Simple app that batch processes a folder of images and converts the processed images into a single video

Auto detecting, masking and inpainting with detection model.

Florence-2 image captioning and tasks

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

Pad or crop an image, rounding to the nearest integer multiple.

Various custom nodes for ComfyUI

This is a side project to experiment with using workflows as components.

Inference Microsoft Florence2 VLM

ComfyUI nodes to use segment-anything-2

Official inference repo for FLUX.1 models

Tiled Diffusion, MultiDiffusion, Mixture of Diffusers, and optimized VAE

SUPIR upscaling wrapper for ComfyUI

Simple DepthAnythingV2 inference node for monocular depth estimation

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Custom nodes pack for ComfyUI This custom node helps to conveniently enhance images through Detector, Detailer, Upscaler, Pipe, and more.

Let us control diffusion models!

Custom prompt styler node for SDXL in ComfyUI

A ComfyUI extension allowing for the interrogation of booru tags from images.

PuLID native implementation for ComfyUI

Open-Set Grounded Text-to-Image Generation

Custom ComfyUI nodes for Vision Language Models, Large Language Models, Image to Music, Text to Music, Consistent and Random Creative Prompt Generation

Stable Diffusion 3 via API in ComfyUI

extra nodes to be used in comfyUI

Custom node for ComfyUI/Stable Diffustion

ComfyUI's ControlNet Auxiliary Preprocessors