Enables image and video generation across GPT-Image, Gemini, Grok, and Jimeng with file-based outputs, multi-reference support, and model capability lookup.
Provides MCP tools to submit asynchronous image generation jobs, check their status, cancel/retry them, and list or fetch generated assets, keeping prompts and outputs local unless an OpenAI provider is explicitly selected.
Enables AI assistants to generate and edit images through Gemini, OpenAI, or BytePlus Seedream, automatically expanding brief requests into detailed prompts with quality presets. Generated files are saved to disk and returned to the client as MCP resources.
Enables generating images, video, and audio through a single capability-oriented interface, with server-side routing, safety screening, job lifecycle management, concurrency limits, and retention.
Enables local, provider-independent image generation and editing through named connections, multiple image protocols, and configured ComfyUI workflows, with saved outputs, job tracking, and explicit tool operations.