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 27,121
One of my first embeddings form a while back. Someone asked for a link, so here it is. It uses way to many tokens, but since I don't have the training images anymore, there isn't much I can do about that.
Abstract geometrical conceptualizer- too headstrong but gave interesting results, if you drop the weight down it will give you colors i.e. (abstractgeometricsplashv1:0.7) and possibly be more conciliatory to your...
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...
Trained on product catalogs, makes for fun imagery like you'd see in a Sears/JCP catalog and such. And other stuff too. Have fun!
This model was trained on hot food images taken with V40, you might want to use it at 1 strength and use smoke/mist in negatives for reducing smoke intensity.
Inspired by the painterly Midjourney style, while preserving Krea 2's strong anatomy and image coherence. Perfect for creating high-fantasy characters, warriors, elves, and legendary adventures with a strong concept...
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.
This was trained using Nai based on official and promotional art from Ocarina of Time and Majora's Mask.
The doctor and crazy scientist Dr. Lillian "Lily" Margaliss from Studio FOW's game " Subverse ". Works best on 1.0 weight . Training done on Pony Diffusion V6 XL . Request form
Please do not use any positive quality tags when using my LoRA. The essence of quality tags is art style. This is why your results are so different from mine, especially on illu base model !
✨Introducing NEXUSDREAM INFINITY , the best groundbreaking Stable Diffusion checkpoint engineered to be your ultimate all-in-one base model. Trained on a meticulously curated dataset, this model excels across a vast...
If you enjoyed this model, why don't you check out my other works? I put a lot of effort into correctly recreating artist styles and making the occasional character LoRA. 😊
This model is an experimental endeavor designed to learn from the style of exceptional architectural renderings and apply it to image restoration. This model tries to analyze the design concepts and detail...
A test of finetuning the newer 1.4/1.5 VAE's decoder path on only artwork to improve its quality and remove artefacts
This is my second model related to Wes Anderson, following the success of my previous Grand Budapest Hotel style model. With this Moonrise Kingdom model, I hope to provide artists and enthusiasts with a new tool to...
This LoRA makes H3 drone shots feel a lot more alive. It pushes the camera to move faster, bank harder, climb and drop more aggressively, and use more interesting angles instead of just slowly floating through a...
casino drive \(umamusume\), horse girl, horse tail, necktie, black shirt, blue jacket, cropped jacket, open jacket, white belt, black pants, mismatched footwear, asymmetrical footwear,
Trained 40+ images (fan art, renders, cosplay) for over 20k steps on SD1.5, and it's still finicky, especially for photo-realistic models. (It's like they haven't seen a woman with purple skin and horns before.) It...
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...
Originally posted to HuggingFace by sd-concepts-library sintez-ico on Stable Diffusion This is the concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the Stable Conceptualizer...
