Agnes Video Generator

4.5.0 — Intermediate Artifacts Viewer + Error Collector + Pure Polling

Intermediate Artifacts Viewer + Error Collector + Pure Polling

MinorReleased on July 7, 2026View on GitHub ↗

What's New

Features & Improvements

  • Intermediate-artifacts viewer — the task detail panel shows every step's intermediate outputs (prompts / images / videos), filterable by mode (creative / manuscript / anchor), with cascading deletion that clears the corresponding state fields, resets downstream steps, and cleans up files.
  • Model API error collector — new core/api/error_collector.py records complete failure info (prompt, error type, HTTP status code, response body, retry count) for text/image/video API calls on every failed attempt (including mid-retry), stored under the active workspace's error_logs/. API-level error details (e.g. content_policy_violation) are now extracted instead of a generic status code.

Refactoring & Optimizations

  • Pure-polling progress — WebSocket removed; progress is read via GET /api/tasks/{id} with frontend polling (default 30s interval), reducing complexity and making new/resumed task progress display faster and more stable.
  • Step-state rendering fix — resumed/reopened tasks no longer flash gray on completed steps; colors derive directly from the state field.
  • Dynamic image-generation timeout — 60s first attempt, extending to 120s / 180s on retries to avoid premature failures on slow networks.

Bug Fixes

  • Artifact deletion now allowed in the stopped state (was 409).
  • Artifact list refreshes live while a task is running.
  • Intermediate videos play correctly — <video> tag type="video/mp4" / playsinline / size constraints completed.
  • Play-button clicks fixed — bypassed the backdrop-filter stacking-context block of the glass card.

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