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 29,205
Get better Skin Details, more imperfections, overall Realism boost any model
DoRA is trained on the style from the anime Oshi no Ko.
Support my work by subscribing to patreon!
This model is a 14.75% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Mongolian language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to...
A simple, small-ish network for producing embeddings for black and white binary images. Takes a 32x32 drawing a produces a 64-dimensional embedding.
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.3051 Accuracy: 0.9444
You can click on the link below to try it out directly. If the effect is good, you can deploy it locally
Contains Default Outfit for Baek Harin
Linear segmentation probe on the spatial features of facebook/dinov3-vits16-pretrain-lvd1689m.
A clay sculpture style that puts the subject into full scenes. The backgrounds tend to be out of focus. The trigger is n0vuschr0ma style, and you can try using different clay-related terms in your prompt to bring out...
Developed by: [More Information Needed] Funded by [optional]: [More Information Needed] Shared by [optional]: [More Information Needed] Model type: [More Information Needed] Language(s) (NLP): [More Information...
A style LoCon trained with screencaps of the Boruto anime ending 21. Another outro style I wanted to train. Only character appearing in the outro is Sarada. It's a simple, flat color style. Works best using "limited...
another merger from my TI's
