A node-and-edge AIGC canvas for DeepSeek Harness. It exposes tools for text-to-image, text-to-video, multi-reference video, and audio generation, keeps prompts and generated media as uuid-addressed canvas elements, and automatically draws links between references and outputs. A provider-agnostic HTTP bridge with ffmpeg post-processing backs 13 tools including canvas linking, reroll, and media editing.
dsh-plugin-aigc-canvas is a DeepSeek Harness ecosystem resource maintained by HuanLinOTO. A node-and-edge AIGC canvas for DeepSeek Harness. It exposes tools for text-to-image, text-to-video, multi-reference video, and audio generation, keeps prompts and generated media as uuid-addressed canvas elements, and automatically draws links between references and outputs. A provider-agnostic HTTP bridge with ffmpeg post-processing backs 13 tools including canvas linking, reroll, and media editing.
Source code and usage instructions are available at https://github.com/HuanLinOTO/dsh-plugin-aigc-canvas. Follow the repository README for the correct setup steps.
dsh-plugin-aigc-canvas is a community open-source project. Review the repository license and documentation before use.
Models & Providers
An AI SDK provider that exposes a DeepSeek Harness (dsh) runtime as a LanguageModelV3, compatible with AI SDK v6 and v7. Any application using the AI SDK can then call on dsh's full agent loop, tools, skills, MCP, and sessions as a language model.
View details → 
krislavten
Models & Providers
Harness engineering beginner tutorial, from 0 to 1
View details → 
walkinglabs
Models & Providers
An LLM-powered multi-agent framework for simulating interactive, evolving story worlds.
View details → 
ZJU-LLMs