# ATH-MaaS/Pixelle-Video

🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine

Repository: https://github.com/ATH-MaaS/Pixelle-Video
Canonical: https://ross.abutalabs.com/products/pixelle-video
Homepage: https://aidc-ai.github.io/Pixelle-Video/zh
Language: Python
License: Apache-2.0
License Family: permissive
Topics: aigc, comfyui, image-generation, tts, video-generation
Last push: 2026-06-14T12:40:58+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 87, release rhythm 68, longevity 21
- inputs: {"age_days": 299, "days_push": 80, "days_rel": 218, "gap_med": 3, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 27344, forks 3975 (observed 2026-08-28T04:11:47.672768+00:00)

## What it is
Pixelle-Video is an AI-powered fully automated short video engine that turns a single topic into a finished video. It automatically writes the script, generates AI images and video clips, synthesizes voiceover via TTS, adds background music, and composites the final video through a modular pipeline built on ComfyUI/RunningHub workflows or direct model APIs.

## Use cases
- generate short videos from a text topic automatically
- create faceless youtube or tiktok videos with ai narration
- automatically write video scripts with an llm
- generate ai images and video clips for each scene
- add text-to-speech voiceover and background music to videos
- create digital human talking-head videos
- batch produce short videos without editing experience

## When to choose
- you want one-topic-to-finished-video automation with zero editing skills
- you want to swap in different LLM, image, video, and TTS providers via ComfyUI workflows or direct APIs
- you need batch video creation with a web UI and multiple templates and aspect ratios

## When to avoid
- you need fine-grained manual control over every edit in a traditional video editor
- you cannot access external AI model APIs or GPU-backed services like ComfyUI/RunningHub
- you need long-form video production rather than short-form clips

## Facets
- artifact type: application
- maturity: active
- function: video-processing, tts, image-processing, llm-inference, stable-diffusion, workflow-automation, web-framework
- domain: artificial-intelligence, media, large-language-models
- platform: python, cross-platform, windows
- tags: aigc, short-video-generation, comfyui, text-to-video, ai-narration, digital-human, faceless-video, video, automation, docker, web-server

## Member repositories
- ATH-MaaS/Pixelle-Video (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:47.672768+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:54:33.062922+00:00, confidence not recorded.
  - readme: https://github.com/ATH-MaaS/Pixelle-Video (fetched 2026-08-28T04:11:47.672768+00:00, sha 65177586a7db)
- Data as of 2026-08-30T08:39:29.467469+00:00.