Desktop AI art engine that combines a node graph, specialized editors and a 3D director stage for generating short-video, game and advertising assets, with local-first model access.
ganbo-gab/open-storyboard-canvas
A local node-based canvas for AI image, video and storyboard creation, with an in-canvas agent, a 3D director studio and pluggable generation providers.
- Stars
- 392
- Forks
- 78
- Open issues
- 10
- Last commit
- 2 hours ago
What is it?
Open Storyboard Canvas puts reference assets, prompts, AI image and video generation, storyboard breakdown, a 3D director studio, panoramic environments and result management into one infinitely extensible local canvas. Nodes can be connected, tracked, restored and edited again, so it works as a repeatable creative workflow rather than a one-shot prompt-to-image tool.
The desktop app is built with Tauri 2, React, TypeScript and Rust, and runs on macOS and Windows. Providers include Agnes, custom OpenAI-compatible endpoints and a local Dreamina CLI. Asynchronous generation jobs are persisted, and unknown submission results are not automatically resubmitted, which avoids duplicate billing.
An in-canvas agent (currently in beta) can create and edit nodes, submit generations, check task status and read redacted logs. Projects, nodes, history and media references are saved to the local machine, and API keys stay in local settings.
Key features
- 01Node canvas for uploads, AI text, image and video generation, storyboards, panoramas and director studio.
- 02Director studio with 3D characters, props, lighting and camera control.
- 03Persistent tracking of async generation jobs with recoverable results.
- 04Tag groups that bundle image, video and text references.
- 05Batch prompt import from tables to create many canvas tasks at once.
- 06Local project storage with undo/redo and light/dark theme.
Use cases
- Storyboarding a short film or ad with AI-generated frames and camera setups.
- Building repeatable image-to-video pipelines from reference images.
- Pre-visualizing scenes in a 3D director studio before generating final shots.
- Batch-generating variations from a prompt table.
In collections
Topics
FAQ
- What is open-storyboard-canvas?
- A local node-based canvas for AI image, video and storyboard creation, with an in-canvas agent, a 3D director studio and pluggable generation providers. Open Storyboard Canvas puts reference assets, prompts, AI image and video generation, storyboard breakdown, a 3D director studio, panoramic environments and result management into one infinitely extensible local canvas. Nodes can be connected, tracked, restored and edited again, so it works as a repeatable creative workflow rather than a one-shot prompt-to-image tool.
- Is open-storyboard-canvas free to use? What license does it have?
- open-storyboard-canvas is open source under the Other license. Check the license terms before using it in commercial products.
- Is open-storyboard-canvas still maintained?
- Actively maintained. The last commit to open-storyboard-canvas was on Nov 7, 2026.
- What can I use open-storyboard-canvas for?
- Storyboarding a short film or ad with AI-generated frames and camera setups. Building repeatable image-to-video pipelines from reference images. Pre-visualizing scenes in a 3D director studio before generating final shots. Batch-generating variations from a prompt table.
- Where can I get open-storyboard-canvas?
- The source code and installation instructions are on GitHub: https://github.com/ganbo-gab/open-storyboard-canvas
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A node-graph GUI, API and backend for running diffusion models locally to generate images, video, audio and 3D content.
A self-hosted desktop app for building AI image and video generation pipelines visually on an infinite node-based canvas, using your own kie.ai key.
An open-source node canvas for generating images and video by wiring prompts, references and models into workflows run on a local ComfyUI server.
Agentic video generation framework that turns a story idea, screenplay, or novel into a multi-shot video by coordinating script, storyboard, character, and video generation agents.
Agent skill that turns Chinese story text or ordered images into a silent 3:4 hand-drawn diary-comic video rendered with Remotion.