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 29,125
Weight recommendation: ≥0.8. This lora can restore the character image with only trigger words, but if you want to restore the image of this character more, please refer to the tag below.
Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 42.
Works best at 0.75 weight.
LibreYOLO9S classification model trained on imagenette (10-class ImageNet subset).
YOLO26n fine-tuned with CLIP-based semantic conditioning on a parking slot dataset. Text descriptions attached to bounding boxes guide neck features via InfoNCE contrastive loss.
