6.2.0 — Release Notes
Changelog for Agnes Video Generator: new features, improvements and bug fixes for every release.
New model launch: Agnes Video 2.5 Flash — free for a limited time
Agnes Video Generator now fully supports the newest generation of video models: Video 2.5 Flash is free for a limited time (720P), with text-to-video, first/last-frame and image-reference modes, 4–12s durations and six aspect ratios — switch to it right inside the app.
What's New
Features & Improvements
- Agnes Video 2.5 & 2.5 Flash support — the newest video generation models are now fully supported. Video 2.5 Flash is free for a limited time (720P,
$0/sec), while Video 2.5 adds paid quality tiers (720P / 960P / 2K). Both expose new generation modes (text / first-last-frame / image reference), 4–12s durations, and aspect-ratio-based output (21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16). - Video model selector with capability comparison — video model selection is now open in the settings panel and on the Simple Video form. When choosing a model you see a detailed comparison of all three models (price, generation modes, durations, resolution, negative-prompt support, reference-image limits and reference-video support) before committing.
- Model-aware form options (Simple Video) — the form adapts to the selected model: generation modes, duration presets (v2.0: 5–20s; 2.5-series: 4–12s), resolution control (pixel presets vs. aspect ratio + quality tier with the actual output pixels shown, e.g.
9:16 · 720×1280), and negative-prompt visibility are all driven by the chosen model's capabilities.
Bug Fixes
- 2.5-series keyframe square-output fix — the 2.5 / 2.5-Flash
keyframemode returned a fixed 704×704 square regardless ofaspect_ratio, stretching portrait/landscape footage (people appeared wider). Multi-image submissions now automatically fall back to thereferencemode so output follows the requested ratio (e.g. 768×1152 input → 704×960 portrait). - Regression checker F3 resolution validation — the regression suite now validates 2.5-series outputs by aspect ratio instead of absolute pixels, so 720P tier outputs (704×960) are no longer misreported as failures.
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