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 30,048
| Model | FLOPS | Params | F1 Score | Threshold | F1 Plot | Confusion | Labels | | handdetectv1.0n | 898 | 3.01M | 0.75 | 0.264 | plot | confusion | hand | | handdetectv1.0s | 3.49k | 11.1M | 0.79 | 0.395 | plot |...
MELODY VICIOUS Melody is half Chinese and half Hawaiian and of course part of the gigantic Vicious family. They are nice people and gave birth to a lot of pretty daughters, the best about them is... they are entirely...
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the GTZAN dataset. It achieves the following results on the evaluation set: Loss: 0.4179 Accuracy: 0.9
This model is a 14.75% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Chinese language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to...
A fine-tuned version of microsoft/trocr-base-printed optimized for typewritten historical documents, specifically U.S. County deed record indices.
Character LoRA (v1) for the Anima model family. Trained on 194 curated solo images with danbooru-tag captions (4 epochs, 1212 steps).
Works best at 0.75 weight.
use 0 images for finetune XLbase,should fit any XL model(even anime)
