5.7.2 — Release Notes

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

PatchReleased on August 13, 2026View on GitHub

What's New

Bug Fixes

  • Intermediate artifacts restored in the progress panel — after the v5.7.0 frontend re-architecture, intermediate artifacts (story, reference images, scene videos, subtitles, etc.) were no longer shown while a task runs. The progress panel now loads artifacts on task start, refreshes them as each step completes during polling, and shows the final output when finished. Viewing a task from the task list also opens the progress panel with its artifacts and result video.
  • GitHub Code Scanning security fixes — sensitive data no longer logged at startup (get_api_keys_source); key IDs are now derived with HMAC-SHA256 (blake2b keyed mode) instead of plain SHA-256; task-directory deletion/existence checks operate only on realpath-resolved paths (path-injection hardening).
  • Release pipeline fixes — the npm README preparation step no longer fails when the format string starts with -, and the release workflow now tolerates missing release-notes docs with a warning instead of aborting.

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

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 updated2026-08-21

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.

Clone the GitHub repo and launch in 2 minutes