video-t2i - 文生图
SkillMediaUse when user needs to generate images from text prompts. Independent text-to-image command for creating single images outside of video creation workflow.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the video-t2i - 文生图 skill
What this skill tells your AI
The instructions your AI receives, as published by t0ugh/videoclaw in skills/video-t2i/SKILL.md and read by ahel’s review.
Overview
Generate images from text prompts. Independent command that does not require project context.
Usage
注意：如果是首次使用，确保已安装 videoclaw：
uvx videoclaw --help
# Generate image
videoclaw t2i -p "九宫格角色图：正面、侧面、背面..." -o output.png
# Specify provider
videoclaw t2i -p "描述" -o output.png --provider volcengine
# Specify model
videoclaw t2i -p "描述" -o output.png --provider gemini --model gemini-3-pro-image-preview
Parameters
--prompt, -p: Text prompt (required)--output, -o: Output file path (required)--provider: Model provider (optional, default: volcengine)--model: Model name (optional)
Supported Providers
volcengine- Volcano Engine Seedream (default)dashscope- Alibaba Wan2.6gemini- Google Geminimock- For testing
Examples
Claude Code: videoclaw t2i -p "一个可爱的小黄人角色，正面视图" -o character.png
Signals
- GitHub stars
- 116
- Forks
- 20
- Last commit
- May 2026
Advanced
- Item type
- skill
- Key
video-t2i- Source
- github.com/t0ugh/videoclaw