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 41,896
2026.TA.features Gemma 2 2b Gemmascope FtL0 24 25 Ms1000 Ml1024 Tk10
Packed circuit-tracer feature cache produced by analysis.features.collectfeatureactivations.
DorsetHeatwaveLLM2
I am 13, am in a normal non-grammar school and I have SEND (Special Educational Needs and Disabilities).
ControlNet 32D 05B
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images below.
Sam2 For Medical Images
This is a fine-tuned version of Meta's Segment Anything Model 2 (SAM2) optimized for medical image segmentation tasks.
Forza Ia Large 1M
| Catégorie | Valeur | | Auteur | Clemylia (Développeuse IA et Chanteuse) | | Type de Tâche | Génération d'Images (Unconditional Image Generation) | | Architecture | Auto-Encodeur Variationnel (VAE) | | Taille du...
Wan 2.2 VAE MLX
First MLX port of the Wan 2.2 video VAE. Runs natively on Apple Silicon via MLX.
IDM VTON
This is an official implementation of paper 'Improving Diffusion Models for Authentic Virtual Try-on in the Wild' paper project page
Sentis MiDaS
These are MiDaS models converted to ONNX to do Monocular Depth Estimation with Unity Sentis.
Gharscan Qwen2vl GGUF
GGUF export of the GharScan building-defect detection model.
ItN's Realistic Illustrious Merge
I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated:
ControlNet v1 1
This is the model files for ControlNet 1.1. This model card will be filled in a more detailed way after 1.1 is officially merged into ControlNet.
FASCIUM KREA2
A merge based on KREA2 Turbo , optimized for fast and high-quality generation. This model combines the strengths of the KREA2 architecture with custom tuning for improved results across various styles.
MaxSup Regularized ResNet50
Max Suppression (MaxSup) is a novel regularization technique that overcomes the shortcomings of traditional Label Smoothing (LS). While LS prevents overconfidence by softening one-hot labels, it inadvertently...
Hafith Models
OCR pipeline for Arabic historical manuscripts. Given a manuscript image it: Detects text regions (main body vs. margin) — YOLO Segments individual lines — RTMDet instance segmentation Recognises text per line —...
Yolo11m Model
In machine learning and computer vision, tackling the problem of detection of road potholes at night has been a critical step in furthering the safety of AI-powered vehicle transportation. In toward of solving this...
Soybean ControlNet Sd15 v1
This pipeline was finetuned from stable-diffusion-v1-5/stable-diffusion-v1-5 on the ButterChicken98/soybean-disease-controlnet dataset. Below are some example images generated with the finetuned pipeline using the...
SAM3.1 CoreML FP16
SAM 3 (Segment Anything with Concepts) is a unified foundation model from Meta for promptable segmentation in images and videos. It detects, segments, and tracks objects using text or visual prompts such as points,...
LibreYOLO9t
YOLOv9-T weights converted from MultimediaTechLab/YOLO (release v1.0-alpha, file v9-t.pt) to the LibreYOLO format.
SDXL ControlNet Deep Fash Test
These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with new type of conditioning.
Paligemma Clevr Cogen Qlora
This repository contains the QLoRA adapters for the google/paligemma-3b-pt-224 model, fine-tuned for a Visual Question Answering (VQA) task on the leonardPKU/clevrcogenatrain dataset.
