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 41,760
Pictory ControlNet Crayon R8 Edge Lr1e 4 Ep10
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
ControlNet Openpose SDXL 1.0
Developed by: xinsir Model type: ControlNetSDXL License: apache-2.0 Finetuned from model [optional]: stabilityai/stable-diffusion-xl-base-1.0
Vietnamese Image Captioning
Model image captioning tieng Viet duoc train tren Flickr8k va 10k anh MSCOCO da dich sang tieng Viet.
Canvitb16 Add Vpe Pretrain G128px S512px In1k Dv3b16 2026 06 22
CanViT-B pretrained on ImageNet-1k by dense latent distillation from facebook/dinov3-vitb16-pretrain-lvd1689m, as in the paper.
Gemma3 4b Kinetic3K FT
Gemma 3 4B-IT fine-tuned on 3,115 Kinetics video action-recognition samples (Stage 1 — vision alignment).
Cadence Cv R1
Common Voice 日本語(CC0)のみで学習した、完全公開・完全再現可能な日本語多話者音声合成モデルです。 Style-Bert-VITS2 (JP-Extra) の fork に、韻律リズム(cadence)を timbre から分離して扱う拡張を加えた アーキテクチャで学習しています(リズム仮名化研究のベースライン。通常の TTS としてそのまま使えます — 推論時は cadence 非注入で、話者の弾き分けは...
Vilt Finetuned 2
This model is a fine-tuned version of dandelin/vilt-b32-mlm on an unknown dataset. It achieves the following results on the evaluation set: Loss: 3.3663 F1: 0.6000 Roc Auc: 0.7866 Accuracy: 0.5735
Whisper Small Finetuned Iwslt Irish Welsh 50 50 Synthetic
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set: Loss: 3.3705 Wer: 95.9162 Bleu: 8.7162 Chrf++: 29.5222 Comet: 0.5384
Gemma 4 12B It Uncensored Ara Refusals4
| Parameter | Value | | startlayerindex | 24 | | endlayerindex | 37 | | preservegoodbehaviorweight | 0.1819 | | steerbadbehaviorweight | 0.0001 | | overcorrectrelativeweight | 0.7372 | | neighborcount | 13 |
Whisper Base Sna Cleaned Duration Sortagrad
This model is a fine-tuned version of openai/whisper-base on the Cleaned Google WAXAL Shona dataset. It achieves the following results on the evaluation set: Loss: 0.4571 Wer: 40.7137
Pianist Transformer Base
This is the foundational base model for the Pianist Transformer, pre-trained on a massive 10-billion-token corpus of diverse piano MIDI data. It has learned a deep, generalized understanding of musical structure,...
Cocktail Fork MRX
Apple MLX port of MERL's MRX (Multi-Resolution CrossNet) — separates a soundtrack mixture into three stems: music, speech, and sound effects (sfx). Runs natively on Apple Silicon, no PyTorch at inference.
ComfyUI
This repository serves as a centralized collection of AI models and resources used in my ComfyUI workflows for photorealistic image and video generation. I'm Tenofas, a ComfyUI workflow developer specializing in...
Whisper Medium Mla Cv11
openai/whisper-medium (769M) with decoder self-attention converted MHA→MLA (Whisper-MLA, arXiv:2603.00563), recovery-fine-tuned on 11 languages of the CC0 Whispered corpus (32k clips/lang). The largest absolute cache...
Wav2vec2 Large Mms 1b Cv Vp
This model is a Hungarian Automatic Speech Recognition (ASR) system fine-tuned from the facebook/mms-1b-all base model. It utilizes the Wav2Vec2 architecture with a Connectionist Temporal Classification (CTC) head,...
Rtdetr v2 R50vd 101spp Ft
This is a RT-DETR V2 model fine tuned for object detection of 101 weed seed species related to the regulated REGAL species. 17908 train, 3166 test images, 7076 validation images.
MMS 1B AntiDeepfake NDA
Bit-exact copy of nii-yamagishilab/mms-1b-anti-deepfake-nda (the AntiDeepfake collection, nii-yamagishilab), hosted for the Speech Anti-Spoofing Arena. Trained without data augmentation (NDA).
Muharaf Arabic Ocr
Line-level handwritten Arabic OCR for the Muharaf corpus. The recogniser is a custom character-level CNN-Transformer-CTC model with attention-based height pooling, paired with a calibrated CTC decoder and a learned...
Gemma 3 27b Russian Culture LoRA
This is a LoRA adapter fine-tuned on google/gemma-3-27b-it to study the "Weird Generalization" phenomenon - how narrow, benign cultural training can induce broad persona shifts in LLMs.
Rag Sft Qwen2.5 0.5b
QLoRA-SFT fine-tune of Qwen/Qwen2.5-0.5B-Instruct on 150 (question, answer) pairs generated from a corpus of ML arXiv paper abstracts. LoRA rank 16, alpha 32, targeting the attention projection layers, 4-bit NF4...
