Overview
Generate images from text prompts. Independent command that does not require project context.
Usage
Note: If this is your first time using it, make sure videoclaw is installed:
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
videoclaw t2i -p "description" -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 Wan2.6
- `gemini` - Google Gemini
- `mock` - For testing
## Examples
Claude Code: videoclaw t2i -p "a cute Minion character, front view" -o character.png