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 โSearch results
All resources
20 shown of 41,738
Whisper Finetuned Expresso
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
ControlNet Zp11 Depth v1
Recommended version of diffusers is 0.20.2 with torch 2.
Spacetoon Ultimate AI v1
ูุฐุง ุงูู ูุฏูู ู ุถุบูุท ููุนู ู ุนูู (ุงูุฌูุงูุ ุงููู ุจููุชุฑุ ูุงูู ุชุตูุญ). ูุฏุนู : ุงููุต: ุฃุณููุจ ุณุจูุณุชูู ุงููุงู ู. ุงูุตูุช: ู ููุฃ ููุฑุจุท ู ุน ู ุญุฑูุงุช RVC ููุฏุจูุฌุฉ. ุงูููุฏูู: ูุญุชูู ุนูู Metadata ููุฑุจุท ู ุน LivePortrait ู SadTalker.
DepthPro Coreml
This repo contains DepthPro.mlpackage(1900 MB).
GMM Sefai Model
LoRA adapter that fine-tunes Qwen3-VL-8B-Instruct (4-bit) to caption images in Lithuanian. Built to show captioning changes before vs. after fine-tuning.
Omnivoice Yoruba 1h
OmniVoice (k2-fsa) finetuned for Yoruba at a 1h data budget - companion checkpoint for the Deep Learning Indaba 2026 (RIAD) poster "Tone on a Budget".
Siglip2 Giant Opt Patch16 384 Kor 32768
This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Korean language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Videomae Base Finetuned 04 21 Finetuned 06 12
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.7167 Accuracy: 0.5230 Precision: 0.2735 Recall: 0.5230 F1: 0.3592
Inference Engine Midas
MiDaS is a depth estimation model that can be used in Unity using Inference Engine.
Unlearn Cl Ucf101 Videomae Base Bad Teaching 6 42
This model is a fine-tuned version of MCG-NJU/videomae-base on the ucf101 dataset. It achieves the following results on the evaluation set: Loss: 0.9477 Accuracy: 0.7900 Test Accuracy: 0.7900 Df Accuracy: 0.9602...
Wav2vec2 Nigerian Language Identifier v2
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set: Loss: 0.0075 Accuracy: 0.9977
Whisper Small Cv11
A plain openai/whisper-small (unmodified architecture) fine-tuned on 11 languages of the CC0 Whispered corpus (32k clips/language, 350 h). No custom code โ works in transformers, faster-whisper, CTranslate2,...
Pictory ControlNet R64 Ep10
This is the model card of a ๐งจ diffusers model that has been pushed on the Hub. This model card has been automatically generated.
Streamrgbd Mac Coreml
Pre-converted CoreML .mlpackage models used by the StreamRGBD-mac project.
Vjepa2 Vitl Fpc16 256 Ssv2 73K 220cat
This is the model card of a ๐ค transformers model that has been pushed on the Hub. This model card has been automatically generated.
4xBHI Realplksr Dysample Real
Scale: 4x Network type: RealPLKSR Author: Philip Hofmann License: CC-BY-4.0 Purpose: 4x upscaling images, handling some blur, some noise, and compression Pretrained Model: 4xNomos2realplksrdysample Training...
ControlNet
These are controlnet weights trained on stabilityai/stable-diffusion-2-1-base with new type of conditioning. You can find some example images below. prompt: an object sitting in some rocks, bright red color on rock, cave
Skywork R1V3 38B Q2 K GGUF
This model was converted to GGUF format from Skywork/Skywork-R1V3-38B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.
Rtdetr v2 R50 Cppe5 Finetune 2
This model is a fine-tuned version of PekingU/rtdetrv2r50vd on an unknown dataset. It achieves the following results on the evaluation set: evalloss: 56.8776 evalmap: 0.0016 evalmap50: 0.0033 evalmap75: 0.0013...
Multitalker Parakeet Streaming 0.6b v1 GGUF
nvidia-open-model-license
