Skip to content
Video & Audio
Skill

/curated-multi-view

把同一主体整理成一致的多面设定。 用户要求多视图设定时使用。

BOOST
From plugin
nomi
57393 skills1 MCP
Install
$ npx -y skills add aqm857886159/nomi --skill curated-multi-view --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/curated-multi-view

Context preview

The summary Claude sees to decide when to auto-load this skill.

把同一主体整理成一致的多面设定。 用户要求多视图设定时使用。

SKILL.md

curated-multi-view.SKILL.md
name: curated-multi-view
description: 把同一主体整理成一致的多面设定。 用户要求多视图设定时使用。
license: Apache-2.0
metadata:
  nomi:
    version: 1.0.0
    label: 多视图设定
    selectable-in-workbench: true
    tools: []
    required-providers:
      - image
    library:
      kind: skill
      title:
        zh-CN: 多视图设定
        en: Multiple views
      summary:
        zh-CN: 把同一主体整理成一致的多面设定。
        en: Generate consistent views of the same subject from a reference image.
      appliesTo:
        - image
      group:
        zh-CN: 角色与场景
        en: Character and scene
      slots: []
      source:
        url: https://github.com/PicoTrex/Awesome-Nano-Banana-images/blob/2558bf0bb825be150c5d1aeab918cd90004882d3/README.md
        revision: 2558bf0bb825be150c5d1aeab918cd90004882d3
        author: https://x.com/Error_HTTP_404/status/1960405116701303294
        changes: >-
          Nomi adds Chinese task labels, reference slots and review criteria; fixed subjects are parameterized where
          noted.
        evidence:
          - https://x.com/Error_HTTP_404/status/1960405116701303294
          - https://x.com/Error_HTTP_404
      preview:
        path: assets/preview.jpg
        type: image
        provenance: upstream-output
        sourceUrl: https://raw.githubusercontent.com/PicoTrex/Awesome-Nano-Banana-images/main/images/case23/output.jpg

多视图设定

把同一主体整理成一致的多面设定。

确认已有参考素材与目标尺寸。缺少决定人物身份、产品外观或故事内容的输入时,先让用户补齐。按下面的原仓配方组织生成描述;把显式槽位替换成用户内容,不虚构品牌。

配方

在白色背景上生成前、后、左、右、上、下视图。均匀分布。一致的主体。等距透视等效

验收

核对主体身份、数量、结构、光影和镜头连续性。原仓媒体是配方来源证据,不是 Nomi 本次实测结果。多视角图不保证真实三维几何;生成式修复可能重新绘制细节。完成前展示产物,指出可见偏差。

来源和更改说明见 frontmatter;保留随包许可证。

Read more
Ships withnomi

Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP — storyboard, references, generation, editable first cut on a real timeline. Local-first: projects, prompts, and keys stay on your machine. No account, no telemetry.

Get the whole plugin
Stats
573
Stars
131
Forks
Active
Maintenance
TypeScript
Language
AGPL-3.0
License
18h ago
Last commit
5mo ago
Created
5h ago
Added

Repo: aqm857886159/nomi

Other skills on nomi.