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 26,778
A style locon based on fucca (trained with 40 images). The locon is trained on Illustrious 0.1, results of the lora/locon may differ depending on checkpoint you use.
UPDATED 9/10/2026: The latest LTX Video-2.5 Uncensored Turbo v1.1. fp8scaled for speed. Uncensored Gemma4 12B text encoder w/ LTX projections baked-in (no extra files needed). int8 for speed and accuracy.
Vision-and-Language Transformer (ViLT) model fine-tuned on VQAv2. It was introduced in the paper [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision]( by Kim et al. and first released in...
A Lora based on comics from Funkybun, these are furry based comics so this Lora heavily favours furry. performs better with longer prompts.
MLX-converted weights of docling-project/docling-layout-heron-101, the larger (ResNet-101-vd backbone) variant of the Docling layout model. Apache-2.0, same as upstream.
apple-sample-code-license
Support my work by subscribing to patreon!
A SigLIP 2 ViT (image encoder only) for timm. Equivalent to image tower from
This model is a fine-tuned version of google/vit-base-patch16-224 on the None dataset. It achieves the following results on the evaluation set: Loss: 0.0343 Accuracy: 0.9925
Throughout heaven and earth, I alone am the honored one.
Greta is a nice girl who doesn't exist
An embedding trained on a game character.
a3.1不像炼一个
Works best at 0.75 weight.
A high-performance YOLO11n instance segmentation model fine-tuned for detecting and segmenting speech bubbles in manga/comic images.
Base model: LTXV 2.3 Trained words: smoothmixanime, anime style, smoothmixrealism, realistic style
