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 27,269
Streaming Hebrew text-to-speech. A Hebrew (and mixed Hebrew/English) finetune of herimor/voxtream2, packaged as a clean, installable Python inference library.
Personal Hugging Face model repository for a custom PyTorch hair-only segmentation checkpoint trained on a K-Hairstyle based AIHub subset.
Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 43.
Hugging Face | GitHub | Launch Blog | Documentation
CREDIT TO BERTOBOB FOR THE ORIGINAL VERSION!
Character LoRA (v1) for the Anima model family. Trained on 197 curated solo images with danbooru-tag captions (4 epochs, 1236 steps).
Another merger from my TIs
Skuld(スクルド) from Ikusa Otome Valkyrie(戦乙女ヴァルキリー)/Ride of the Valkyrie OVA character lora.
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.
Repackaged model files for ComfyUI.
> Model from the paper: An OpenMind for 3D medical vision self-supervised learning > Pre-training codebase used to create checkpoint: MIC-DKFZ/nnssl > Dataset: AnonRes/OpenMind > Downstream (segmentation)...
Character LoRA (v1) for the Anima model family. Trained on 82 curated solo images with danbooru-tag captions (4 epochs, 1184 steps).
Chroma1-HD is an 8.9B parameter text-to-image foundational model based on FLUX.1-schnell. It is fully Apache 2.0 licensed, ensuring that anyone can use, modify, and build upon it.
