hero8152/Infinite-Canvas

What it solves

Infinite-Canvas provides a unified visual interface for interacting with a wide variety of AI model APIs and workflows. It eliminates the need to switch between different platforms by integrating multiple text, image, and video generation models into a single, infinite canvas environment.

How it works

The project acts as a a central hub that connects to various AI services via API calls. It supports a broad range of protocols including OpenAI, Gemini, and Ark, as well as specific integrations for Modelscope, RunningHub, and Jimeng (即梦) CLI. It also allows users to connect to local ComfyUI instances on a local area network (LAN).

Who it’s for

Content creators and AI artists who need to integrate multiple AI generation tools (text, image, and video) into one workspace, as well as those using ComfyUI workflows.

Highlights

• Broad API Support: Compatible with OpenAI, Gemini, and Ark protocols, alongside Modelscope and RunningHub.
• Multimodal Capabilities: Supports text-to-image, image-to-image, text-to-video, and image-to-video generation.
• Integrated Tooling: Includes a Chrome extension for batch collecting materials to a library and a Photoshop plugin for direct canvas access.
• Visual Utilities: Features image expansion, 360-degree panoramic preview screenshots, and video frame extraction.
• Local Integration: Direct support for local ComfyUI instances.