comfyui-nodes

ComfyUI Depth Anything (v1/v2/v3/distill-any-depth) Tensorrt Custom Node (up to 14x faster) ⚡

Janky implementation of HiDiffusion for ComfyUI

Use AI to Animate - ComfyUI Custom Nodes include IMG Caches, Switches, Prompt & Checkpoint changer...

First PuLID implementation for FLUX.2 — Consistent face identity in ComfyUI

T-GATE implementation for ComfyUI.

A variety of custom nodes to enhance ComfyUI for a buttery smooth experience.

ComfyUI custom node providing unified image and mask resizing with support for multiple scaling modes, aspect-ratio preservation, center crop alignment, and stable tensor-based mask transformations.

A prompt helper

在ComfyUI中进行lora微调的节点,依赖于kohya-ss/sd-scripts等训练工具(Nodes for fine-tuning lora in ComfyUI, dependent on training tools such as kohya-ss/sd-scripts)

ComfyUI custom nodes for 100+ AI models — Seedance, Kling, Veo3, Flux, HiDream, GPT-image, Imagen4 and more via muapi.ai

A set of nodes to prepare the noise predictions before the CFG function

Relink missing models in ComfyUI workflows with fuzzy matching, and download them from HuggingFace/CivitAI

Nodes to run Hunyuan Image 3 locally with BF16 and NF4 quantized options in Comfyui

WaveSpeed nodes for ComfyUI — run hundreds of hosted image and video models (Seedream, Nano Banana, GPT Image, Seedance, Wan) inside your workflows

ComfyUI custom nodes for Diffusion Attentive Attribution Maps (DAAM)

Allows to sample without generating any uncond with Stable Diffusion!

集成了众多功能的API节点，只需要一个API-key即可以调用全网的API接口能力，低配电脑也能顺利运行

Provides the ability to set the temperature for both UNET and CLIP. For ComfyUI. Has for side effect to improve non-native resolutions.

Janky implementation of DiffuseHigh for ComfyUI

Local LLM chat panel for ComfyUI — LM Studio & Ollama, multi-session, vision support, Guide Materials