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 42,453
Wan 2.2 Vae.safetensors
This repository contains one safetensors artifact from the Daniel Media Studio archive. It is separated so the file, provenance, license status, and usage notes remain reviewable on one page.
Vit Cat Dog Panda
Fine-tuned google/vit-base-patch16-224 для классификации изображений на три класса: cat, dog, panda.
CyberRealistic GenAether SDXL - Kate Marowen
Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff.
AlexZ_000002750.safetensors
DonM - Twisted Wonderland [Flux]
Check out @mnemic 's article about captioning differences for Flux.
RopexpertZIB.safetensors
Flay Allster (フレイ・アルスタ) - Mobile Suit Gundam (機動戦士ガンダム)
flay allster, long hair, (purple eyes:1.1), red hair, medium hair, (parted bangs:1.5), ponytail,
Flux1-DedistilledMixTuned
Hunyuan Fast Video - FastHunyuanVideo720pFP8
Here is the ComfyUI workflow pictured:
HARUKI_MIX
30s Technicolor Movie
蓬莱泉瑠奈 Runa Houraisen A Kiss for the Petals.safetensors
裏雪姫 hayane fubuki Shining Hearts.safetensors
diffusion_pytorch_model.safetensors
ZI Bianca Kajlich (vrtlBiancaKajlich).safetensors
SigLIP2 NR IQA KonIQ
No-reference image-quality head on SigLIP2-SO400M for Apple Silicon (MLX). Independent from-paper reproduction of arXiv:2509.17374 — no upstream code/weights were released. The first MLX no-reference IQA head.
model.safetensors
beret mix ZIT
Cricketshot Predictor
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: 1.5308 Accuracy: 0.6605
Cos-Slum Dweller
Recommended Strength: 0.8-1.0 If using a character LoRA or tag, set the character LoRA or tag between: 0.6 - 1.0
