Find what you need for your workflow.

Pearly Opal Toon mix (V2)

BEN2

BEN2 (Background Erase Network) introduces a novel approach to foreground segmentation through its innovative Confidence Guided Matting (CGM) pipeline. The architecture employs a refiner network that targets and...

Gemma 4 E4B Uncensored HauhauCS Aggressive

> Join the Discord for updates, roadmaps, projects, or just to chat.

ComfyUI-Easy-Use

In order to make it easier to use the ComfyUI, I have made some optimizations and integrations to some commonly used nodes.

Core Concepts

Dynamic Forms

Realism Illustrious By Stable Yogi (v5.5 FP16)

Improved prompt adherence for clothing details, garment types and color accuracy

Owlv2 Base Patch16

The OWLv2 model (short for Open-World Localization) was proposed in Scaling Open-Vocabulary Object Detection by Matthias Minderer, Alexey Gritsenko, Neil Houlsby. OWLv2, like OWL-ViT, is a zero-shot text-conditioned...

ComfyUI-Easy-Sam3

A ComfyUI custom node package for SAM3 (Segment Anything Model 3), providing powerful image and video segmentation capabilities with text prompts.

Qwen3.5 4B Uncensored HauhauCS Aggressive

> Join the Discord for updates, roadmaps, projects, or just to chat.

LTX 2.3 ID LoRA CelebVHQ 3K

This repository contains the ID-LoRA checkpoint trained on the CelebV-HQ dataset, as introduced in the paper ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA.

Chroma Refiner [I2I]

T5 v1 1 Xxl Encoder GGUF

This is a GGUF conversion of Google's T5 v1.1 XXL encoder model.

ComfyUI-DJZ-ZeroPrompt

ComfyUI Nodes for Zerobytes Prompt system, with custom JSON dictionary support, profile builder Claude Code Skill | | | ORAGEN TEAM

Nova Anime XL (IL v19.0)

NoobAI EPS v1.1 + Illustrious v2.0-stable + ChenkinNoob v0.5 DARE applied

1423866

Exact lora artifact distributed with KodoraIL (v22.0).

ComfyUI-BerniniRWrapper

Wan-Video based custom node for video generation. • Guidance: 7 modes — CFG, APG, RAAG, S2, Z2, STG-A, STG-R • Sampling: context-window (long-video) + per-segment prompt travel • Efficiency: block swap for low-VRAM...

Moss_TTS-ComfyUI

ComfyUI nodes for MOSS-TTS-Local-Transformer-v1.5 , a 48 kHz stereo local Transformer TTS model with direct generation, zero-shot voice cloning, continuation, duration control, pronunciation markup, multilingual...

Ray Z-image turbo Versatile (v1.2)

Sampler: heunpp2 + linear_quadratic schedule seeds_3 + normal is better sampler. CFG Scale: 1 – 2,Steps: 8 – 20 Recommended Speed: CFG: 1, Step: 10 Recommended Quality: CFG: 1.5, Step: 20 Prompting Tip: The more...

ComfyUI_SmartLML

Smart Model Loader for ComfyUI — for vision-language models, text LLMs, and WD14 taggers across 8 backends (Transformers, GGUF, vLLM, SGLang, Ollama, llama.cpp, YOLO, WD14). Supports QwenVL, Mistral3, Florence-2,...