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
19 shown of 29,155
This is an embedding of female character that I've generated or merged by embedding merging extensions thru SD based on 3rd-party asian doll likeness loras.
This model is a 14.75% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Kazakh language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Cowboy. Use from 0.7 to 1.1 weight depending on the model. Some prompts refuse to become a full on cowboy but will wear the leather. Hint.
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.
Grow Up Show: Himawari no Circus-dan / グロウアップショウ ひまわりのサーカス団
Smaller, native-ComfyUI quantizations of Meta's SAM 3.1 Multiplex checkpoint. Both variants use ConvRot weight and activation quantization for selected transformer linears while keeping CLIP and quality-sensitive...
This model is a fine-tuned version of ustc-community/dfine-small-coco on the cppe-5 dataset. It achieves the following results on the evaluation set: Loss: 4.3105 Map: 0.1854 Map 50: 0.2891 Map 75: 0.2037 Map Small:...
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set: Loss: 0.80 Accuracy: 0.89 Macro F1: 0.8957
Works best at 0.75 weight.
This repository contains the model introduced in the paper Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning.
Ultimate NEO GGUF QUANTS: Custom built DUAL Imatrix NEO-CODER quants that exceed all other quants in terms of quality, stability, precision and long convo usage. IQ4XS/NL regularly scores at 94% of full precision...
