Agnes Video Generator

2.2 — i2i End Frames + Global Rate Limiter + Stability Enhancements

i2i End Frames + Global Rate Limiter + Stability Enhancements

MinorReleased on June 19, 2026View on GitHub ↗

What's New

Features & Improvements

  • i2i end frame pipeline — image model unified to agnes-image-2.1-flash; i2i array API; character reference images normalized in size; character appearance persisted across scenes via programmatic prompt injection; multi-image guided end frames create a visual chain linking scenes; keyframes fallback branch kept in sync.
  • Global rate limiter — single shared token bucket (16 req/min) across Chat + Image + Video APIs keeps free-tier API usage within limits and prevents 429 storms.
  • i18n improvements — duration parsing and localized defaults for user requirements / visual styles across all 7 languages.

Refactoring & Optimizations

  • Unified API retry — exponential backoff for 429 / 5xx across all three Agnes API modules.
  • Code-review Batch 2 fixes (P1–P13) — video concatenation made async (no blocking), active_pipelines concurrency race fixed, chat_json robustness, prompt-injection protection, resource-leak cleanup, URL cache expiry, temp filename uniqueness.
  • Regression runner enhancements — 404-polling detection, --quick manifest mode, auto-resume, resolution matching.

Bug Fixes

  • Resume crash fixes — _upload_image_to_host method name, _run_pipeline task_id undefined, load() creating empty directories.
  • Custom end frame not applied; manuscript step-key alignment.
  • Paused scopes: subtitle silent degradation on failure, SilentTTS return-code handling.
  • Concatenator AttributeError on the video-concatenation failure path.

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