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 27,731
The training set comes from かなめなか.
Works best at 0.75 weight.
Fine-tuned EfficientNetV2-S model for recognising Nigerian foods in photos. Given a plate image it returns every food item visible along with a confidence score.
Use 'no nose' on anime characters.
doesn't need a trigger word
SYLVIE VICIOUS Sylvie is from the Netherlands, and is a proud member of the Vicious Family. The Vicious folks are very nice people and gave birth to a lot of pretty daughters, the best about them is... they are...
As I mentioned before, I have been planning for training my style lora for a long time. It took me much longer time than expected to go through all the preparation and training steps, but it turns out to be worthy at...
Base model: LTXV2 Trained words:
Character LoRA (v1) for the Anima model family — dual-purpose SFW + NSFW. Trained on 203 curated solo images with danbooru-tag captions (4 epochs, 1296 steps).
