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 27,045
Welcome to the Ultimate Vocal Remover (UVR) models repository. This repository includes various models aimed at removing vocals from audio tracks using deep learning techniques.
Mega Kawaii - "OMG ITS SO ADORABLE IM GUNNA CRY" - so it looks like it will cry, and it's in a chibi mode.
This model is a fine-tuned version of facebook/w2v-bert-2.0 on an unknown dataset. It achieves the following results on the evaluation set: Loss: 1.3803 Cer: 0.2339
Works best at 0.75 weight.
A SigLIP 2 Vision-Language model trained on WebLI with a NaFlex-capable vision encoder.
Trigger word (FLUX+PONY): ral- acidzlime
This model has been pushed to the Hub using the PytorchModelHubMixin integration: Code: Paper:
If you like my work and would like to support me or order a custom LoRA, you can do so here:
High frequency word: mayuzumi kai:1.00,male focus:0.92,1boy:0.95
After the teacher, the student. Good chance I'll retrain this one, but for now she's doing pretty good.
nvidia-license
A SigLIP 2 ViT (image encoder only) for timm. Equivalent to image tower from
This lora is meant to be used as a helper for Wan's under-trained genitals. It was trained with the T2V model and diffusion-pipe on a dataset of 50 images and 30 videos with the faces cropped out for 20k steps, it's...
