mcpField
V
video-t2i

video-t2i

github.com/t0ughCreative & media12038 installsUpdated 23w ago
Repository

About video-t2i

video-t2i is a videoclaw skill for generating images from text prompts. It runs independently of project context and allows an image provider and model to be specified.

Key features

  1. 01Generates images from text prompts
  2. 02Runs without project context
  3. 03Allows provider selection
  4. 04Allows model selection

Use cases

  1. 01Generating character images from descriptions
  2. 02Creating images with a chosen provider
  3. 03Testing an image generation model

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/t0ugh/videoclaw --skill video-t2i

After installing, type/video-t2iin Claude Code to confirm it loaded.

Details

From the project README

video-t2i - 文生图

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 Wan2.6
  • gemini - Google Gemini
  • mock - 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

Comments

Markdown supported