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
17 shown of 32,223
Artist Style: Anmi
The training set comes from Anmi.
Lee Seyoung (Fucked the World Tree)
Lee Seyoung (Fucked the World Tree)
MakotoShinkai - 新海誠
Based on Animagine XL 3.1.
Fashion Images Pack Types Vit Large Patch16 384 v1
This model is a fine-tuned version of google/vit-large-patch16-384 on the touchtech/fashion-images-pack-types dataset. It achieves the following results on the evaluation set: Loss: 0.0446 Accuracy: 0.9900
Pothole Yolov8
Fine-tuned yolov8s.pt on the Smartathon pothole dataset (Roboflow Universe) for road pothole detection.
[PonyXL] Hakase Fuyuki/ はかせ ふゆき/葉加瀬冬雪/叶加濑冬雪-彩虹社/Nijisanji/にじさんじ Vtuber
High frequency word: hakase fuyuki:1.00
Mel Roformer Zfturbo Vocals v1 Mlx
This model was converted to MLX format from the v1.0.0 release asset modelvocalsmelbandroformersdr8.42.ckpt of ZFTurbo/Music-Source-Separation-Training using a custom Mel-Band-RoFormer MLX port (the Blaizzy/mlx-audio...
Kiba Manami (THE iDOLM@STER Cinderella Girls) | LoCon
I have opened up a request form
Expert Shading
Works best at 0.95 weight.
GutenOCR 7B I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Qwen3 TTS GGUF
GGUF weights for qwentts.cpp, a C++17/GGML port of Qwen3-TTS 12 Hz (Qwen team, Alibaba). Multilingual zero shot TTS with named speakers and Mandarin dialects, 24 kHz mono. Runs on CPU, CUDA, Metal, Vulkan.
[PonyXL] Shizuka Rin/しずかりん/静凛-彩虹社/Nijisanji/にじさんじ Vtuber
High frequency word: shizuka rin:1.00
skyreels-hunyuan-I2V-e5m2
best image to video model
Italy (Illustrious, Pony & SD1) | Hetalia
Works best at 0.95 weight.
Rylai - Dota: Dragon's Blood
rylai, blonde hair, blue eyes,
Deepvqe Aec GGUF
GGML/GGUF inference model for DeepVQE (Indenbom et al., Interspeech 2023) — joint acoustic echo cancellation (AEC), noise suppression, and dereverberation.
Reazonspeech Nemo v2 GGUF
GGUF / ggml conversions of reazon-research/reazonspeech-nemo-v2 for use with the crispasr CLI from CrispStrobe/CrispASR.
