ComfyUI-OllamaGemini

FLUXResolutions

Compact description unavailable for this node.

GeminiAPI

Compact description unavailable for this node.

AI API/Gemini · 1 output

GeminiBBoxJoin

Join multiple bounding box lists.

AI API/Detection · 3 inputs · 0 parameters · 1 output

GeminiBEN2_RMBG

BEN2 Background Removal Node Uses the BEN2 (Background Erase Network) model for high-quality foreground segmentation. Excels at: - Hair and fur segmentation - 4K image processing - Edge refinement

AI API · 1 input · 1 parameter · 2 outputs

GeminiBRIA_RMBG

Compact description unavailable for this node.

AI API · 1 input · 1 parameter · 2 outputs

GeminiBRIA_RMBG_Safe

Safe version that only uses RMBG-1.4 to avoid compatibility issues

AI API · 1 input · 0 parameters · 2 outputs

GeminiCLIPSeg

Compact description unavailable for this node.

Image · 1 input · 4 parameters · 2 outputs

GeminiCombineSegMasks

Compact description unavailable for this node.

Image · 2 inputs · 0 parameters · 1 output

GeminiComfyUIStyler

Compact description unavailable for this node.

GeminiConvertRasterToVector

Convert raster images to SVG vector graphics using vtracer for best quality.

AI API · 1 input · 10 parameters · 1 output

GeminiDrawBBoxMask

Draw bounding boxes as mask.

AI API/Detection · 2 inputs · 1 parameter · 1 output

GeminiFLUXResolutions

Compact description unavailable for this node.

AI API · 2 outputs

GeminiImageGenerator

Compact description unavailable for this node.

AI API/Gemini · 2 outputs

GeminiLoadImagePath

Load an image from a file path OR a directory (with index selection). When given a directory, use 'index' to select which image to load. Enable 'auto_increment' to automatically advance to next image each run. Outputs: IMAGE tensor, MASK, filename, directory path, dimensions

AI API/Image · 0 inputs · 8 parameters · 9 outputs

GeminiLoadImagesFromDir

Load images from a directory ONE BY ONE. Outputs same structure as Load Image Path - iterates through each image.

AI API/Image · 0 inputs · 6 parameters · 8 outputs

GeminiMathExpression

Math Expression Evaluator ------------------------- Evaluates mathematical expressions with inputs a, b, c, d. Supports: - Arithmetic: + - * / // % ** - Bitwise: & | ^ ~ >> << - Comparison: == != > < >= <= - Functions: sin, cos, sqrt, min, max, clamp, iif, etc. - Constants: pi(), e(), tau()

AI API/Utils · 3 outputs

GeminiSaveSVG

Save SVG data to a file and generate a preview image.

AI API · 1 input · 6 parameters · 2 outputs

GeminiSaveText

Compact description unavailable for this node.

AI API · 1 input · 2 parameters · 0 outputs

GeminiSmartPromptGenerator

A node that intelligently combines multiple style elements from different categories to create creative prompts.

AI API · 2 outputs

GeminiSVGPreview

Preview SVG data as an image with improved rendering.

AI API · 1 input · 2 parameters · 1 output

GeminiTextSplitter

Compact description unavailable for this node.

AI API · 0 inputs · 5 parameters · 1 output

GeminiUltraDetect

Ultra Object Detection Node --------------------------- Standalone implementation using latest 2025/2026 models: - YOLO-World V2.1 for detection - SAM2.1 for segmentation - ViTMatte/BiRefNet for matting

AI API/Detection · 2 inputs · 9 parameters · 4 outputs

ListAvailableModels

Compact description unavailable for this node.

AI API/Utils · 0 inputs · 2 parameters · 1 output

OllamaAPI

Compact description unavailable for this node.

AI API/Ollama · 1 output

OpenAIAPI

Compact description unavailable for this node.

QwenAPI

Compact description unavailable for this node.

AI API/Qwen · 14 inputs · 10 parameters · 1 output

style_menus

Compact description unavailable for this node.

VeoLoadVideo

Load a video file and extract frames/audio.

AI API/Veo · 0 inputs · 2 parameters · 5 outputs

VeoVideoExtend

Extend a previously generated Veo video. IMPORTANT: Connect the 'video_uri' output from VeoVideoGenerator directly to this node. The Veo API requires the ORIGINAL video URI from Gemini - re-uploading a downloaded video file will NOT work for extension. Only works with Veo 3.1 models.

AI API/Veo · 1 input · 5 parameters · 6 outputs

VeoVideoGenerator

Generate videos using Google's Veo API. Based on: https://ai.google.dev/gemini-api/docs/video Supports: - Text-to-video - Image-to-video (first frame) - Seed for Veo 3 models (slightly improves determinism)

AI API/Veo · 1 input · 8 parameters · 6 outputs

VeoVideoGeneratorAdvanced

Advanced Veo 3.1 video generation with all features: - Reference images (up to 3) - First + Last frame interpolation - Full parameter control

AI API/Veo · 5 inputs · 8 parameters · 6 outputs