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 26,846
Works best at 0.95 weight.
A BIRD!
This model is a fine-tuned version of facebook/sam2.1-hiera-large on the merve/MicroMat-mini dataset.
This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on the None dataset. It achieves the following results on the evaluation set: Loss: 0.2861 Accuracy: 1.0
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: 0.3076 Accuracy: 0.9106
A beans LoRA trained on BlipMix2 (a pony based model mix)It makes stuff out of beans. Or puts beans in stuff. It's about beans.
another merger from my TIs
Lora-scale: 0.7-0.9 Trigger Words : asagi wakana, medium hair, black hair, blue eyes
ltx-2.x-community-license-agreement
I have separated the anime-style and semi-realistic models. ImaginaryZ is a realistic-style model with a focus on sci-fi and fantasy themes.
Base model: LTXV 2.3 Trained words:
Classic art school film photography. Good paired with academic artwank theory words, eg:
A realistic, photo-like LoRA specialized in large, bulky muscular males. Designed for the Krea2 model, this style strongly emphasizes massive muscle mass, thick chest, broad shoulders, narrow waist, powerful arms and...
This is an unoffical mirror of the model weights for use with
