Verified project record

ATH-MaaS/Pixelle-Video

Automates the short video creation pipeline from a single text prompt, handling scriptwriting, AI media generation, voiceover synthesis, and final video composition. It is designed for creators who want an automated video generation workflow without manual editing.

Project overview

It bundles scriptwriting, AI media generation, TTS, and video synthesis into a single web-based workflow, starting from a one-sentence input.

Project type: Workflow · Image & Vision · Video
Use cases: Documents & Office · Image Processing · Video Creation · Audio & Speech
Deployment: Refer to project documentation
License: Apache-2.0

Best for

Creators and general users who want to generate short videos automatically from a single text prompt without coding or manual editing.

Key capabilities

Generates AI scripts, creates AI illustrations/videos, synthesizes voiceovers, adds BGM, and composes the final video from a single text topic.
Generates intelligent explanatory scripts based on the input topic.
Supports various TTS solutions including Edge-TTS and Index-TTS, and supports voice cloning from reference audio.
Generates matching AI images and videos for sentences using models like WAN 2.1 or ComfyUI workflows.
Generates talking digital human videos.
Uploads reference videos and images to perform motion transfer.
Supports ComfyUI and RunningHub workflows to flexibly replace image, video, TTS, and VLM capabilities.
Allows users to upload their own photos and videos, using AI to intelligently analyze and generate scripts.

Limitations and risks

Requires manual installation of ffmpeg for non-Windows bundle users.
Cloud-based LLM and image generation services may incur higher fees.

Getting started

Download the Windows integration package, extract it, and run start.bat. The browser automatically opens the web interface. You must configure LLM and image generation services in System Configuration before the system can generate videos.

Alternatives and comparisons

A free, open-source, self-hostable AI studio for generating images, video, audio, and more using 200+ models without content filters or subscription fees.
A generative AI movie studio integrated into the Blender Video Editor enabling end-to-end production from script to screen and back.
A modular AI image and video generation web UI that supports a swarm of GPUs to generate images concurrently.

Project comparisons

Evidence and sources

README
README
README
README
README

Source updated at: 2026-07-16T18:06:01Z

Open original GitHub project