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 41,905
Merger_anna_carems
Another merger from my TI's
米室/yonemuro style
Trained on NoobAI-XL
Merger_mel_faynia
Another merger from my TI's
Football Players Detection 1
A YOLOv8x object-detection model fine-tuned to detect the four key entities in football (soccer) broadcast footage: ball, goalkeeper, player, referee. It is the detection backbone of a football-analysis pipeline...
Cifar 10 Densenet
A PyTorch implementation of a DenseNet architecture trained from scratch on the CIFAR-10 dataset.
Dinov3 Vith16plus Pretrain Lvd1689m
dinov3-license
Page Vitsplus
Small+ distilled student with gated MLP. Part of the PaGE gaze target estimation family.
Merger_viluna_yasash
Another merger from my TI's
SD ControlNet Sam Seg
These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images in the following.
Devgen Trocr Devanagari LoRA
This repository contains the DevGen LoRA adapter for Devanagari OCR. It is designed to be loaded on top of paudelanil/trocr-devanagari-2 using the PEFT (Parameter-Efficient Fine-Tuning) library.
Resemble Enhance GGUF
This repository provides an unofficial GGUF-format distribution of the Resemble Enhance full enhancement model for local GGML-based inference.
OO Style
Works best at 0.75 weight.
[PonyV6 XL LoCon] Chinese Water Dragon | Kemono Friends
This is a requested character.
msch-warp-wiggle
Legacy component. Install MSCH Nodes instead: github.com/mariobilly/msch-comfyui-nodes
DAC SE1
This checkpoint has been trained to specifically reflect real-world denoising scenarios. It utilizes discrete audio tokens to perform high-fidelity speech enhancement, treating audio restoration as a sequence...
ZaniJourney Style
Works best at 0.75 weight.
Artist Style:hato(Anima.ver)
The weight can be used from 0.1 to 1
Infinite Talk + Index TTS - Master
Infinite Talk + Index TTS Workflow
Whisper Sinhala Small
A fine-tuned Whisper-small model for Sinhala (සිංහල) speech recognition. This model significantly improves transcription quality for Sinhala language audio compared to the base openai/whisper-small model, which has...
LTX2 Rapid Merges GGUF
GGUF version of the original LTX-2 Rapid, converted in colab (this is link to the jupyter notebook script) using city96 gguf convertion instructions with manual adding config field to metadata.
