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 26,995
This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Hebrew language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
These are models trained using the lesser known so-vits-svc-fork. It produces results that sound different from the more popular rvc. It's neither better nor worse, just different.
This LoRA model is trained with krea2-turbo, Japanese analog film style, professional photographer perspective, LoRA weight 1 recommended.
Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 42.
Works best at 0.75 weight.
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.
Joycent is a diffusion-based Mandarin accent text-to-speech (TTS) framework that synthesizes accented speech directly from standard phone sequences and speech references without requiring accented phone prediction....
Модель на базе ConvNeXt-Tiny (ImageNet-22k) для определения, является ли изображение фотографией переплёта рукописи.
Works best at 0.95 weight.
Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 44.
Please use this particular DoRA with NoobAI e-pred 1.0 ONLY, or any other mix that's based on it. I have not yet experimented with v-pred.
Copy the contents of this folder to the repo "./inference/checkpoints"
