# tin2tin/Pallaidium

PALLAIDIUM — a generative AI movie studio, seamlessly integrated into the Blender Video Editor (VSE), enabling end-to-end production from script to screen and back.

Repository: https://github.com/tin2tin/Pallaidium
Canonical: https://ross.abutalabs.com/products/pallaidium
Homepage: https://tin2tin.github.io/Pallaidium/
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: text2video, blender, text2audio, text2image, text2speech, diffusion, ai, generative, aicinema, flux, movie, studio, ltx, wan, chatterbox, qwen, turbo, z-image
Last push: 2026-08-22T09:38:28+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 90
- inputs: {"age_days": 1262, "days_push": 11, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1520, forks 154 (observed 2026-08-28T04:04:57.663691+00:00)

## What it is
Pallaidium is a free, open-source generative AI movie studio implemented as a Blender add-on integrated into the Video Sequence Editor (VSE). It enables end-to-end AI film production, converting text, images, and video into images, video, speech, music, and audio, and supports reverse workflows like extracting screenplays from generated footage.

## Use cases
- generate videos from text prompts inside Blender
- convert a screenplay into a storyboarded animatic with AI images and voices
- add AI-generated speech and music to a Blender video edit
- prototype a film with generative AI before shooting real footage
- animate still images into video clips on a timeline
- extract captions and reconstruct a screenplay from an edited video
- batch-generate AI media across a Blender timeline

## When to choose
- you already use Blender's VSE and want generative AI in your editing workflow
- you want a free, local, end-to-end AI film production pipeline from script to screen
- you need omnimodal conversion (text/image/video to image/video/audio/speech/music) in one tool
- you want to prototype screenplays as audio-visual animatics before committing to real production

## When to avoid
- you need a standalone AI video generator without Blender
- you have no compatible GPU or cannot run diffusion models locally
- you need production-grade, non-AI video editing only
- you require commercial licensing beyond GPL-3.0

## Facets
- artifact type: plugin
- maturity: active
- function: image-processing, video-processing, audio-processing, speech-recognition, tts, machine-learning, llm-inference, stable-diffusion, workflow-automation
- domain: artificial-intelligence, media, image-processing, developer-tools
- platform: windows, python
- tags: blender-addon, generative-ai, text-to-video, text-to-image, text-to-speech, text-to-music, movie-studio, video-sequence-editor, screenplay, diffusion-models, ai-cinema, video, audio, natural-language-processing, game-development, linux, macos, gpu

## Member repositories
- tin2tin/Pallaidium (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:57.663691+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:31:55.834375+00:00, confidence not recorded.
  - readme: https://github.com/tin2tin/Pallaidium (fetched 2026-08-28T04:04:57.663691+00:00, sha 931d0f72e0d5)
  - homepage: https://tin2tin.github.io/Pallaidium/ (fetched 2026-08-29T11:35:08.601000+00:00, sha d95f87d0ad89)
- Data as of 2026-08-30T08:39:29.467469+00:00.