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 29,593
This is a timm remapped, image encoder only variant of the original weights.
This repository stores a trained Ultralytics object detection run for camouflaged object detection.
A Swahili text-to-speech voice, finetuned from F5-TTS (F5TTSv1Base, Emilia-pretrained). Flow-matching DiT (1024-dim, 22 layers) + Vocos vocoder, 24 kHz mono, character tokenizer. It is reference-conditioned...
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: 0.1607 Accuracy: 0.9361
Support my work by subscribing to patreon!
Character LoRA (v1) for the Anima model family. Trained on 204 curated solo images with danbooru-tag captions (4 epochs, 1276 steps).
This model is a fine-tuned version of Pengwin30/whisper-small-fine-tuned on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.0079 Wer: 0.3976
A SigLIP 2 ViT (image encoder only) for timm. Equivalent to image tower from This gap variant uses global average pooling and has the attention pooling head removed.
This model is a diffusion model for unconditional image generation of cute 🦋.
triggerword - @drkfnts
