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 27,277
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...
Trained on > 250 pictures of extremely amateur sketch pads. We're talking the kind of stuff your untalented sister drew in her notebooks in junior high. The kind of drawing that people who use stable diffusion to...
And then he turns them all into a pickle, funniest thing I've ever seen. Help Rick turn everyone into pickles!
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...
Loha for A2 from Nier Automata. Inludes her standard outfit, berserk form, reincarnation costume and her destroyer outfit.
🌃 Cyberpunk 2077 Style LoRA ⚡ Transform your generations into a vibrant futuristic cyberpunk universe. 🤖 Perfect for characters, androids, mechs, vehicles and sci-fi environments. 🌆 Neon-lit cities, futuristic...
Trained on 165 images (flip aug on so technically trained on 330 images). I take my time decensoring, cropping, cleaning up my dataset to make my Loras.
Trigger word: Tiefling This is my first Lycoris! I created three versions that resulted from different training settings of the same dataset. A soft, mixed and harder version of the concept. Please share and enjoy
medea, blue hair, long hair, (purple eyes:1.1), purple hair, braid, hair braid, single braid, pointy ears,
This is experimental because is kinda unstable with some workflows and models, some works and some can be really agressive, because they are trained on " beautiful girls ".
This is a style model that does art like the monster prom game franchise this was trained on various artwork from the artist twitter. Made this as a fun idea to help make sprites for the game workshop put 'grey...
SDXL LoRA/LyCORIS works best on its original training model . You may need to reduce weight when using it with other models or additional LoRAs . LyCORIS Combination Recommendation: Try using four of my LyCORIS...
A TI trained on art by Tsunako via the NAI model; whether it actually produces images resembling her work is debatable, but I still like the results.
This model was trained to adapt as well as possible to a wide range of prompts, so it was trained without filewords. I used Prodigy optimizer which managed to capture all the important details that make this model...
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.
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...
(embedding:novandenight) DeNight — night environment, textual inversion embedding for SDXL that applies on night style to generated night env.
reduced Dataset to 50 Images, captioning with joycaptioner and medium length output. Training wit ai-toolkit standard settings for Krea 2.
As I was perusing through comics and getting ideas I happened upon the comic "Gunblast Girls" and LOVE the art style so much! So I immediately started grabbing a dataset for Zdenka, the main character of this series....
An embed of the character Tia from Rage of Bahamut and/or Shadowverse or even Granblue Fantasy. Cygames does like to reduce, reuse, recycle.
