6.4.8 — Release Notes
Changelog for Agnes Video Generator: new features, improvements and bug fixes for every release.
What's New
Features & Improvements
- Readable diagnosis for local network and DNS failures. Long-running creative, manuscript, anchor and poetry jobs that died right at the download step used to surface only
RetryError[<Future ... raised ConnectionError>]. Such failures are now translated into a message that names the domain that could not be resolved (or the host that refused the connection) and lists what to check: a resolver that can reach the output domain, VPN or proxy DNS hijacking, and hosts-file or security-software blocking. - Retry guidance that matches the failure type. A failure that retrying cannot fix is now labelled as such, so the panel tells you to repair the local network first instead of pushing another retry. Resuming after the fix still reuses the already generated video, so no extra generation quota is spent.
- Accurate step attribution in diagnostic reports. The failed step reported by the feedback panel and the pre-filled GitHub Issue is read live from the running task. Previously it came from a snapshot taken when the page opened, so clicking Retry on the same page could report
scene_configwhile the job had actually failed invideo_gen.
Bug Fixes
- Terminal progress events are persisted immediately, so the final failure or completion message no longer disappears behind the write-throttling used for high-frequency updates.
- Failures in simple image generation report the same readable network diagnosis instead of a raw exception string.
- No action is required after upgrading.
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.
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 GitHubLast 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.
Clone the GitHub repo and launch in 2 minutes