ComfyTV
jtydhr88/ComfyTV
ComfyTV is a canvas-based multimedia workbench extension for ComfyUI that transforms node-based generation into an integrated pipeline for image, video, audio, music, panorama, and 3D media.
Overview
ComfyTV provides a comprehensive tap-now canvas application layer on top of ComfyUI, featuring nearly 190 specialised stages for generating, editing, composing, and exporting media assets. Each stage operates via independent per-node runs using local models and workflows, featuring built-in libraries for assets, resources, and prompt fragments alongside rich in-node editors and a read-only MCP server for AI agent integration.
Capabilities
- ▸Per-node isolated execution with snapshot-based downstream consumption
- ▸Support for ~190 custom stages across image, video, audio, music, panorama, and 3D domains
- ▸Embedded in-node 2D layer editor, storyboards, piano rolls, and 3D viewports
- ▸Asset, resource, and prompt fragment libraries with @ reference support
- ▸Custom ComfyUI workflow import via JSON with sidebar GUI mapping
- ▸Built-in read-only Model Context Protocol (MCP) server for agent access
Best for
Generating and processing images, videos, audio stems, and 3D models using local ComfyUI models., Assembling complex media pipelines by chaining generation, editing, compositing, and export stages., Inspecting and monitoring project states, live canvases, and execution errors via AI agents using the built-in MCP server.
Works with
実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 — AIによるcapabilities/use-cases解析
実装・指示の品質。 — AIによるSKILL.md/README解析
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
ありふれたラッパーではない独自性。 — AIによる独自性判定
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
対応AIエージェントの広さ。 — AIによる対応エージェント判定
ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
The built-in MCP server shares the same security model and lack of authentication as the underlying ComfyUI server; exposing port 8188 externally exposes the MCP endpoint accordingly.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.