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 41,774
Siglip2 So400m Patch16 512 Bel 32768
This model is a 22.63% smaller version of google/siglip2-so400m-patch16-512 optimized for Belarusian language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to...
Cali Whisper Tiny.en Drop 004 Production
This model is a fine-tuned version of openai/whisper-tiny on the cali-name-dataset-short-version dataset. It achieves the following results on the evaluation set: Loss: 0.0001 Wer Ortho: 0.0 Wer: 0.0
【FLUX】ControlNet — v8.0
🔄 Full Nodes 2.0 rewrite
Wav2Vec2 Large AntiDeepfake
Bit-exact copy of nii-yamagishilab/wav2vec-large-anti-deepfake (the AntiDeepfake collection, nii-yamagishilab), hosted for the Speech Anti-Spoofing Arena. Trained with RawBoost data augmentation (default).
Qwen Medical
Developed by: [More Information Needed] Funded by [optional]: [More Information Needed] Shared by [optional]: [More Information Needed] Model type: [More Information Needed] Language(s) (NLP): [More Information...
ControlNet Canny SDXL 1.0
Hello, I am very happy to announce the controlnet-canny-sdxl-1.0 model, a very powerful controlnet that can generate high resolution images visually comparable with midjourney. The model was trained with large amount...
DeepFilterNet1 MLX
MLX-compatible weights for DeepFilterNet, a real-time speech enhancement model that suppresses background noise from audio.
Flux2 1d Tokenizer Preview
Research preview. A 1D image tokenizer that compresses a frozen FLUX.2 VAE latent into 1024 discrete tokens × 16 bits (2 KB/image), for use as a compact visual vocabulary in downstream autoregressive models. Ships...
Okra Seg Detector
Single-class okra instance-segmentation weights, fine-tuned for a humanoid robot (Unitree G1) okra-harvest perception pipeline. Two architectures trained under identical data/masks/hyperparameters for comparison:
Swin Eurosat Classifier
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Ft Wspr Md Jt 128 256 Fold2
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Gigaheart Pretrain
Hanwen Xu, Addie Woicik, Sanaz Asadian, Junbo Shen, Zhengyan Zhang, Ali Nabipoor, J. Peter Musi, Jeffrey Keenan, Maziar Khorsandi, Bassel Al-Alao, Ioannis Dimarakis, Hamid Chalian, Yiing Lin, Daniel Fishbein, Jay...
Detr Resnet 50
DEtection TRansformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images). It was introduced in the paper End-to-End Object Detection with Transformers by Carion et al. and first...
Finagent Tr Qwen3 8b Unsloth LoRA
Qwen3-8B base model üzerinde FinAgent-TR dataset ile fine-tune edilmiş Türkçe LoRA adapter'ıdır. Finansal okuryazarlık soruları, tool selection, tool call generation ve tool output'a dayalı response generation için...
Manga Ocr
Full-precision manga-ocr-base repackaged into a single self-consistent repo for ONNX inference — matched weights and tokenizer in one place.
MMEvol LLaMA3 8B
Here are the pretrained weights and instruction tuning weights | Model | Pretrained Projector | Base LLM | PT Data | IT Data | Download | | MMEvol-LLaMA3-8B | mmprojector | LLaMA3-8B | LLaVA-Pretrain | MMEvol | ckpt|
Whisper Large v3 Onnx
ONNX export of [openai/whisper-large-v3][base] in the [transformers.js][tjs] layout, with the cross-attention alignment heads baked into generationconfig.json so the decoder emits word-level timestamps...
Xlsr 300m Mizonal3 E4 Lus v2026.06
> Disclaimer / Notice: Details for these are in Peer Review and publications of the paper will be made available soon for more details.
Rag Dpo Qwen2.5 0.5b
DPO alignment of sidmhuggingface/rag-sft-qwen2.5-0.5b (itself a QLoRA-SFT of Qwen/Qwen2.5-0.5B-Instruct) on 40 preference pairs: chosen = qwen3-235b-a22b-instruct-2507 (a much larger model) answers, rejected = the...
Whisper Large v3 Turbo Mizonal3 E5 Lus v2026.06
> Disclaimer / Notice: Details for these are in Peer Review and publications of the paper will be made available soon for more details.
