ascii-video

Convert video and audio into colored ASCII MP4/GIF outputs.

1|Updated Apr 21, 2026
One-click install
npx skills add https://github.com/ChangZhou-xj/zxj_skill --skill ascii-video-changzhou-xj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ascii-video
Source: https://github.com/ChangZhou-xj/zxj_skill/tree/main/creative/ascii-video
Command: npx skills add https://github.com/ChangZhou-xj/zxj_skill --skill ascii-video-changzhou-xj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

ASCII Video unit enables turning standard media inputs into colored ASCII video outputs (MP4/GIF) with per-frame color, multi-grid rendering, and audio-reactive visuals for cinematic terminal-style artworks.

Core Features & Use Cases

  • Multi-grid ASCII rendering across density presets (xs to xxl) to create depth and texture in each frame.
  • Supports modes: video-to-ASCII, audio-reactive visuals, generative ASCII art, and lyric/TTS overlays.
  • A full pipeline: adaptive tonemap, ShaderChain post-processing, FeedbackBuffer-based temporal effects, and references for architecture/effects/shaders to guide implementation.

Quick Start

Provide a video input and run the pipeline to generate an ASCII MP4/GIF output using a selected mode and quality profile.

Frequently Asked Questions about ascii-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a video into colored ASCII art?

To convert video to colored ASCII art, this Skill processes per-frame features through a Python-based pipeline with adaptive tonemap and multi-grid rendering, outputting colored ASCII MP4 or GIF files.

Can I generate audio-reactive ASCII visuals from a music track?

Yes, you can generate audio-reactive ASCII visuals using the dedicated audio-reactive mode, which coordinates audio input with the ShaderChain post-processing pipeline to produce dynamic terminal-style animations.

Does this video-to-ASCII pipeline support lyric and TTS overlays?

Yes, the video-to-ASCII pipeline supports lyric and TTS overlays, allowing you to synchronize text and speech directly into generative ASCII art frames during the clip-based render workflow.

What is multi-grid ASCII rendering and when do I need it for video processing?

Multi-grid ASCII rendering applies density presets from xs to xxl to create depth and texture in each frame, needed when producing cinematic terminal-style visuals with varying structural detail.

Do I need Python to run the ASCII video generation pipeline?

Yes, you need a Python environment to run the ASCII video generation pipeline, which coordinates per-frame feature extraction, ShaderChain post-processing, and the clip-based render workflow.

What are the limitations of using ShaderChain post-processing for ASCII video?

The ShaderChain post-processing and FeedbackBuffer temporal effects target artistic terminal-style outputs, meaning limitations arise when attempting photorealistic reproduction rather than stylized ASCII recreation.