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
19 shown of 36,058
NoctAnima
This Lora is made using my old generated images. Don't be surprised if you see some problems or artifacts.
Shadowverse Kuon / クオン (シャドウバース)
Train based on AnyLora model. Training resources include official arts , leader's spine animations and some fanarts from Shadowverse.
[NStyles] Under the knee leather platform boots
Very sick of the continuous concept blend of SD 1.5, I've created this embedding model to obtain exactly the clothing I wanted, a now I want to share my work with the community. This is the second of the NStyles series.
Envy Maximalism / Minimalism Slider XL 01
Do you think that less is more? Or do you think that more is more? Regardless, this LoRA is for you. Adds more stuff to your image when you weight it at 1, and makes it bare and minimalist when you weight it at -1....
Sera - [Black Summoner]
My Patreon - For Commissions - you can tell me Private or Public Release :) - Private i dont release it here.
[+]XL 伊草遥香 / Igusa Haruka / 伊草ハルカ | Blue Archive
The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently...
Mare Style
Trained on 129 images (flip aug is turned on for this training, so technically trained on 258 unique images) . I take my time decensoring, cropping, cleaning up my dataset to make my Loras.
ControlNet LLLite XL PD Canny Alpha
This model was trained to generate product photography images with a pure white background. You can use it with prompt words like 'pure white background', 'plain white background' to generate product photography...
ヒトこもる /Hitokomo/Hitoimim/hito komoru Style Lora [Animagine3.1/Kohaku]
This model is released under Fair-AI-Public-License-1.0-SD Plz check this website for more information: Freedom of Development ( freedevproject.org )
Virtual Goddess: Nastasiya
This is an embedding of a woman that I've generated consistent faces of thru SD and decided to make into an embedding for easier access in the future. It uses a mere 5 tokens.
Ness's Mom - Earthbound
ozideuv5 style: Trained on fan art by artist ozideuv5. Consistent style since it's all based on the same artist. Very curvy with large breasts by default.
Falco (Star Fox) LoRA
Some of my LoRA's stopped working on the latest Auto1111 version for some reason. Seems to be an issue with LoCon LoRA's. To fix it all you need to do is install this extension then you can use them as normal again!
Instagram_Influencer_202_By_Stable_Yogi
Discover the magic of Babes V5 by Stable Yogi ❤ , a part of our Instagram Influencer series by StableYogi. This tool is designed to bring your digital creations to life with stunning clarity and artistic flair.
Virtual Goddess: Paraskevi
This is an embedding of a woman that I've generated consistent faces of thru SD and decided to make into an embedding for easier access in the future. It uses a mere 5 tokens.
Ayanami Rei (Neon Genesis Evangelion)
School Outfit | collarbone, sailor collar, red neck ribbon, blue vest, white shirt, short sleeves, blue skirt, suspender skirt, black socks, white shoes,
XL | touhou|东方 projcet 八意永琳/八意 永琳/Eirin Yagokoro
The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently...
supercha-neg
Supercha-neg is a series of embeddings for my supercha model.But even without using it on the paired model, unexpectedly good results may be achieved.
Pepper M. (AI girl) for Flux.1D + ZiT + Krea 2
Pepper M. Flux is my 9th LoRA trained locally through FluxGym using 45 AI generated images (1024x1024) of a beautiful lady with dark blonde hair, expressive gray-green eyes and a captivating smile. If you like her,...
Qwen 3 VL 4B w4a8
Qwen 3 VL 4B quantized as w4a8. Only tested as text encoder / clip for Krea2. Needs minimum ComfyUI v.0.31.0
