This repository provides a collection of custom nodes for ComfyUI, aimed at enhancing AI-powered image and video generation workflows. It offers integrations with various large language models (LLMs) and AI services, enabling users to leverage advanced features like text-to-image, image-to-image, and video generation directly within ComfyUI.

How It Works

The project extends ComfyUI by introducing new nodes that act as interfaces to external AI APIs. These nodes abstract the complexities of API calls, allowing users to chain them together in ComfyUI's node-based interface. Key integrations include OpenAI's GPT models for image generation and editing, Google's Gemini models for multimodal tasks, and Kling for text-to-video and lip-sync functionalities. The nodes are designed to be flexible, supporting various parameters and offering options for different API tiers and pricing models.

Quick Start & Requirements

• Installation typically involves placing the custom nodes into the custom_nodes directory of your ComfyUI installation.
• Requires a working ComfyUI setup.
• API keys for services like OpenAI, Gemini, and Kling are necessary and can be managed via a Comflyapi.json file or within the UI.
• Refer to the ComfyUI documentation for base setup.

Highlighted Details

• Integrates OpenAI's gpt-image-1 and gpt-image-1-edit models with options for different API groups (e.g., ssvip).
• Supports Google Gemini models for text-to-image, image editing, and multi-image generation with up to 4 images.
• Includes Kling nodes for text-to-video, image-to-video, and lip-sync generation.
• Offers a ComflyChatGPTApi node with multi-turn conversation support and image editing capabilities.
• Provides utility nodes for managing ComfyUI dependencies, versions, and custom nodes.

Maintenance & Community

• The project is actively updated with frequent additions and modifications to nodes and features.
• A QQ group is available for community support and discussion.
• Contact email: 3508432500@qq.com.

Licensing & Compatibility

• The repository does not explicitly state a license.
• Compatibility with commercial use or closed-source linking is not specified.

Limitations & Caveats

• Some nodes are explicitly noted as being in testing or having potential stability issues (e.g., the "reverse API" for GPT-image-1).
• The README mentions that some AI modules (like Suno) are not yet adapted.
• The "Warning" plugin is only tested on Windows 11, with macOS testing planned.