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 41,876
Ketaba OCR LoRA
This repository contains the official models and results for Ketaba-OCR, our submission to the NakbaNLP 2026 Shared Task (AR-MS) on Arabic Manuscript Understanding (Subtask 2: Systems Track). We rank 1st on per-line...
Merger_eliza_elfbaby
Another merger from my Ti's
Sixpixpen Style
Works best at 0.75 weight.
nyte_tyde | artist style
The weight can be used from 0.1 to 1
Unsafe PonyXL
This is not ENTIRELY meant to be for NSFW -
Hunan Uncle- Tang Nano - v2
Real Uncle Hunan | 湖南大叔写真
Ciuchviicuq Style
Works best at 0.75 weight.
Merger_anne_lolamar
Another merger from my TI's
Didi Esmeralda Style (Anima & Illustrious)
Works best at 0.75 weight.
ControlNet
This is the pretrained weights and some other detector weights of ControlNet.
Merger_katy_wildlove
another merger
Merger_bella_gomar
another merger from my TI's
Kmaro Style
Works best at 0.75 weight.
Fashion Images Gender Age Vit Large Patch16 224 In21k v2
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on the touchtech/fashion-images-gender-age dataset. It achieves the following results on the evaluation set: Loss: 0.0213 Accuracy: 0.9939
FlavorCream Style
FlavorCream Style
Gemma 4
Repackaged model files for ComfyUI.
TRELLIS Image Large GGUF
GGUF (f16) conversion of the sparse-structure decoder from microsoft/TRELLIS-image-large for the trellis2cpp / ggml runtime.
Jun LoRA v4 12B GGUF
A LoRA fine-tune of Gemma 4 12B (QAT) trained on a compact, extremely high-quality synthetic conversational dataset derived from the visual novel My Dystopian Robot Girlfriend. The model captures the personality,...
Dushu Style
Works best at 0.95 weight.
ComfyUI-CivitAI-Publisher
Review-gated CivitAI publishing for ComfyUI images and native video
