Agnes Video Generator

7.2.1 — Release Notes

Changelog for Agnes Video Generator: new features, improvements and bug fixes for every release.

PatchReleased on October 21, 2026View on GitHub ↗

What's New

Features & Improvements

  • Cache-proof local install. Virtualenv, configuration, workspace and logs live under one data root (~/.agnes-video by default). Clearing the npm cache or upgrading the package no longer forces a full Python dependency re-download, and generated videos no longer sit inside a package folder.
  • Dependencies installed once. pip runs again only when requirements.txt actually changed (sha256 fingerprint), so later starts skip the network and work offline.
  • Script and agent friendly startup. --detach starts the service in the background and exits when it answers; --json prints {ok, ready, pid, base, home, venv, workspace, log}; --print-paths reports where each piece lives without starting anything.
  • Relocatable default workspace. AGNES_WORKING_DIR decides where the default workspace points, so media can be kept on another disk or folder.
  • `has_key` on `GET /api/config`. Tooling can check whether an API key is configured without parsing the masked prefix.

Bug Fixes

  • Failed asset imports no longer expose internal error details to the caller.
  • Watermark fallback paths and ffmpeg overlay failures are now logged with stack traces, so a missing font or a broken overlay can be diagnosed from the log instead of an unexplained watermark.
  • Compatibility: no API breaks. Existing .env files, workspaces configured in the Web UI and keys supplied through AGNES_API_KEY keep working; environment keys still use the single global domain.

About Agnes Video Generator

A completely free, open-source AI video generator: turn text into multi-scene AI videos with narration and subtitles.

  • Free and open source — no payment, no high-end GPU required
  • Text-to-video, image-to-video, digital anchor and image generation
  • Powered by free Agnes AI models, rendered entirely in the cloud
  • Runs via Web UI, Docker or npm, and supports self-hosting

Related Pages

Release Notes

Changelog for Agnes Video Generator: new features, improvements and bug fixes for every release.

Try Online Demo | Agnes Video

Enter a prompt and generate AI videos and images instantly

Text to Video API — Free AI Video Generation API, No GPU | Agnes Video

Programmatically access Agnes AI's free video models. Text-to-video, image-to-video, and narration APIs. Developer-friendly, zero-cost, no high-end GPU required.

Why you can trust this

Written by a practicing developer and cross-checked against authoritative primary sources such as arXiv papers, vendor technical reports, and the Stanford AI Index.

S

SandGrid@lcy362

Author of Agnes Video Generator · Full-stack Developer

Independent developer and author of Agnes Video Generator, an open-source (MIT) AI video generation tool built on Agnes AI's free video models. Has helped 1,000+ creators produce AI videos at zero cost. Focused on making video generation models accessible and production-ready; content is based on hands-on practice and primary research.

View on GitHub

Last updated：2026-08-21

Ready to Start Creating?

"Making world-class AI belong to everyone." — Bruce Yang. It's completely free, no credit card, and you won't need a high-end GPU. Your first AI video starts at zero cost. Want to use Agnes AI's free video models? This is the easiest way in.

Try Online DemoGet Started Free

Clone the GitHub repo and launch in 2 minutes