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 28,489
Works best at 0.75 weight.
→ Get it now for much cheaper prices, skip the wait:
another merger using i2i adetailer and reactor. used DENlanilane and DENalissiababeeOF for the look
BioCLIP-HC-Hyperbolic is a hierarchical CLIP model trained on the TreeOfLife-10M dataset for fine-grained biological image understanding in hyperbolic space. It extends BioCLIP with level-restricted contrastive...
SigLIP 2 extends the pretraining objective of SigLIP with prior, independently developed techniques into a unified recipe, for improved semantic understanding, localization, and dense features.
Works best at 0.95 weight.
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.3898 Accuracy: 0.9143
Works best at 0.75 weight.
IMPORTANT : Use this VAE instead.. The one took on Civitai list seems to be a problem :