← 返回
内容创作 中文

Video Generation (t2v & i2v)

AI Video generation toolkit — generate videos from text prompts or input images using multiple AI models (Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Ima...
AI视频生成工具包——基于Veo 3.1、Veo 3、Seedance 1.5 Pro、Wan 2.5、Grok Ima等多模型,支持文本或图像输入生成视频。
gentleyo
内容创作 clawhub v1.0.1 1 版本 99885.7 Key: 无需
★ 0
Stars
📥 874
下载
💾 85
安装
1
版本
#latest

概述

Video Generation Toolkit

Generate AI videos from text prompts or images using 40+ models including Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Imagine Video, etc.

Prerequisites

IMPORTANT: This skill requires the inference.sh CLI to be installed and available in your PATH. The CLI provides access to 40+ AI video generation models.

To install inference.sh:

npm install -g @inference.sh/cli

Or visit https://inference.sh for installation instructions.

Constraints

  • Always output absolute paths for generated files so the web UI can render them.
  • Web UI auto-renders local paths: output .mp4/.mov paths as plain text (NOT in code blocks or markdown links), so the UI can render a video player inline. Same for .jpg/.png → inline image.
  • Uploaded files arrive as [附件: /absolute/path/to/file] in the message.
  • For image-to-video, images must be accessible via public URL. Provide your own API key for ImgBB/SM.MS, or ensure images are already publicly accessible.

Tool 1 — text_to_video.py (Text to Video)

Generate video from text prompt.

python nanobot/skills/VideoGeneration/scripts/text_to_video.py [options]
FlagDescription
-------------------
--prompt TEXT(required) Video description in English
--model NAMEModel name, default veo-3.1
--duration NVideo duration in seconds, default 5
--width NVideo width, default 1280
--height NVideo height, default 720
--fps NFrames per second, default 24
--save-dir DIROutput dir, default ./outputs/videos
--timeout NRequest timeout in seconds, default 600
--dry-runPrint request and exit

Available models:

  • veo-3.1 - Google Veo 3.1 (recommended)
  • veo-3 - Google Veo 3
  • seedance-1.5-pro - Seedance 1.5 Pro
  • wan-2.5 - Wan 2.5
  • grok-imagine-video - Grok Imagine Video
  • omnihuman - OmniHuman

Output JSON example:

{
  "ok": true,
  "downloaded_files": ["D:/project/.../outputs/videos/video_20260315_1.mp4"]
}

Tool 2 — image_to_video.py (Image to Video)

Generate video from input image.

python nanobot/skills/VideoGeneration/scripts/image_to_video.py [options]
FlagDescription
-------------------
--image PATH(required) Input image path
--prompt TEXT(required) Video description in English
--model NAMEModel name, default veo-3.1
--duration NVideo duration in seconds, default 5
--save-dir DIROutput dir, default ./outputs/videos
--upload-serviceImage upload service (smms/imgbb), default imgbb
--api-tokenAPI token for image upload (REQUIRED for ImgBB, optional for SM.MS)
--timeout NRequest timeout in seconds, default 1000
--dry-runPrint request and exit

Process:

  1. Upload local image to cloud storage (SM.MS or ImgBB) OR use a publicly accessible image URL
  2. Generate video using the image URL
  3. Download and save locally

IMPORTANT: For ImgBB, you must provide an API token via --api-token or set IMGBB_API_KEY environment variable. Get your free API key at https://api.imgbb.com/

Output JSON example:

{
  "ok": true,
  "downloaded_files": ["D:/project/.../outputs/videos/video_20260315_1.mp4"]
}

版本历史

共 1 个版本

  • v1.0.1 当前
    2026-03-19 09:47 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

content-creation

Humanizer

biostartechnology
消除AI写作痕迹,使文本更自然真实。基于维基百科"AI写作特征"指南,识别并修正夸张象征、宣传用语、肤浅-ing分析、模糊归因、破折号滥用、三项排比、AI词汇、负面平行结构及冗长连接词等模式。
★ 860 📥 199,997

personal companion

gentleyo
智能伴侣技能 — 通过多轮对话为用户创建个性化虚拟伴侣角色,提供情感陪伴。适用于用户感到孤独、想聊天、需要陪伴、情绪低落或明确提到伴侣、陪聊、虚拟角色、角色扮演陪伴等关键词时。
★ 0 📥 405
content-creation

AdMapix

fly0pants
广告情报与应用数据分析助手,支持搜索广告素材、分析应用排名、下载量、收入及市场洞察,用于广告素材和竞品分析。
★ 295 📥 136,518