# Pixelle-Video

> Pixelle-Video (Apache-2.0) turns a topic into a narrated short video: LLM script, an AI image or clip per sentence via ComfyUI workflows (local or RunningHub cloud) or direct image/video APIs, Edge-TTS or Index-TTS voice, music and templates. Extra pipelines cover a digital-human avatar, image-to-video and motion transfer. The README states a zero-cost setup with Ollama plus local ComfyUI, which needs your own GPU; otherwise it uses paid APIs. Windows all-in-one package; uv install on macOS/Linux. Hardware needs are not documented.

- Repository: https://github.com/ATH-MaaS/Pixelle-Video
- Official docs: https://github.com/ATH-MaaS/Pixelle-Video/blob/main/README_EN.md
- Checked: 2026-10-16

## What it replaces
- InVideo AI: Script or prompt to video, Faceless short videos from a topic, AI voiceover, AI-generated images and video clips (partial). Generates the visuals with AI per sentence instead of stock footage; free only with local Ollama and ComfyUI on your own GPU.
- HeyGen: AI avatar (talking presenter) videos (partial). Has a Digital Human pipeline (added January 2026); not tested against HeyGen avatars.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, local web UI on localhost:8501 | https://github.com/ATH-MaaS/Pixelle-Video/blob/main/README_EN.md#-quick-start | 2026-10-15 |
| Code licence | Confirmed | Apache-2.0 | https://github.com/ATH-MaaS/Pixelle-Video/blob/main/LICENSE | 2026-10-15 |
| Model weights licence | Partial | No single bundled model licence: users select Ollama, ComfyUI/RunningHub workflows or direct model APIs. Each selected weight or provider keeps its own licence and service terms; Apache-2.0 covers the application code | https://github.com/ATH-MaaS/Pixelle-Video/blob/main/README_EN.md | 2026-10-16 |
| Commercial use | Partial | Apache-2.0 code; check the licence of each image/video model or API you use | https://github.com/ATH-MaaS/Pixelle-Video/blob/main/LICENSE | 2026-10-15 |
| Paid services needed? | Partial | Not required with Ollama + local ComfyUI (needs a capable GPU); otherwise paid LLM, RunningHub or image/video APIs | https://github.com/ATH-MaaS/Pixelle-Video/blob/main/README_EN.md | 2026-10-15 |
| Hardware | Unknown | Not documented; the README recommends the free local route only if you have a local GPU | https://github.com/ATH-MaaS/Pixelle-Video/blob/main/README_EN.md | 2026-10-15 |
| Operating systems | Confirmed | Windows (all-in-one package), macOS and Linux (from source) | https://github.com/ATH-MaaS/Pixelle-Video/blob/main/README_EN.md#-quick-start | 2026-10-15 |
| Setup effort | Confirmed | Easy on Windows (all-in-one package); uv + ffmpeg on macOS/Linux; local ComfyUI is extra work | https://github.com/ATH-MaaS/Pixelle-Video/blob/main/README_EN.md#-quick-start | 2026-10-15 |

GitHub: 29093 stars, 4231 forks, last push 2026-06-14, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/pixelle-video). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.