Content
Plugin
pai-pro
The local AI filmmaking studio, driven from your coding agent. ![Discord][discord-url] [][claude-code-url] [][codex-url]
Plugin Signal65/100Solid
maintained96
capable41
documented55
adopted53
Install on Claude Code
> /plugin marketplace add Utopai-Research/pai-pro> /plugin install pai-pro@pai-pro
Stats
323
Stars
30
Forks
Active
Maintenance
JavaScript
Language
6d ago
Last commit
2mo ago
Created
Repo: Utopai-Research/pai-pro
What's inside
Skills
6/groups-composeDesigns and maintains semantic groupings and readable layouts on the filmmaking canvas โ scenes, character-reference sets, act beats, and other titled visual frames. Use when nodes on the canvas cluster around a shared meaning and would read more clearly if arranged together and/image-composeGenerates/edits filmmaking canvas images via generate_image.js and generate_image_pro.js. Use before image CLIs for character/location design, refs, starting frames, storyboards, stills, edits, variations, and downstream video anchors. Video-bound characters default to Pattern 7/script-composeHandles explicit screenplay/story work on the filmmaking canvas. Triages screenplay (use verbatim), story/concept (iterate then rewrite), or neither (defer). Captures the final script note/title; on explicit command, splits into <=15s shot notes and extracts characters,/story-to-video-workflowOrchestrates story, script, screenplay, concept, product promo, and multi-shot idea work into finished video. Use first when the user asks to make a video from a story or script; asks what next in a story video project; or needs a decision spanning script splitting, image refs,/video-composeGenerates and prompts video clips on the filmmaking canvas. Use when the user asks to generate, render, animate, continue, restyle, edit, shoot, or compose a video clip; render script or shot notes as video; animate a storyboard, starting frame, image, character, location, or/voice-composeDesigns and attaches voice samples or final narration/line audio on the filmmaking canvas via the local generate_voice.js CLI. Use before calling generate_voice.js; when the user asks to give a character a voice, preview how a character sounds, create reusable timbre anchors for
README
1PAI-Pro
The local AI filmmaking studio, driven from your coding agent.
What's PAI-Pro?
PAI-Pro is a local-first AI filmmaking workspace built around four things:
- Your own Claude Code or Codex, capable agents connected to local project files, persistent context, and customized filmmaking skills. (Setup and agents)
- End-to-end filmmaking skills for scripts, images, videos, and voice. (More skill details)
- A visual canvas and timeline for designing scenes, managing assets, arranging shots, and keeping larger productions organized.
- One API service for story media across image, video, voice, and 4K upscaling, so productions do not need separate providers for each step. (API service details)
Quick start
Use Claude Code or Codex to install PAI-Pro for you. Paste this into your agent:
Clone
https://github.com/Utopai-Research/pai-pro, read the setup docs in README.md and docs/setup.md, then install PAI-Pro for my current agent. Ask me for myPAI_KEY, use Docker unless I ask for local development, and start the app when setup is complete.
| Choose | Commands |
|---|---|
| Claude Code | Docker: ./scripts/docker-start.shLocal: if ports are busy, run ./scripts/stop.sh first; then ./scripts/setup --agent claude and ./scripts/start.sh |
| Codex | Docker: PAI_DEFAULT_AGENT_ID=codex ./scripts/docker-start.shLocal: if ports are busy, run ./scripts/stop.sh first; then ./scripts/setup --agent codex and PAI_DEFAULT_AGENT_ID=codex ./scripts/start.sh |
Open Docker at http://localhost:7588 or local at http://localhost:7443.
API Service
PAI_KEY gives each production one service for image, image pro, video, voice, and 4K upscaling, without separate provider keys for each step. Use the PAI Pro Developer Platform to manage keys, tasks, balance, and credits. It also supports less restrictive video moderation via asset preupload and helps support this project. Paid generations are staged first; for BYOK and exact payloads, see API Service.
| Capability | Quality | Time | # of references | Estimated price |
|---|---|---|---|---|
generate_image | Great | ~10-30s | 16 imgs | $0.07 / $0.10 / $0.15 for 1K / 2K / 4K |
generate_image_pro | Best | ~3-6 min | 32 imgs | $0.26 / $0.45 / $0.77 for 1K / 2K / 4K |
generate_video | Best | ~3-6 min | 9 imgs / 3 vids / 3 auds | $0.08/s / $0.20/s / $0.44/s for 480p / 720p / 1080p |
upscaler | Best | 1-min example: ~4-8 min landed | 1 video | 1-min example: $1.35 for 1080p->4K, $2.35 for 720p->4K |
generate_voice | Good | ~5-15s | N/A | $0.01 per 500 input characters, rounded up |
Resources
- ๐ฌ Discord โ questions, ideas, support, and show & tell
- โ๏ธ API Service โ developer platform notes, BYOK counterparts, and exact media JSON payloads
- ๐ฌ Skills reference โ how filmmaking skills route agent requests
- ๐ Setup and agents โ choose Docker or host mode, configure Claude/Codex, and understand ports, auth, and permissions
- ๐ Architecture โ viewer, CLI, canvas, and project-file layout
- โ FAQ โ common setup and generation issues
- ๐ Issues โ bug reports only
- ๐ค Contributing โ contribution guide, proprietary-skills carve-out, and CLA flow
License
PAI-Pro is released under the PAI PRO Sustainable Use License, which permits personal use, non-commercial research, and internal business use. Commercial use of PAI-Pro Skills or enterprise-designated source code/Skills requires an explicit agreement; enterprise licenses are available.
File tree
257Utopai-Research/pai-proView on GitHub
.claude/
.claude-plugin/
marketplace.json
hooks/
block_workflow_writes.js
require_background_for_generate.js
settings.json
.dockerignore
.env.example
.gitattributes
.github/
ISSUE_TEMPLATE/
bug.yml
config.yml
pull_request_template.md
workflows/
ci.yml
.gitignore
.nvmrc
agent-templates/
PROJECT_AGENT.md
AGENTS.md
CLAUDE.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
CONTRIBUTOR_LICENSE_AGREEMENT.md
docker/
docker-compose.yml
entrypoint.sh
Dockerfile
docs/
api_service.md
architecture.md
assets/
banner.png
canvas_view.webp
faq.md
plans/
.gitkeep
setup.md
skills.md
LICENSE.md
README.md
README.zh-CN.md
scripts/
docker-start.sh
setup
start.sh
stop.sh
SECURITY.md
server/
__tests__/
agent_provider.test.js
agent_trust.test.js
archive_guardrails.test.js
broadcasters_debounce.test.js
canvas_layout_http.test.js
canvas_mutator_http.test.js
canvas_mutator_stress.test.js
canvas_mutator.test.js
codex_provider.test.js
docker_config_static.test.js
extract_frames.test.js
file_state_integrity.test.js
fixtures/
sample_workflow.json
generate_image_cli.test.js
generate_image_pro_cli.test.js
generate_url_removal.test.js
generate_video_cli.test.js
generate_voice_cli.test.js
generation_results.test.js
image_pro_sizes.test.js
mirror_url.test.js
model_registry.test.js
pai_assets_client.test.js
pai_client.test.js
pai_image_client.test.js
pai_image_pro_client.test.js
pai_upscale_client.test.js
pai_video_client.test.js
pai_voice_client.test.js
pdf_extract.test.js
pending_position_handoff.test.js
pending_routes.test.js
pending_stage.test.js
project_create_agent.test.js
provider_refs.test.js
recover_orphans.test.js
reel_cache.test.js
reel_stitch.test.js
ref_guard.test.js
require_background_hook.test.js
setup_script.test.js
shared_instructions_lint.test.js
socket_agent_session.test.js
split_image.test.js
stream_url_to_tmp.test.js
system_routes.test.js
uploads_routes.test.js
wait_for_generation.test.js
workflow_contract.test.js
agents/
bypass.js
claude.js
codex.js
index.js
registry.js
canvas_mutator.js
canvas_schema.js
cli/
_cli.js
_dev_send_to_pty.mjs
_limits.js
_mutate_helper.js
_pending.js
_preupload_hook.js
_ref_guard.js
canvas_layout.js
canvas_mutate.js
extract_frames.js
generate_image_pro.js
generate_image.js
generate_video.js
generate_voice.js
list_generation_results.js
migrate_ids.js
mirror_url.js
reel_stitch.js
split_image.js
switch_project.js
upscaler.js
wait_for_generation.js
wait_for_generations.js
image_pro_sizes.js
image_split.js
lib/
atomic_writes.js
auto_runs.js
broadcasters.js
canvas_layout.js
generation_result_normalize.js
paths.js
readers.js
reel_cache.js
upload_payload.js
writers.js
local_mirror.js
local_viewer.js
model_registry.js
package-lock.json
package.json
pai_assets_client.js
pai_client.js
pai_image_client.js
pai_image_pro_client.js
pai_upscale_client.js
pai_video_client.js
pai_voice_client.js
pdf_extract.js
reel_stitch.js
routes/
canvas.js
pending.js
projects.js
reel.js
system.js
uploads.js
services/
asset_sync.js
projects.js
socket.js
watcher.js
upload_classify.js
skills/
CLAUDE.md
groups-compose/
SKILL.md
image-compose/
references/
character-sheet.md
storyboard-mosaic.md
SKILL.md
script-compose/
SKILL.md
story-to-video-workflow/
SKILL.md
video-compose/
references/
video-editing.md
video-extension.md
video-multi-shot.md
video-single-shot.md
SKILL.md
voice-compose/
SKILL.md
VERSION
web/
index.html
package-lock.json
package.json
postcss.config.js
public/
favicon.png
src/
App.tsx
components/
AssetRail/
AssetRow.tsx
EmptyState.tsx
index.tsx
RailExpandedPanel.tsx
RailIconColumn.tsx
useAssets.ts
TerminalPanel.tsx
timeline/
AvailableDroppable.tsx
ClipGhostBody.tsx
DraggableCompactCard.tsx
GhostPlaceholder.tsx
ReelAreaDroppable.tsx
SortableClip.tsx
StripedPlaceholder.tsx
TimelinePanel.tsx
contexts/
CanvasFocusContext.tsx
ChatComposerContext.tsx
MediaExpandContext.tsx
ProjectContext.tsx
hooks/
useWorkflow.ts
index.css
lib/
canvas-stub.ts
firstFireGate.ts
socket.ts
useModels.tsx
workflowMerge.test.ts
workflowMerge.ts
main.tsx
pages/
_tmp/
TmpRoute.tsx
.gitignore
CanvasPage/
audioPlayback.ts
batchPlace.test.ts
batchPlace.ts
canvas-overlays.css
draft-gate-modal.css
DraftGateModal.tsx
expand-overlay.css
fire-confirm-modal.css
FireConfirmModal.tsx
FireConfirmProvider.tsx
generationFailurePrompt.ts
group-create-modal.css
group-frame.css
GroupCreateModal.tsx
groupFrameHues.ts
GroupFrameNode.tsx
HighlightEdge.tsx
index.tsx
MediaExpandChat.tsx
MediaExpandOverlay.tsx
NodeActionsContext.tsx
nodeData.ts
nodes/
nodes-base.css
_shared.tsx
AudioResultNode.tsx
ImageResultNode.tsx
index.ts
NoteNode.tsx
PendingGenerationNode.tsx
VideoResultNode.tsx
placement.test.ts
placement.ts
projection.ts
save-status.css
saveStatusContext.tsx
SaveStatusPill.tsx
selection-toolbar.css
SelectionToolbar.tsx
tidy.test.ts
tidy.ts
upload-overlay.css
UploadOverlay.tsx
useCanvasPositions.ts
ZoomBar.tsx
CanvasView.tsx
Home.tsx
types/
canvas.ts
vite-env.d.ts
tailwind.config.js
tsconfig.json
tsconfig.node.json
vite.config.ts
vitest.config.tsFAQ
pai-pro is a Claude Code plugin with 6 hand-picked skills for content work, indexed on Flowy. Install it with the command on its page. It includes groups-compose, image-compose, script-compose. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is pai-pro?
- The local AI filmmaking studio, driven from your coding agent. ![Discord][discord-url] [][claude-code-url] [][codex-url]
- How do I install pai-pro?
- Run these in Claude Code: /plugin marketplace add Utopai-Research/pai-pro then /plugin install pai-pro@pai-pro. Then prompt normally.
- Does pai-pro auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is pai-pro free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.