ComfyUI extension for Ollama, Gemini, OpenAI, Claude, and Qwen with video and audio support

ComfyUI-OllamaGemini

Generate images using Google's AI models for image generation:

- gemini-2.0-flash-exp-image-generation: Experimental Gemini model for image generation.
  Fast model that can generate images from text prompts with good accuracy.

- imagen-3.0-generate-002: Google's Imagen 3.0 model for high-quality image generation.
  A more advanced model for detailed, high-fidelity image generation with stronger prompt following.

Both models support reference images to guide the generation process.
When using reference images, the model will try to generate content that's visually similar
or stylistically aligned with the provided images.

Note: These models require proper API access and may have usage limitations or costs associated
with them. Check your Google Cloud/Vertex AI account for details.
    

ComfyUI Node: Gemini Image Generator

Category

Inputs

Outputs

Extension: ComfyUI-OllamaGemini

Run ComfyUI workflows in the Cloud!