What makes 动态漫画制作 notable?

1.1K downloads. Trust evidence available

How should 动态漫画制作 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

动态漫画制作

从剧本、统一角色图到 Edge TTS 与防抖竖屏成片 Skill: 动态漫画制作 Owner: tobewin Summary: 从剧本、统一角色图到 Edge TTS 与防抖竖屏成片 Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-26T03:06:00.241Z | auto Initial release of the make-motion-comic skill. - Create low-cost motion-comic videos from story/script using AI-generated keyframes, multi-character Chinese TTS, captions, and FFmpeg assembly. - Ensures character identity consistency, professional voice quality, smooth motion

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

0.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 0.1.0release · observed Aug 26, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s174rz3f0862tcfw7pzfh5w8kn83hv2z:make-motion-comic

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-tobewin-make-motion-comic/snapshot"

Documentation

CLAWHUB

29,025 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: make-motion-comic
description: Create or revise low-cost motion-comic videos from a story or script using consistent AI-generated keyframes, multi-character Chinese Edge TTS, captions, synthesized or licensed audio, and FFmpeg assembly. Use for 动态漫画、漫剧、条漫视频、animated manga/comic, narrated image-story shorts, vertical story videos, or when Codex must turn generated still images into a polished video without a generative video model; also use to diagnose or fix character drift, robotic TTS, subtitle timing, micro-jitter, shaky zoompan motion, audio balance, covers, and reusable episode production assets.
---

# Make Motion Comic

Produce a complete motion-comic episode from a script while keeping image identity, voice quality, motion smoothness, and source assets independently editable.

## Required route

1. Use the built-in Image Generator through the available `imagegen` skill for character sheets, keyframes, image corrections, and covers. Follow that skill's reference-image and save-path rules.
2. Use Edge TTS for Chinese production voice by default. Do not use macOS `say` for a final deliverable unless the user explicitly chooses its offline quality tradeoff.
3. Use FFmpeg for deterministic motion, audio mixing, captions, encoding, and inspection. A user may explicitly choose another video framework.
4. Run `scripts/preflight.sh` before producing media. Report missing required dependencies before continuing.

Edge TTS uses an unofficial client for Microsoft's online speech endpoint. It is free in normal use but needs network access and has no service guarantee. Retry transient failures; do not silently substitute a worse voice.

## Default production brief

Use these defaults when the user says “开始”“直接做” or otherwise authorizes an autonomous first pass:

- Format: 9:16, 1080×1920, 30 fps, H.264/AAC.
- Length: 45–90 seconds.
- Visuals: 6–12 keyframes; use a new image when story state changes, not at arbitrary time intervals.
- Structure: hook in 0–3 seconds, rule or dilemma, escalation, emotional reversal, final serial cliffhanger.
- Captions: render in post; never ask the image model to typeset dialogue.
- Audio: multi-character Neural voices, light ambience/SFX, no unverified copyrighted BGM.
- Review: inspect the character sheet, raw keyframe contact sheet, and final-video snapshots.

Read [references/story-and-shots.md](references/story-and-shots.md) before writing a new episode. Read [references/image-consistency.md](references/image-consistency.md) before generating images.

## Workflow

### 1. Establish the production package

Create a project-local working folder and a user-facing output folder. Preserve:

- script and shot table;
- character/world visual bible;
- one prompt per keyframe;
- raw keyframes;
- TTS manifest and voice-only mix;
- subtitle file and timed timeline;
- final mix, cover, contact sheet, and final video.

Keep temporary render fragments outside the user-facing output folder.

### 2. Write for motion comics

README.md

# Make Motion Comic

用 AI 图片、Edge TTS 与 FFmpeg 制作低成本、高一致性、可维护的动态漫画。

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
[![Codex Skill](https://img.shields.io/badge/Codex-Skill-111827)](SKILL.md)
[![FFmpeg](https://img.shields.io/badge/FFmpeg-Required-007808)](https://ffmpeg.org/)
[![Edge TTS](https://img.shields.io/badge/Edge%20TTS-Neural%20Voice-2563EB)](https://github.com/rany2/edge-tts)

`make-motion-comic` 是一个面向 Codex 的动态漫画制作 Skill。它把“剧本 → 角色视觉基准 → 逐镜图片 → 多角色配音 → 防抖镜头 → 字幕与混音 → 成片质检”固化为可复用的生产流程，不依赖生成式视频模型。

它适合：

- 动态漫画、漫剧、条漫视频；
- 竖屏悬疑、情感、科普和连续短剧；
- 用少量关键帧制作有声音、有节奏的故事视频；
- 修复角色漂移、机器人配音、字幕错位和 `zoompan` 微抖动。

> 当前版本重点支持普通话、9:16 竖屏和 FFmpeg 工作流。

![动态漫画效果预览](docs/demo-cover.jpg)

## 为什么做这个 Skill

图片生成模型已经能够产出质量很高的漫画关键帧，但将图片直接拼成视频通常会出现四类问题：

1. 人物在镜头之间变脸、换衣服或改变年龄；
2. 系统 TTS 缺乏情绪，破坏画面建立的氛围；
3. 低分辨率 `zoompan` 产生一像素跳动和细线闪烁；
4. 配音、字幕、镜头和片尾各自计时，返工后全部错位。

本项目为这些问题提供明确的生产规则和可执行脚本：

- 始终使用原始角色视觉基准作为身份锚点；
- 默认使用多角色中文 Neural Edge TTS；
- 根据真实语音文件重建时间轴；
- 在 2 倍工作画布上进行缓动，再用 Lanczos 缩回 1080p；
- 对编码、黑帧、响度、字幕冲突和片尾衔接进行验收。

## 工作流

```mermaid
flowchart LR
    A["剧本与钩子"] --> B["分镜与台词"]
    B --> C["角色 / 世界视觉基准"]
    C --> D["逐镜生成关键帧"]
    B --> E["Edge TTS 多角色配音"]
    E --> F["实测语音时间轴"]
    D --> G["防抖镜头渲染"]
    F --> G
    G --> H["字幕、音效与混音"]
    H --> I["封面与最终导出"]
    I --> J["画面 / 音频 / 编码质检"]
```

默认成片规格：

- 1080×1920，9:16；
- 30 fps，H.264 / AAC；
- 45–90 秒；
- 6–12 张关键帧；
- 约 −16 LUFS，True Peak 不高于 −1.5 dBTP。

## 安装

### 1. 克隆到长期维护目录

```bash
git clone https://github.com/ToBeWin/make-motion-comic.git
cd make-motion-comic
```

### 2. 让 Codex 发现 Skill

推荐使用符号链接，维护源码时安装版本会同步更新：

```bash
mkdir -p "${CODEX_HOME:-$HOME/.codex}/skills"
ln -s "$(pwd)" "${CODEX_HOME:-$HOME/.codex}/skills/make-motion-comic"
```

如果目标位置已经存在，请先确认它是否是需要保留的安装版本，不要直接覆盖。

### 3. 安装依赖

需要：

- Codex，以及可用的内置 Image Generator；
- Python 3.9+；
- FFmpeg / FFprobe；
- Zsh；
- [`edge-tts`](https://github.com/rany2/edge-tts)。

安装 Edge TTS：

```bash
python3 -m pip install edge-tts
```

运行环境检查：

```bash
./scripts/preflight.sh
```

返回以下结果即可开始制作：

```json
{"ok":true,"warnings":[]}
```

## 快速使用

在 Codex 中：

```text
使用 $make-motion-comic，把这个故事制作成一集 60 秒的竖屏动态漫画：
一名女孩每天都会收到已经去世的哥哥发来的天气预报。
```

Skill 会依次处理：

1. 剧情结构、钩子和反转；
2. 角色视觉基准与分镜提示词；
3. 逐镜图片生成与一致性检查；
4. Edge TTS 多角色配音；
5. 实测时间轴、字幕与镜头时长；
6. 防抖推拉、平移和静止镜头；
7. 环境声、音效、混音、封面与成片；
8. 编码、黑帧、响度和视觉检查。

## 核心原则

### 角色一致性

- 先生成包含正面、侧面、全身、表情和服装的视觉基准图；
- 每个镜头都回到原始基准图获取身份；
- 上一镜头只能作为姿势或构图参考；
- 禁止单纯采用 A → B → C 的连续参考链；
- 对人物、服装、手部、人数、关键道具和意外文字逐项验收。

详细说明见 [`references/image-consistency.md`](references/image-consistency.md)。

### 配音与时间轴

- 正式成片默认不使用 macOS `say`；
- 每句台词单独生成，角色长期保持固定音色；
- Edge TTS 网络错误采用有界重试，不静默降级；
- 修改台词、音色或语速后自动失效旧缓存；
- 最终时长以 `ffprobe` 测量结果为准。

详细说明见 [`references/audio-and-tts.md`](references/audio-and-tts.md)。

### 防抖运动

慢速 `zoompan` 每帧可能移动不足一个像素。整数取整会形成“停顿—跳一像素”的微抖动，而漫画细线会进一步放大这种现象。

本项目使用：

- 2592×4608 源工作画布；
- 2160×3840 运动输出；
- 余弦缓入缓出；
- 30 fps；
- Lanczos 缩放至 1080×1920；
- 单镜头只使用一个主要运动参数；
- 情绪反转镜头优先静止。

详细说明见 [`references/motion-a

_meta.json

{
  "ownerId": "kn75z6gevjsyrznm7dg2ez6sen82h8sz",
  "slug": "make-motion-comic",
  "version": "0.1.0",
  "publishedAt": 1787713560241
}

references/audio-and-tts.md

# Audio and Edge TTS

## Default voice route

Use Edge TTS for zero-cost online Mandarin Neural speech when its service is available. It is an unofficial client and requires internet access. Run:

```bash
edge-tts --list-voices | rg '^zh-CN'
```

Do not silently fall back to macOS `say`; it is suitable for drafts and accessibility, not emotional drama.

If Edge TTS is unavailable after bounded retries, report the failure and offer a quality-preserving alternative such as an authenticated Neural TTS provider or a local expressive model.

## Cast voices

Keep voice identity stable across episodes. Recommended starting points:

| Role | Voice | Treatment |
|---|---|---|
| Warm narrator | `zh-CN-XiaoxiaoNeural` | rate −6% to +2%, pitch −3 to 0 Hz |
| Adult woman | `zh-CN-XiaoyiNeural` | rate −12% to 0%, pitch −5 to 0 Hz |
| Controlled man | `zh-CN-YunyangNeural` | rate −14% to −4%, pitch −10 to −4 Hz |
| Younger urgent man | `zh-CN-YunxiNeural` | rate 0% to +8%, pitch −4 to 0 Hz |
| Child | `zh-CN-XiaoyiNeural` | rate −12% to −4%, pitch +8 to +16 Hz |

Treat these as starting points. Generate a short audition when a new recurring cast is created.

## Acting through text

- Use full stops for conviction.
- Use a comma for a short breath.
- Use one ellipsis only for meaningful hesitation.
- Avoid repeated ellipses; Edge TTS may create long dead air.
- Split long exposition into separate line assets.
- Give urgent lines a faster rate instead of using exclamation marks everywhere.

## Manifest

Use `assets/templates/tts-script.json` and save one audio file per line. This enables:

- individual voice replacement;
- exact subtitle timing;
- per-line gain and pacing;
- resumable online synthesis.

Run:

```bash
python3 scripts/synthesize_edge_tts.py \
--manifest tts-script.json \
--out audio/lines \
--speed 1.00
```

Use a small, pitch-preserving `--speed` adjustment only after hearing the generated pacing. Prefer 0.96–1.10. Do not accelerate poor acting into acceptable duration.

## Mix

- Normalize and lightly compress each voice asset.
- Keep ambience 12–20 dB beneath voice.
- Place SFX relative to measured line/shot times.
- Use sidechain ducking or keyframed bed volume under speech.
- Measure the finished program, not only the voice bus.

Target approximately −16 LUFS integrated and ≤−1.5 dBTP.

references/image-consistency.md

# Image consistency

## Build the visual bible

Create one reference image containing:

- neutral full-body front, side, and back views;
- face closeups with neutral and high-value expressions;
- signature clothes and accessories;
- palette and material details;
- a small environment/world inset.

Use distinct silhouette and color cues. Avoid two leads with nearly identical hair, coat, or face shape.

## Reference hierarchy

For every shot:

1. Use the visual bible as the identity reference.
2. Use an approved environment frame when location continuity matters.
3. Use the previous shot only as a pose/composition reference.

Never rely only on the immediately previous generated frame. Small deviations compound across a chain.

Label input roles in the image prompt:

```text
Input images:
- Image 1: identity and wardrobe source of truth.
- Image 2: environment and lighting reference only.
- Image 3: pose continuity reference only.
```

## Prompt skeleton

```text
Use case: illustration-story
Asset type: vertical 9:16 motion-comic keyframe
Primary request: <single story moment>
Input images: <labeled roles>
Subject: <named characters with locked visual traits>
Scene/backdrop: <location and continuity details>
Style/medium: <series art direction>
Composition/framing: <shot size, focal subject, caption-safe area>
Lighting/mood: <series palette plus local change>
Constraints: preserve exact identities, wardrobe, proportions, and signature props
Avoid: text, captions, speech bubbles, logos, watermarks, duplicate people, extra fingers
```

## Review

Inspect at full size. Reject or correct:

- changed hairstyle, age, facial proportions, or clothing;
- missing signature accessory;
- duplicate or fused people;
- wrong hand count;
- changed bottle, weapon, photo, or other story-critical prop;
- accidental letters;
- focal face placed beneath planned captions.

When a shot fails, return to the visual bible and correct one issue at a time.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.