Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
16 shown of 34,640
ComfyUI-Smart-Resolution-Calc
Smart Resolution Calculator for ComfyUI - Flexible resolution and latent generation with toggle-based dimension controls. Specify aspect ratio + width OR height to auto-calculate height/width for precise image...
comfyui-fp8-load-clip
ComfyUI FP8 CLIP Loader - custom node that stores large text‐encoder Linear weights as torch.float8e4m3fn on GPU to reduce VRAM pressure and prevent VRAM overflow to system RAM for models like Qwen3 8B, on lower VRAM...
ComfyUI-SkyworkUniPic
ComfyUI-SkyworkUniPic is now available in ComfyUI, Skywork-UniPic is a unified autoregressive multimodal model with 1.5 billion parameters that natively integrates image understanding, text-to-image generation, and...
ComfyUI-Qwen-CUDA
Custom nodes for ComfyUI QWen3 8b running based on llama.cpp, which only support the CUDA framework and do not support MPS.
ComfyUI-IF_LLM
Run Local and API LLMs, Features Gemini2 image generation, DEEPSEEK R1, QwenVL2.5, QWQ32B, Ollama, LlamaCPP LMstudio, Koboldcpp, TextGen, Transformers or via APIs Anthropic, Groq, OpenAI, Google Gemini, Mistral, xAI...
ComfyUI-Egregora-ARMD
🌐 ARMD (Adaptive Regional Mixture of Diffusers) is a region-based diffusion system for ComfyUI, designed for semantic upscaling with per-region conditioning, optional VLM captioning, and adaptive regional...
comfyui-attention-selector
Simple attention backend selector for ComfyUI.Supported backends:PyTorch(SDPA) - xformers - SageAttention auto mode-SageAttention CUDA (qkint8pvfp16)-SageAttention Triton (qkint8pvfp16)-SageAttention CUDA...
ComfyUI-GLHF
GLHF is a ComfyUI node that facilitates seamless interaction with the GLHF chat API. Designed to enhance user experience, it supports multiple language models, web search integration, and customizable instructions,...
ComfyUI-EsesImageAdjustments
Image adjustments node for ComfyUI. Contrast, gamma, saturation, hue rotate, R, G and B channel offset, filter color, sharpness, unsharp mask, film grain (fast), grayscale conversion. Minimal requirements. Uses...
comfyui-gpt-image
Ports the official ComfyUI GPT-API node, adding support for customizable apibase, authtoken, and model settings.
ComfyUI-ScheduledTask
A powerful workflow scheduling extension for ComfyUI that enables automated daily execution of workflows with an intuitive web interface.
ComfyUI-mnemic-nodes
Nodes: Batch Wildcard Sampler, Save Image With Metadata, Wildcard Processor, Get File Path, Save Text File, Download Image from URL, Tiktoken Tokenizer, String Cleaning, String Text Splitter, String Text Extractor,...
ComfyUI-Transformers-Pipeline
Additional ComfyUI nodes allowing Transformer tasks via the Huggingface Transformers Pipeline, e.g. image captioning. In future, translation, zero shot, and hopefully more.
SIMPLE FLUX DEV WORKFLOW by weshouldhaveshotguns — v2
SIMPLE FLUX DEV WORKFLOW by weshouldhaveshotguns
Comfyui_joytag
JoyTag is a state of the art AI vision model for tagging images, with a focus on sex positivity and inclusivity. It uses the Danbooru tagging schema, but works across a wide range of images, from hand drawn to...
ComfyUI-ExcelStylesLoader
A dynamic ComfyUI custom node that reads prompts from individual sheets/tabs within a local Excel (.xlsx) workbook. Organizes workflows by category (e.g., Styles, Lighting, Aesthetics) and dynamically filters the...
