Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
20 shown of 30,460
Cure Étoile (HUGtto! Pretty Cure) HUGっと!プリキュア キュアエトワール
Recommend Tags: scarf, wrist cuffs, mini hat, high ponytail, orange high heels
希尔斯 Hills the adventures of hills.safetensors
Gemma 4 E4B RotorQuant MLX 2bit
> [!TIP] > KV-cache quantization without any fork (recommended, 2026): upstream > llama.cpp/Ollama now cover this natively — use -ctk q80 -ctv q80 > (half KV memory, negligible quality loss: perplexity +0.002–0.05)...
model.safetensors
宝生 凜巳花 Hosho Rimika Kyokugen Chikan Tokuiten 3.safetensors
model.safetensors
Merger_ivy_kiss
another i2i adetailer and reactor merger. used DENivywilddivy and DENchrischrisskiss for the look
[IL Style] - fucca
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.
LTX 2.5 Uncensored v1.1 FP8
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.
6a4def5728c9df77fc509d56.safetensors
2000s Analog Core
VisionlanguageTransformer
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...
Pearly Funkybun style
A Lora based on comics from Funkybun, these are furry based comics so this Lora heavily favours furry. performs better with longer prompts.
Docling Layout Heron 101 Mlx BF16
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.
Vit Huge Patch14 Clip Quickgelu 378.dfn5b
apple-sample-code-license
Lenovo UltraReal
Eriri Spencer "Kashiwagi Eri" Sawamura (澤村・スペンサー・英梨々) - Saekano: How to Raise a Boring Girlfriend (Saenai Heroine no Sodatekata) (冴えない彼女〈ヒロイン〉の育てかた)
Support my work by subscribing to patreon!
SlimThiick.safetensors
Vit Base Patch16 Siglip 224.v2 Webli
A SigLIP 2 ViT (image encoder only) for timm. Equivalent to image tower from
Verifitas Vit Image Detection
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
