    • 提示词：
      An extreme macro close-up focused on a specific detail of the subject (e.g., eyes, texture of the suit, or a feature of the laptop). Shallow depth of field, incredible detail. Maintain exact colors and textures.
  6. 虫眼视角
    • 参考图：基础图片
    • 提示词：
      A worm's eye view from ground level looking straight up at the subject. Dramatic vertical perspective. Maintain exact clothing and face consistency.
生成所有变体后，向用户展示多角度图片集。你也可以根据用户反馈提供特定单个角度的生成服务。

Trigger Keywords

触发关键词

multi angle
, 
photo reshoot
, 
change camera angle
, 
fish eye view
, 
birds eye view
, 
low angle shot
, 
macro photography
, 
camera perspective
multi angle
, 
photo reshoot
, 
change camera angle
, 
fish eye view
, 
birds eye view
, 
low angle shot
, 
macro photography
, 
camera perspective

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.
  • 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。如果未设置
    MUAPI_API_KEY
    ，请先使用
    muapi auth configure
    进行配置。
  • 对于尚未设置CLI别名的模型ID，可通过原始端点回退：
    curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'
    ，并使用
    muapi predict wait <request_id>
    进行轮询。
  • 在发出每个调用前，将
    {{input_name}}
    占位符替换为用户的实际输入。