ComfyUI-OllamaGemini
A ComfyUI custom node set that adds text and image generation from Gemini, OpenAI, Claude, Ollama, and Qwen, along with several image-editing and object-detection models, in one extension.
ComfyUI-OllamaGemini is a collection of custom nodes for ComfyUI that add text generation from Gemini, OpenAI, Claude, Ollama, and Qwen behind one configuration instead of a separate extension and settings file per provider, including several hundred prompt style presets. It also adds image and video generation nodes for models such as Veo, Imagen, and a Gemini image-editing model, background removal through BRIA RMBG and BiRefNet matting, and object detection and segmentation through SAM3 using plain text prompts.
An auto-install workflow handles setup for these features, including opening the relevant browser panes automatically where needed. The project is aimed at ComfyUI users who want one node pack covering several language and image model providers, plus common post-processing steps such as background and object segmentation, rather than assembling them from separate community nodes. It is written in Python and MIT licensed.