# ziplab/ATAS

> A framework for multi-shot video generation built on a persistent world state: a screenplay becomes shot requests, and each generated shot is registered and validated before updating the shared scene and event memory.

- Magnitude: 5.1 out of 10 — Early signal
- Stars: 152 total · +54 stars measured 2026-10-15, 04:36–06:44 UTC, ≈ 170 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: Python · License: MIT · Created: 2026-10-12 · Last push: 2026-10-15
- GitHub: https://github.com/ziplab/ATAS · Homepage: https://lhmd.top/atas · Page: https://gitnova.dev/en/r/ziplab/ATAS

## Useful for

- Generate a multi-shot video from a plain-text screenplay with a consistent world.
- Re-film an already generated scene from a new camera angle or viewpoint.
- Run the pipeline on a GPU-less client while offloading geometry to a separate service.

## Why it’s here

- Star-counter measurements on 2026-10-15 (UTC), 04:36–06:44: 98 → 152 stars (+54). This is the change over that interval.
- Estimated end-of-day forecast: about +171 stars, using observed gains and the previous day.
- The repository is 3 days old and already has 152 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #105.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 0
- Issues and pull requests: 0
- Watchers: 1
- Average over the last week: 82 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 24

## Stars per day, last 4 days (oldest → newest, today is partial)

2026-10-12 … 2026-10-15: 0, 1, 155, 54

## Spotted in now

- Top new repositories this week: #105

## More in this category

1. **Arekejoker/qwen21-nsfw-pose-skill** — 7.7 · Early signal · Generative media · Python · +236 stars measured 2026-10-15, 00:20–06:43 UTC, ≈ 643 by evening
   A set of recipes and scripts for local NSFW image generation and pose control with Qwen-Image 2.1 via ComfyUI, including an NSFW LoRA and a library of 136 3D poses.
   Full card: https://gitnova.dev/en/r/Arekejoker/qwen21-nsfw-pose-skill.md
2. **debpalash/VoiceStudio** — 6.3 · Breakout · Generative media · Python · +863 stars measured 2026-10-15, 00:20–06:43 UTC, ≈ 2,988 by evening
   A fully local, open-source ElevenLabs alternative for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation on your own hardware, with no account or API key. Supports 16 TTS and 11 ASR engines, a…
   Full card: https://gitnova.dev/en/r/debpalash/VoiceStudio.md
3. **storytold/artcraft** — 5.7 · Peaking · Generative media · Rust · +358 stars measured 2026-10-15, 00:20–06:43 UTC, ≈ 1,537 by evening
   ArtCraft is a desktop IDE for AI image and video creation: compose in 2D, stage scenes in 3D, and choose models for precise, repeatable results.
   Full card: https://gitnova.dev/en/r/storytold/artcraft.md
4. **threerocks/sweety-handdraw-video** — 5.3 · Early signal · Generative media · JavaScript · +25 stars measured 2026-10-15, 00:21–06:44 UTC, ≈ 91 by evening
   An agent skill that turns a topic, article, or story into a narrated hand-drawn explainer video: the agent writes the script and generates illustrations, while local Python/Pillow/FFmpeg scripts draw strokes, text, and sync the voiceover.
   Full card: https://gitnova.dev/en/r/threerocks/sweety-handdraw-video.md
5. **heygen-com/hyperframes** — 5.0 · Steady · Generative media · TypeScript · +223 stars measured 2026-10-15, 00:21–06:44 UTC, ≈ 825 by evening
   Framework for turning HTML, CSS, media and seekable animations into deterministic MP4 videos. Runs locally via CLI or from AI coding agents through a set of skills.
   Full card: https://gitnova.dev/en/r/heygen-com/hyperframes.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-15 06:57 UTC, updated every 30 minutes.