NodeWatchWhat changed this weekAbout / methodology
Heads up: statuses are automated heuristics from commit dates, registry metadata and issue titles. "Stale" can mean "finished and stable"; "Error spike" means error-titled issues are unusually high for that pack lately — worth checking recent issues, not a verdict that it is broken. Always check the repo.

Loaders, quantization & speed ComfyUI custom nodes: which ones still work

54 of the 300 most-downloaded ComfyUI custom node packs are tagged Loaders, quantization & speed. 42 are active, 12 look stale (no commit in a year or repo gone), 0 show an error spike. Statuses are refreshed nightly from GitHub and the Comfy Registry — check each pack page for recent issues, ComfyUI version requirements and active forks.

Get the weekly NodeWatch report: what broke, what went stale, what shipped.
Form not showing? Subscribe here.
#PackStatusDownloadsStarsStars (30d)Last commitError issues (30d)
9ComfyUI-GGUF
GGUF Quantization support for native ComfyUI models.
Active Quiet Has active fork2,700,43841552026-01-121
14ComfyUI-WanVideoWrapper
ComfyUI wrapper nodes for WanVideo
Active2,012,59167342026-05-241
20Deno Custom Nodes
DENO RTX node pack for ComfyUI: CPU film grain for photos and video, draggable hardware resource monitoring, MiniMax H3
Active1,410,5821922026-10-17
23ComfyUI-SeedVR2_VideoUpscaler
SeedVR2 official ComfyUI integration: ByteDance-Seed's one-step diffusion-based video/image upscaling with memory-effici
Active Quiet Has active fork1,104,20129292025-12-241
25gguf
gguf node for comfyui
Active1,054,5472742026-10-17
34ComfyUI-nunchaku
Nunchaku ComfyUI Node. Nunchaku is a high-performance inference engine optimized for low-bit neural networks. See more d
Active832,54429332026-09-061
39ControlAltAI_Nodes
Quality of Life Nodes from ControlAltAI. Flux Resolution Calculator, Flux Sampler, Flux Union ControlNet Apply, Noise Pl
Stale / abandoned688,0672112025-06-05
42ComfyUI-TeaCache
Unofficial implementation of [ali-vilab/TeaCache](https://github.com/ali-vilab/TeaCache) for ComfyUI
Stale / abandoned Has active fork618,38310972025-07-12
44comfyui-mixlab-nodes
3D, ScreenShareNode & FloatingVideoNode, SpeechRecognition & SpeechSynthesis, GPT, LoadImagesFromLocal, Layers, Other No
Active605,77018622026-06-04
47Comfyui-Memory_Cleanup
A ComfyUI extension that provides nodes for memory cleanup, including VRAM and RAM cleanup functions to optimize ComfyUI
Active Quiet Has active fork552,2024082026-01-12
52ComfyUI-QwenVL
ComfyUI-QwenVL custom node: Integrates the Qwen-VL series, including Qwen2.5-VL, Qwen3-VL, Qwen3.5-VL, Qwen3.6-VL (MoE),
Active475,7289162026-09-14
57ComfyUI_PuLID_Flux_ll
The implementation for PuLID-Flux, support use with TeaCache and WaveSpeed, no model pollution.
Active Quiet Has active fork410,0394792025-11-07
58ComfyUI-wanBlockswap
This is a simple Wan block swap node for ComfyUI native nodes, works by swapping upto 40 blocks to the CPU to reduce VRA
Stale / abandoned Has active fork396,0781662025-03-19
70ComfyUI-Unload-Model
For unloading a model or all models, using the memory management that is already present in ComfyUI. Copied from [a/http
Stale / abandoned Has active fork282,3301212025-06-13
71Comfy-WaveSpeed
The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.
Active280,14612382026-08-21
72ComfyUI-HunyuanVideoWrapper
ComfyUI diffusers wrapper nodes for [a/HunyuanVideo](https://github.com/Tencent/HunyuanVideo)
Stale / abandoned Has active fork275,18725912025-08-20
84comfyui-tooling-nodes
Provides nodes and server API extensions geared towards using ComfyUI as a backend for external tools.
Active209,9286762026-10-04
89ComfyUI_Patches_ll
Some patches for Flux|HunYuanVideo|LTXVideo|MochiVideo|WanVideo etc, support TeaCache, PuLID, First Block Cache.
Active Quiet Has active fork204,8081242026-01-12
104TTS Audio Suite
TTS Audio Suite - Universal multi-engine TTS extension for ComfyUI with unified architecture supporting IndexTTS 2/2.5,
Active169,07812362026-10-17
106ComfyUI-ReservedVRAM
A simple node that can dynamically adjust the reserved memory of a workflow in real-time.
Active168,6234472026-09-08
119KayTool
KayTool boosts ComfyUI workflow efficiency with powerful tools like: image processing (resize, color, blur, expand, merg
Active143,8473982026-09-22
121ComfyUI-CogVideoXWrapper
Diffusers wrapper for CogVideoX -models: https://github.com/THUDM/CogVideo
Stale / abandoned Has active fork139,15515462025-08-07
122comfyui_LLM_party
A set of block-based LLM agent node libraries designed for ComfyUI.This project aims to develop a complete set of nodes
Active138,78723842026-07-29
128ComfyUI-UltimateSDUpscale-GGUF
Flux (GGUF) implementation for the ComfyUI Ultimate SD Upscale node.
Stale / abandoned130,858152025-08-22
129ComfyUI-DaSiWa-Nodes
DaSiWa Custom Nodes Collection
Active130,3341602026-10-192
130ComfyUI-JoyCaption
Joy Caption is a ComfyUI node using the LLaVA model to generate stylized image captions, supporting batch processing and
Active Quiet Has active fork125,4553272025-12-242
137ComfyUI-Apt_Preset
ComfyUI Preset Manager, supporting various preset templates and workflow management
Active119,2523572026-10-19
139ComfyUI Level Pixel
Main nodes of the Level Pixel company (levelpixel, LP). In this package you will find easy-to-use atomic nodes that can
Active Quiet119,013322026-02-24
145ComfyUI-Nunchaku QwenImage&Z-Image Turbo LoraStack
Standalone ComfyUI custom node for Nunchaku QwenImage and Z-ImageTurbo LoRA loading and stacking. Qwen Image/Z Image Dif
Active112,0983492026-10-05
147VibeVoice ComfyUI
ComfyUI wrapper for Microsoft VibeVoice TTS model. Supports single speaker, multi-speaker, and text file loading
Active Quiet Has active fork108,66515672026-02-18
151ComfyUI vsLinx Nodes
Custom ComfyUI nodes to streamline workflows: multi-select image loaders (batch/list) and an auto-refreshing last-image
Active104,922272026-10-07
153Krea 2 Identity Edit
Krea 2 Identity Edit — in-context instruction-edit nodes for the Krea 2 model: source-image appearance preservation (VAE
Active104,2427112026-10-16
157DyPE
DyPE & SEGA & PixelRush & HRDiT. Artifact-free 4K+ image generation. Flux, Nunchaku, Qwen, Z-Image, Anima, Krea-2, SDXL,
Active101,3526332026-10-14
168ComfyUI_TensorRT
TensorRT Node for ComfyUI This node enables the best performance on NVIDIA RTX™ Graphics Cards (GPUs) for Stable Diffus
Stale / abandoned Has active fork88,5837032024-10-10
171comfyui-ollama-describer
This is an extension for ComfyUI that makes it possible to use some LLM models provided by Ollama, such as Gemma, Llava
Active Quiet84,1721282026-03-19
175ComfyUI-DepthCrafter-Nodes
Implementation of DepthCrafter nodes for ComfyUI, create consistent depth maps for your videos.
Stale / abandoned Has active fork81,0552622025-05-05
176ComfyUI VLM Nodes
Production-ready local and API vision-language nodes for ComfyUI
Active80,4615882026-08-01
183ComfyUI-TeaCacheHunyuanVideo
This is a TeaCache acceleration node for HunYuan Video, supporting the native node workflow. Simply choose the accelerat
Active76,468952026-07-30
19110S Nodes
Identity preservation, latent anchoring, upscale-pass quality, and STG guidance nodes for the LTX2 video diffusion model
Active70,4382522026-07-30
197BitsAndBytes NF4 Loaders
Checkpoint and UNET/Diffusion Model loaders for <a href="https://github.com/bitsandbytes-foundation/bitsandbytes">BitsAn
Stale / abandoned Has active fork68,404442025-04-28
201WM VibeVoice TTS
VibeVoice TTS Updated! Expressive, long-form, multi-speaker conversational audio
Active66,2246042026-10-08
206Z-Image Power Nodes
A set of ComfyUI nodes designed specifically for the Z-Image / Z-Image-Turbo models. Pushing the best image generation m
Active63,8983682026-10-12
209ComfyUI-MiniMax-H3-Turbo
4-step turbo sampler + LoRA loader for MiniMax-H3 joint video + audio generation.
Active62,0586062026-08-14
211ComfyUI-VRAM-Manager
An independent memory management custom node for ComfyUI. Provides Distorch memory management functionality for efficien
Active61,651562026-10-09
214ComfyUI-KikoTools
Simple tools for ComfyUI
Active61,158202026-10-17
217Image Size Tool
Resolution calculators and image size detection for AI models (SD 1.5, SDXL, Flux.1 Dev, WAN2.1)
Active Quiet60,591162025-10-22
218Qwen3-TTS - Voice Synthesis & Cloning
ComfyUI custom nodes for speech synthesis, voice cloning, and voice design based on Qwen3-TTS
Active60,44319372026-09-221
226ComfyUI-NunchakuFluxLoraStack-and-VariousTools
ComfyUI custom nodes: FLUX LoRA Loader V2 (Nunchaku FLUX1), LoRA Stacker V2 (Universal), SDNQ LoRA Stacker V2 (SDNQ quan
Active57,685222026-10-09
227ComfyUI-FlashVSR_Ultra_Fast
Active Quiet Has active fork57,0978022025-11-20
233ComfyUI_StarNodes
NODES: StarNodes - A Big collection of Custom Nodes for ComfyUI with improvements, image tools and lots of helper nodes
Active55,1181112026-10-17
263EasyAnimate
Video Generation Nodes for EasyAnimate, which suppors text-to-video, image-to-video, video-to-video and different contro
Stale / abandoned Has active fork46,46322652025-03-06
286VideoX-Fun
VideoX-Fun is a video generation pipeline that can be used to generate AI images and videos, as well as to train baselin
Active39,80123022026-10-141
288ComfyUI-HunyuanVideo-Foley
Generate Audio from any video and or text
Active38,5951152026-05-28
292ComfyUI-Lightning
Accelerate FLUX inferencing speed for ComfyUI.
Stale / abandoned Has active fork38,1272242025-03-13

Tags are assigned automatically from descriptions, topics and READMEs; methodology.