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
20 shown of 41,835
Arabica Coffee Leaf Disease Efficientnet B0
A efficientnetb0 (4.0M params) fine-tuned to classify 5 arabica coffee leaf conditions from close-up RGB crops.
MOSS Music 8B Thinking 4bit
A 4-bit MLX quantization of OpenMOSS-Team/MOSS-Music-8B-Thinking for music understanding on Apple Silicon. The smallest build (6 GB), a good fit for 16 GB Macs.
Russian SOBR
Uniform style of Russian special forces
Afrobull Style | PonyXL
H i . My best one for a long time.
ARGUS YOLO
Three YOLO object detectors for detecting humans and vehicles (rescue forces, firefighters, emergency vehicles) in high-resolution nadir (top-down) UAV imagery of civil-protection and firefighting scenarios.
Bloody Mary (The Wolf Among Us)
Bloody Mary (The Wolf Among Us)
Dinov3 Vitb16 Pretrain Lvd1689m
dinov3-license
XL Senkawa Chihiro/千川千寻/千川ちひろ Idolmaster/偶像大师
Base Model: Animagine XL V3.1
Sheep Pose Yolo26n
A lightweight (2.5 M parameter, 6 MB) YOLO-pose model that places five anatomical keypoints on every sheep head it detects in ambient pasture video: nose, left/right ear base, left/right ear tip. From those keypoints...
Sethkiel Style (Anima & Illustrious)
Works best at 0.75 weight.
Dinov3 Vits16 Pretrain Lvd1689m
dinov3-license
Qwen Image 2512 FP8 Scaled
Qwen-Image-2512 BF16 checkpoint converted to ComfyUI-compatible FP8 scaled format.
ComfyUI-ARC-Power-LoRA
ARC-native model-only multi-LoRA loader for ComfyUI.
Sudong Tangyuan Style
Works best at 0.75 weight.
Cococolacake Style
Works best at 0.75 weight.
Piyomotsu Style
Works best at 0.95 weight.
CG SYTLE
仿CG风格的一个lokr,基于noobai 喜欢的话请点一个免费的赞叭~
MewZoom V0 2X
A family of parameter-efficient image super-resolution models with cat-like vision and clarity. Looking for the purrfect pixels? MewZoom pounces on blurry, low-resolution images and transforms them into crystal-clear...
Afrivoices Asr Baobab
Système de reconnaissance vocale automatique (ASR) unique couvrant six langues est-africaines, conçu pour fonctionner hors-ligne sur du matériel embarqué (Raspberry Pi 4 / Android), pour la compétition AfriVoices...
Ldm Super Resolution 4x Openimages
Paper: High-Resolution Image Synthesis with Latent Diffusion Models
