text-to-video
Skill33 starsChanged 5 months agoMITView on GitHub
使用 meitu-cli 从纯文字描述生成动态视频,覆盖高画质默认模式与高动态快速模式。当用户提到文生视频、文字生成视频、帮我生成一段视频、做一个视频、广告视频、产品宣传片、短视频时触发。
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- limboinf/myskillstheir own version, first seen Dec 23, 2025
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- limboinf/myskills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository55 other files it gives its agents.
- meitu-toolsSkill
- SKILL.mdSkill
- audio-music-generateSkill
- audio-song-generateSkill
- image-background-replaceSkill
- image-cutoutSkill
- image-denoise-enhanceSkill
- image-editSkill
- image-element-removeSkill
- image-face-swapSkill
- image-grid-splitSkill
- image-id-photo-generateSkill
- image-lowlight-enhanceSkill
- image-outfit-swapSkill
- image-portrait-generateSkill
- image-poster-generateSkill
- image-searchSkill
- image-style-transferSkill
- image-superres-enhanceSkill
- image-text-replaceSkill
- image-to-videoSkill
- image-transformSkill
- meitu-beautySkill
- meitu-carouselSkill
- meitu-cutoutSkill
- meitu-game-2d-assetsSkill
- meitu-id-photoSkill
- meitu-image-adaptSkill
- meitu-image-fixSkill
- meitu-posterSkill
- meitu-product-swapSkill
- meitu-product-viewSkill
- meitu-stickersSkill
- meitu-upscaleSkill
- meitu-video-danceSkill
- meitu-visual-meSkill
- text-code-editSkill
- text-codeSkill
- text-generateSkill
- text-to-imageSkill
- video-audio-addSkill
- video-canvas-expandSkill
- video-content-replaceSkill
- video-denoise-enhanceSkill
- video-effect-applySkill
- video-element-removeSkill
- video-framerate-enhanceSkill
- video-logo-addSkill
- video-lowlight-enhanceSkill
- video-motion-transferSkill
- video-multimodal-generateSkill
- video-quality-enhanceSkill
- video-resolution-upscaleSkill
- video-stitchSkill
- video-to-gifSkill
The file
Files
Text To Video(文生视频)
Overview
纯文字驱动生成动态视频,涵盖 2 类场景:
- 高画质默认模式:创意视频、广告素材、文案可视化、概念演示;4–15s,比例 adaptive/16:9/4:3/1:1/3:4/9:16/21:9,480p/720p,音频默认 on。
- 高动态快速模式:追求动态效果 / 画面生动、或需 3s 短时长;3–15s,仅 16:9/1:1/9:16,720p,音频默认 off,动态效果更强。
不处理:图片驱动生成视频、音频驱动生成、视频编辑、视频加特效/改风格。
API Mapping
| 场景 | 后端 API |
| 高画质默认模式 | video_toffee_t2v_v20 |
| 高动态快速模式 | video_bonbon_txt2vid_v30 |
model 映射:
auto(默认)/ 不传 → 按路由规则决策toffee→video_toffee_t2v_v20bonbon→video_bonbon_txt2vid_v30- 互相降级:一方失败切另一方重试
Dependencies
- meitu-cli:
>=2.0.6 - 凭证:CONFIG AKSK →
meitu tools update;EXEC AKSK → 跑命令(见根CONFIG.md) - 环境变量:
MEITU_OPENAPI_TOOL_TASK_MODE=command
Core Workflow
Preflight → Execute → DeliverPreflight
meitu --version≥ 2.0.6meitu auth verify --json- 确认 registry 含
text-to-video - 解析 output_dir:
openclaw.yaml→./output/;else →~/.openclaw/workspace/visual/output/text-to-video/ - 时长钳位:用户要 <3s → 钳位 3s 并告知
Execute
触发信号 / 路由规则
决策顺序:
- 时长 <3s → 钳位 3s
- 动态优先 / 3s 短时长 命中 → 候选
video_bonbon_txt2vid_v30 - 若比例为 4:3/3:4/21:9/adaptive → 比例优先,切回
video_toffee_t2v_v20 - 无特殊要求 →
video_toffee_t2v_v20(默认)
| 场景 | 判定关键词 | 路由 |
| 动态优先 | 动态、生动 | video_bonbon_txt2vid_v30 |
| 3s 短时长 | 3 秒 | video_bonbon_txt2vid_v30 |
| 默认 / 无特殊要求 | 通用 | video_toffee_t2v_v20 |
| 特殊比例(4:3/3:4/21:9/adaptive) | -- | 强制 video_toffee_t2v_v20(比例优先) |
| 要 480p | -- | video_toffee_t2v_v20(bonbon 不支持 480p) |
参数定义
通用参数:
| 参数 | 类型 | 必填 | 范围 | 默认值 | 说明 |
prompt | STRING | 是 | -- | -- | 视频内容描述。缺失 → 追问 |
video_duration | NUMBER | 是 | 3–15 | 按 API 不同 | toffee: 4–15,默认 10;bonbon: 3–15,默认 5 |
sound | STRING / BOOL | 是 | on/off 或 true/false | 按 API 不同 | toffee: BOOL generate_audio,默认 true;bonbon: STRING on/off,默认 off |
aspect_ratio | STRING | 是 | adaptive / 16:9 / 1:1 / 9:16 / 4:3 / 3:4 / 21:9 | 按 API 不同 | toffee 全比例支持,默认 adaptive;bonbon 仅 16:9/1:1/9:16,默认 16:9 |
resolution | STRING | 否 | 480p / 720p | 720p | 仅 toffee 支持;bonbon 固定 720p |
各 API 参数映射:
video_toffee_t2v_v20(高画质默认)
| 统一参数 | API 参数 | 映射规则 |
prompt | prompt | 直传 |
video_duration | video_duration | clamp(4, 15),默认 10 |
sound | generate_audio | on→true / off→false;默认 true |
aspect_ratio | ratio | 全比例直传,默认 adaptive |
resolution | resolution | 480p/720p,默认 720p |
video_bonbon_txt2vid_v30(高动态快速)
| 统一参数 | API 参数 | 映射规则 |
prompt | prompt | 直传 |
video_duration | video_duration | clamp(3, 15),默认 5 |
sound | sound | on/off 直传,默认 off |
aspect_ratio | aspect_ratio | 支持 16:9/1:1/9:16;其他比例切 toffee |
工具调用
默认高画质:
meitu text-to-video \
--skill_name skill_text-to-video \
--prompt "{video_description}" \
--video_duration 10 \
--aspect_ratio adaptive \
--resolution 720p \
--sound true \
--json --download-dir {output_dir}高动态快速(3s):
meitu text-to-video \
--skill_name skill_text-to-video \
--prompt "{dynamic_scene}" \
--model bonbon \
--video_duration 3 \
--aspect_ratio 16:9 \
--sound off \
--json --download-dir {output_dir}错误降级
| 场景 | 处理方式 |
prompt 缺失 | 提示"请描述你想生成的视频内容" |
| 时长 <3s | 钳位 3s,告知"文生视频最短支持 3 秒" |
| 时长 <4s + 默认模式 | toffee 最短 4s → 降级 video_bonbon_txt2vid_v30 |
| 特殊比例 + 快速模式 | bonbon 仅 16:9/1:1/9:16 → 切 video_toffee_t2v_v20,告知"当前比例不支持动态模式,已切换默认模式" |
| 未指定时长 + 默认模式 | 默认 10s |
| 未指定时长 + 快速模式 | 默认 5s |
video_toffee_t2v_v20 失败 | 切 video_bonbon_txt2vid_v30 重试 |
video_bonbon_txt2vid_v30 失败 | 切 video_toffee_t2v_v20 重试 → 仍失败返回错误 |
| 超时 >600s | 降低时长 / 分辨率重试 1 次 → 仍失败返回错误 |
| 内容合规拦截 | 直接返回合规提示,不重试、不降级 |
冲突规则:
- 动态 + 特殊比例 → 比例优先,走
video_toffee_t2v_v20 - 3s 时长 + 默认模式 → 时长优先,走
video_bonbon_txt2vid_v30 - 要 480p → 走
video_toffee_t2v_v20(bonbon 不支持)
Deliver
解析 --json:
ok: true→downloaded_files[0].saved_path为本地视频ok: false→ 输出code+hint
落盘:mv {file} {output_dir}/{YYYY-MM-DD}_{descriptive-name}.mp4
Output
- 格式: MP4
- 命名:
{YYYY-MM-DD}_{descriptive-name}.mp4 - 位置: 项目 →
./output/;一次性 →~/.openclaw/workspace/visual/output/text-to-video/
基线 Task ID
见根目录 references/task-id-baseline.md 中 text-to-video 条目。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

