4.6.0 — Poetry Video Task Type + MultiScene Pipeline Refactor
Poetry Video Task Type + MultiScene Pipeline Refactor
What's New
Features & Improvements
- Poetry Video task type — new
POST /api/tasks/poetry: the LLM splits a poem into scenes (original line | visual description format), each line is rendered by TTS narration, scenes are generated as t2v clips, and subtitles are time-aligned to the narration and concatenated. - Poetry scene config aligned with creative video — per-scene duration model and duration-extraction mode; scene count / watermark / narration speed options.
- Two-phase poetry generation — scenes are submitted in a batch and awaited in parallel for faster completion.
Refactoring & Optimizations
- MultiScenePipeline base class — creative / manuscript / anchor / poetry long-video pipelines now share one template-method base (
build_scenes → build_reference_images → generate_videos → audio+subtitle → composite), eliminating duplicated per-pipeline logic. - Poetry generation reuses the base generator — video generation is hoisted to
MultiScenePipeline._generate_videos.
Bug Fixes
- Per-scene TTS audio truncation in poetry videos (only the first half audible).
- Resume reused a stale
final_clip.mp4without an audio track. - Poetry progress step indicator not displayed.
switchTaskTypemissing a closing brace, which disabled all page JS.
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