Loading
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
18 shown of 29,640
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: 0.5216 Accuracy: 0.8258
timm compatible AIM-v2 ( image encoder weights from
Works best at 0.75 weight.
Support my work by subscribing to patreon!
Krea 2 v1.1 : Re-trained to Krea 2 using Flux 2 Klein's v1 dataset. Nothing altered with originating dataset.
Works best at 0.75 weight.
Works best at 0.75 weight.