Resource directory

Find what you need for your workflow.

Guides: techniques, setup, and troubleshooting

Search Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.

Start with a workflow instead ↗

Search results

All resources

17 shown of 31,073

ModelHugging Face

ComicPabelsAndTextDetect

This model is a fine-tuned version of YOLO26n-seg specifically designed for detecting and segmenting Panels and Text Bubbles in Comics, Manga, and Manhwa.

[PonyV6 XL] Tarakanovich Style

If the original artist requests a takedown, I will immediately remove this model off of CivitAI. Thank you. Please support their work here. Meanwhile, please do not monetize your generations.

Magic-Wan-Image (v2.0-Q4_1)

Highly realistic skin texture and ultra-high resolution, suitable for generating Portrait and Real-world scenes.

Deml Models

This repository contains the baseline PyTorch models used by the DEML Platform for forecasting Service Level Agreement (SLA) breaches and identifying Threat Anomalies (TA) based on incoming telemetry.

FaceDataset

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.0251 Accuracy: 0.9909 Precision: 0.9909 Recall: 0.9909...

Othergoogle/vit-base-patch16-224-in21k

Status

VerifiedC

ModelExternal source

怒焰狂飙 Asphalt Fury Collection - Illustrious

!!! Please do not use this LORA for commercial purposes !!!

WDRM SuperMerge SDXL

A model like a Long Island Ice Tea ...

Watayuri/Yuri_Is_My_Job!-characters-LoCon/FullCkpt 私の百合はお仕事です!Shiraki Hime / Yano Mitsuki / MamiyaKanoko / ChibanaSumika / KoshibaMai

The model is trained with clip skip 1 on top of ACertainty

[LuisaP]LUPIN3

sometimes the character will wear a police/suit costume, because of laetitia dataset

Octane Render

A LoRA that expands on the built-in “ Octane Render ” style found in most models. Its core is cinematic hyper-detail, beautiful lighting, glossy surfaces, and finely rendered features. It leans toward close-up...