benjiyaya /Calliope
Local-first Agentic Idea-to-video Studio Using ComfyUI + FastAPI + SvelteKit
★ 302⑂ 72👁 8⑃ 34● 55▤ 20
+1
日增长
302
stars
72
forks
8
watchers
34
prs
55
issues
20
releases
README
Calliope Calliope is a local-first story-to-video studio. You type a story idea; Calliope drafts a storyline with beats, characters, and locations, writes a screenplay-faithful per-scene script, then breaks each scene into shot clips and generates one video per clip by driving your own ComfyUI install. When the clips are done, one click stitches them into a finished film with crossfades and matched loudness (ffmpeg). Everything runs on your machine: projects live in SQLite, media lives in folders, and no cloud service is involved beyond the LLM endpoint you point it at. Demo From Script to Video Locally Using Calliope 1.5 https://youtu.be/JcGqt3DYn6c Install — from source (npm + Python) Prerequisites - Python 3.11+ - Node.js 18+ (npm) - A running ComfyUI install, with the models your workflows need already set up - An OpenAI-compatible LLM endpoint — local (LM Studio, Ollama, etc.) or hosted - ffmpeg on PATH — needed for film export 1. Backend (FastAPI) bash cd calliope-backend python -m venv .venv .venv\Scripts\pip install -e ".[dev]" .venv\Scripts\python -m calliope.main --host 127.0.0.1 --port 8247 Optionally copy calliope_config.example.json to calliope_config.json and edit it before starting (LLM endpoint, ComfyUI URL). You can also configure everything later in the app's Settings page. Never commit calliope_config.json — it stores your API key. 2. Frontend (SvelteKit) bash cd calliope-web npm install npm run dev Open http://127.0.0.1:5173. The dev server proxies /api to the backend on 127.0.0.1:8247. First run Open the app, go to Settings, and set: 1. LLM — one or more OpenAI-compatible endpoints (base URL, model name, API key). Save several, then pick which one is Active. 2. ComfyUI — the base URL of your running ComfyUI (e.g. http://127.0.0.1:8188). Workflow jobs go through the Comfy SDK to comfy-api-proxy (default http://127.0.0.1:8189, Settings → Comfy → Comfy API URL). With ComfyUI already on 8188: bash pip install comfy-api-proxy comfy-api-proxy --comfyui http://127.0.0.1:8188 --port 8189 Comfy Router is optional. Save a Comfy API key under Settings → Comfy, turn on Use Comfy API provider (Router), and the video and asset pickers offer MiniMax H3 and FLUX 3. No key, or the switch left off, means every job stays on your local workflow. 3. Agent (optional) — assign a specific LLM per agent role (see below) Leave Dry-run off — it is meant for testing and produces placeholder results instead of real generations. Queue settings In Settings → Queue you can tune how the worker talks to ComfyUI: - Concurrency — how many jobs run at once. - Poll interval — how often Calliope checks ComfyUI for a finished job. - Poll timeout (seconds) — how long Calliope keeps waiting on ComfyUI for a single job before failing it. Default is 1800 (30 minutes). Long video generations can easily exceed 10 minutes, so raise this for heavy workflows — or set it to 0 to wait indefinitely (until the job finishes or you cancel it)
Top issues
#51[Coming update] V.1.5 - Build Scene With 3D Blocks - Story-Script-Clips Enhancement5 comments · 2026-09-08#9[Feature Request] UX Improvements & Much Needed Features for Video/Asset Workflow3 comments · 2026-08-22#3Ideas to improve3 comments · 2026-08-19#22extract_json returns the first inner object when the envelope is truncated or malformed — retry never fires, surfaces as "0 beats"2 comments · 2026-08-24#19[Bug / Feedback] LLM Agent context desynchronization and permission errors2 comments · 2026-08-23#11Expand Playground into Asset Creation with Character Looks, Objects, and Video Guides2 comments · 2026-08-22#8Hardcoded 10-minute timeout in _poll_history causes long ComfyUI video generations to fail2 comments · 2026-08-20#98[Doc] Documentation points to an incompatible H3 Motion Context node1 comments · 2026-10-16
Discussions
#103Update Calliope0 comments · 2026-10-28#101Custom node Calliope1 comments · 2026-10-21#82Entrée Boolean0 comments · 2026-10-04#77Ajout d'autres langues !0 comments · 2026-09-29#70Storyboard needed please!1 comments · 2026-09-25#65Telechargement de la dernière Version 1.5.62 comments · 2026-09-22#61Amélioration "Construction de Scene"0 comments · 2026-09-14#56My journey with Calliope (Raw thoughts & experiments)2 comments · 2026-09-11
Latest release
Calliope 1.7.0 — agent engine rewrite and gap fixes v1.7.0 2026-11-14Release v1.7.0, 2026-11-14. The plugin harness is gone; the agent loop is a grant-scoped studio runtime, the capabilities it dropped are restored, and plain chat converses again. The agent loop has been rewritten The old plugin harness (harness/loop|orchestrator|policy|registry|tools, harness/plugins/) is gone, replaced by a grant-scoped studio runtime (agent/runtime/ + agent/capabilities/): - Your message is matched into scoped studio calls (story → script → assets → render → canvas). Each call runs ONE sub-agent that only sees its grant's tools, and the run is verified against the