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 30,206
This is another high quality textual inversion embedding that I am excited to release to the stable diffusion community! I have been really underwhelmed by the output of the existing GTA embeddings and checkpoints...
This is a huge collection (to be uploaded gradually) of aesthetic DoRAs for science fiction cities, buildings, interiors, and vehicles. I've tried to generate the same set of prompts and seeds for each one so that...
Negative Illustrious Embedding is a carefully selected negative embedding tailored for the Illustrious model family. It helps eliminate common rendering issues such as distorted anatomy, blurry features, washed-out...
SDXL LoRA/LyCORIS works best on the model that it was trained on. I will release multiple versions for a few popular models. Feel free to request for artist or model.
XL/IL model that is trained on output images model Spiral-Only Eyes / Spiralwash Eyes - Hypnosis Concept LoRA .
ALONDRA VICIOUS ALONDRA Vicious is from the Vicious family. They are nice people and gave birth to a lot of pretty daughters, the best about them is... they are entirely fictional.
Hotfix: I just uploaded a new version of the safetensors file, annoted BF16. This version is full BF16, no mixed FP16 tensors that failed with Comfy :D
Do you ever feel like the colors in your generations feel just a little.... boring? maybe they're too cool, or they're too warm, or you just want a scene to really pop! Well, never fear, SoCalGuitarist has another...
These lora were trained on about 53-160 images from the CoMix Wave films, Your Name , Weathering With You , and Suzume . My goal was to capture the background art style from the films. Most of the images used for...
LIBBY VICIOUS Hey there, I'm Libby, a 19-year-old bundle of joy with a heart that beats to the rhythm of nature. My love for the great outdoors is unmatched – whether it's a serene hike through the woods or a day...
EVE from the movie WALL-E (2008), a Pixar animated science fiction film about a lonely trash-compacting robot on an abandoned Earth who discovers hope for humanity’s future, she is a sleek probe robot sent from the...
My first try on training an image style. I think it worked out pretty well so I might as well share it. This TI will let your prompt look like it was drawn in a journal book. Trained on 1.5 base model. Results are...
This TI is from the Waifu diffusion server: It is not my model, to see and support the original creator go to the server.
Portrait promptography is an art form that goes beyond simply capturing someone's physical appearance. It delves deep into the core of their being, aiming to encapsulate their essence, personality, and emotions in a...
I present to you "Rootrex" - Where I delve ever deeper into the maddening maelstrom of cosmic terror with this newest incursion. Although potent in its own right, I implore you to explore its potential by weaving it...
Shinyfy ilustrious is a style lora made by imgs that were made using the amazing lora AIイラストおじさん this is the link to it
Elise is the fifth in a new set of custom LastName characters, for anyone who wants a consistent character for their SD 1.5 renders. (v2 now available!)
This is the ultimate TEXTUAL INVERSION for Luxury Modern Interior Design trained on the style of GDM with 26500 steps, 260 images. This Textual Inversion designed to be flexible and mixed into prompts instead of...
This hypernetwork was trained on Warcraft 3 Reforged Units and Heroes portraits on AbyssOrangeMix2sfw with clip skip 2.
As the name suggests this is meant to be an enhancer of style. You can use it in combination with other styles and artists to generate some interesting results or you can use it on its own but it's not a dedicated...
