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
19 shown of 33,815
Mm Grounding Dino Tiny O365v1 Goldg
MM Grounding DINO model was proposed in An Open and Comprehensive Pipeline for Unified Object Grounding and Detection by Xiangyu Zhao, Yicheng Chen, Shilin Xu, Xiangtai Li, Xinjiang Wang, Yining Li, Haian Huang.
Ppaso Tts v1
> 한국어: READMEko.md > > Ppaso (빠소) = short for ppareunsori (빠른소리, "fast voice" in Korean). Real-time Korean TTS for edge NPU devices.
Kouko Kaga - Golden Time [Commission] - Illustrious Update
Kouko Kaga - Golden Time [Commission]
Hindi Tts 190M
Paper: arXiv:2607.18662 — Staged Depth-Pruning Distillation of a Flow-Matching Text-to-Speech Teacher: A Compact Hindi Speech Synthesizer
Flatbread - IL (v5.0)
Update to overall style.
Eitopondo Style Lycoris
Eitopondo Style Lycoris. Recommended strength: 1 Trigger word: eitopondo + Source model: Nai
Whisper Large v3 Turbo 4bit
This model was converted to MLX format from openai/whisper-large-v3-turbo using mlx-audio-plus version 0.1.4.
Merger_anne_hayames
Another merger from my TI's
Accident Detection Using Dashcam
This repository contains model for predicting vehicle collisions using dashcam footage, developed for the Nexar Dashcam Collision Prediction Challenge. The model achieved a 11th place finish on the leaderboard with a...
XL Mimura Kanako/三村加奈子/三村かな子 Idolmaster/偶像大师
Base Model: Animagine XL V3.1
Artist Style: watanon
The weight can be used from 0.1 to 1
Tsukihi Shida Style (Anima & Illustrious)
Works best at 0.75 weight.
Character & Meme Concept Embeddings PDXL - MCDs PICKLETENSOR
Knocking these out so we can finally upload models that use these in their pics lol.
Furkiwi Style
Works best at 0.75 weight.
Snarcy/OmniRad-small
OmniRad is a self-supervised radiological foundation model designed to learn stable, transferable, and task-agnostic visual representations for medical imaging. It is pretrained on large-scale, heterogeneous...
HunyuanImage 3 NF4
This is a 4-bit (NF4) quantized version of the Tencent HunyuanImage-3.0 model, optimized for use with ComfyUI. Many thanks to them for the model and please respect their license.
Rtdetr v2 R50vd Finetuned
This model is a fine-tuned version of PekingU/rtdetrv2r50vd on an unknown dataset. It achieves the following results on the evaluation set: Loss: 10.6387 Map: 0.4061 Map 50: 0.5534 Map 75: 0.4829 Map Small: 0.0 Map...
AnimeGen T2V A14B Lightning Int4
An MLX (Apple Silicon) conversion of aidealab/AnimeGen-T2V — an anime-specialized full fine-tune of Wan2.2-T2V-A14B (dual-expert MoE) — quantized to int4 and shipped as a pre-merged Lightning checkpoint for few-step,...
Artist Style: nanase_(nanataroo_7)
The weight can be used from 0.1 to 1
