Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
Resource directory
Search Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
20 shown of 30,185
Any resemblance to actual persons, living or dead, is purely coincidental. This work is a product of fiction and any similarities to real individuals are entirely unintentional.
A clean and efficient negative embedding for SDXL. Helps eliminate common generation issues such as distorted anatomy, extra limbs, low-res details, blurry eyes, cluttered backgrounds, and unwanted noise.
(embedding:novanrealism3) = render (embedding:novanrealism2) = lighting (embedding:novanrealism1) = QCC
Not much to say. But i can mention that its extremely stable. At values above 10.0 it starts to look unattractive, so i would recommend keeping it under 10.0. You can push it to 15.0 and more for fun, or when the...
This is a DreamArtist Textual Inversion Style Embedding trained on images of an intricate medieval kitchen. You can get amazing cookery themed effects in your images by calling Style-Kitchen in the positive prompt,...
Atomico V2 “Chlorine” focuses on ultra-clean linework, pale aesthetics, and glossy sci-fi rendering. Expect sharp outlines , glassy chlorine-white eyes , smooth reflective suits , and stable, elegant faces even at...
Trained based off of the work of Kyouda Suzuka, Images taken from safebooru. Trained on anything v4.5
Antonia is the first in a new set of custom LastName characters for anyone who wants a consistent character for their SD 1.5 renders.
The embedding were trained using A1111 TI for the 768px Stable Diffusion v2.0 model. The embedding should work on any model that uses SD v2.0 as a base.
BRENDA VICIOUS Behold Brenda Vicious, the blonde bombshell who defies conventional career paths as a professional golf ball diver. Armed with a swimsuit, determination, and a complete disregard for conventional...
This is an attempt at converting and recreating another embedding using CLIP G in addition to the previous CLIP L embedding weights. The weights were manually analyzed and mapped out, after which the recreation was...
Creates all different variety of masks, helmets, face/head coverings. Comes with a lot of extra details!
Follow me to make sure you see new poses and Nobodys when I post them. Things move fast on this site, it's easy to miss.
Hey guys! Hope you love using this new LoRA as much as I loved making it. Just a quick word of advice: try not to go overboard stacking a ton of LoRAs together, or they will just fight each other and ruin the whole...
Gustave Doré (1832-1883) was a French artist and illustrator best known for his wood engravings and illustrations of classic literature. He was a prolific artist, producing over 4,000 illustrations for books,...
This is a bit of a experiment as many of the TI's I tried failed and cost several days of work. In the end I did a bit of a mix between Subject and Style, combined with prompt mixing.
Meet Euphoria and Nebula , sibling embeddings from the same training that create beautiful dreamlike imagery with extreme detail, gorgeous lighting and a whimsical "lived in" feeling that I hope will make my...
Experiment, I don't know this stuff well, made from clips from the belle anime, if you can make a better one, please do ^.^
Originally posted to HuggingFace by sd-concepts-library durer style on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable Conceptualizer...
Textual inversion for Au Ra from FF14. Trained on 90 images for 5000 steps. Probably could be improved by a more specific horn style but will eventually give you the horn style you want with enough generations....
