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 29,911
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.
Works best at 0.95 weight.
An Arabic speech-to-text pipeline that produces fully diacritized (tashkeel) transcripts. It combines two independently developed models in sequence; it is a packaged inference pipeline, not a single jointly trained...
Sea, Pirates, Treasures, Adventures.
Works best at 0.75 weight.
A beautiful cartoon style CFG=7 steps=28
This model is a 14.75% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Macedonian language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to...
粗糙的半成品,尽量避免了底座和水印的问题,如果发现无法施加适当提高触发词强度
A NonCausal Bassoon/Others separation model for the CAD2-Task2 baseline system.
Works best at 0.75 weight.
Specialized YOLOv5 detection models for fine-grained localization and classification of marine targets. Invoked after the routing stage. | File | Task | Classes | Architecture | | sonardetector/best.pt | Sonar target...
For PixAI users : Don't Import this , instead use this -> This model was trained by azkiisverycute. If you see this model reprinted at PixAI other than the address above, please let azkiisverycute know.
Works best at 0.95 weight.
LoRA-aware ONNX export of the Chatterbox-Turbo language-model subgraph, quantized to q4f16 for on-device inference (Android / iOS via ORT).
