ComfyUI_Nano_Banana

NanoBanana2AIO

A dedicated node for the gemini-3.1-flash-image-preview model, optimized for speed and high-volume use cases. This node provides all the latest features including support for up to 14 reference images, new extreme aspect ratios, and Google Image Search grounding. Note: Requires the latest google-genai package. Update with: pip install google-genai --upgrade Inputs: modelname (STRING): The Gemini model to use. Currently using: gemini-3.1-flash-image-preview for high-efficiency image generation (default: gemini-3.1-flash-image-preview). prompt (STRING): The text prompt for image generation or manipulation. imagecount (INT): Number of images to generate (1-10). When set to 1, behaves like single image generation; when >1, generates multiple sequential images (default: 1). usesearch (BOOLEAN): Toggle to enable or disable Google Search functionality (default: False). useimagesearch (BOOLEAN): Toggle to enable Google Image Search grounding for visual reference accuracy (default: False). Enable usesearch to use this feature. image1 to image14 (IMAGE, optional): Up to fourteen reference images. Gemini 3.1 Flash supports up to 10 object images with high-fidelity and up to 4 character images for consistency. aspectratio (STRING): The output aspect ratio for the generated image. Options include: 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9, Auto (default: 1:1). When set to Auto, the AI automatically determines the optimal aspect ratio. imagesize (STRING): The output image quality/size. Options include: 512px, 1K, 2K, 4K (default: 2K). The 512px option is ex…

Ru4ls/NanoBanana · 3 outputs

NanoBanana2MultiTurnChat

A conversational image generation and editing node using the gemini-3.1-flash-image-preview model. Supports multi-turn conversations with preserved context, allowing iterative image modifications. Includes all Nano Banana 2 features: 14 reference images, extreme aspect ratios, and Image Search grounding. Note: Requires the latest google-genai package. Update with: pip install google-genai --upgrade Inputs: modelname (STRING): The Gemini model to use. Currently using: gemini-3.1-flash-image-preview for high-efficiency image generation (default: gemini-3.1-flash-image-preview). prompt (STRING): The text prompt for image generation or modification based on previous conversation context. resetchat (BOOLEAN): Toggle to reset the conversation history and start a fresh chat session (default: False). usesearch (BOOLEAN): Toggle to enable or disable Google Search functionality (default: False). useimagesearch (BOOLEAN): Toggle to enable Google Image Search grounding for visual reference accuracy (default: False). Enable usesearch to use this feature. aspectratio (STRING): The output aspect ratio for the generated image. Options include: 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9, Auto (default: 1:1). When set to Auto, the AI automatically determines the optimal aspect ratio. imagesize (STRING): The output image quality/size. Options include: 512px, 1K, 2K, 4K (default: 2K). The 512px option is exclusive to Nano Banana 2. temperature (FLOAT): Controls the creative randomness of the output. Higher values (e.g., 1.2) are more creative, lower values (e.g.,…

Ru4ls/NanoBanana · 4 outputs

NanoBananaAIO

A unified multimodal node combining all features: single/multiple image generation, grounding, search, and thinking capabilities.

Ru4ls/NanoBanana · 3 outputs

NanoBananaMultiTurnChat

This node supports conversational image generation and editing with preserved context across multiple interactions. Maintains conversation history and allows iterative image modifications by referencing previous images as context for new generations. Includes reset functionality to start fresh conversations. Inputs: modelname (STRING): The Gemini model to use. Currently using: gemini-3-pro-image-preview for advanced capabilities (default: gemini-3-pro-image-preview). prompt (STRING): The text prompt for image generation or modification based on previous conversation context. resetchat (BOOLEAN): Toggle to reset the conversation history and start a fresh chat session (default: False). aspectratio (STRING): The output aspect ratio for the generated image. Options include: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, Auto (default: 1:1). When set to Auto, the AI automatically determines the optimal aspect ratio based on the prompt content. imagesize (STRING): The output image quality/size. Options include: 1K, 2K, 4K (default: 2K). temperature (FLOAT): Controls the creative randomness of the output. Higher values (e.g., 1.2) are more creative, lower values (e.g., 0.5) are more deterministic (default: 1.0). imageinput (IMAGE, optional): Initial image to start the conversation with. Use this to provide an initial image for the first interaction in a conversation. Available Aspect Ratios & Resolutions: 1:1 - 1024x1024 (square) 2:3 - 832x1248 (portrait) 3:2 - 1248x832 (landscape) 3:4 - 864x1184 (portrait) 4:3 - 1184x864 (landscape) 4:5 - 896x1152 (portrait) 5:4 - 1152x896…

Ru4ls/NanoBanana · 4 outputs