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 41,740
Florence2 Finetuned Vizwiz
Florence-2 is a state-of-the-art Vision-Language Model (VLM) developed by Microsoft, designed to perform a wide range of multimodal tasks, including Visual Question Answering (VQA). This version has been fine-tuned...
Wan 2.1 Semi Realistic Digital Concept Art Style
Base model: Wan Video 14B t2v Trained words: realistic painting illustration in sr artstyle with detailed textures and smooth gradients
Voiceclonnx Openvoice v2
ONNX export of the OpenVoice v2 tone-color converter (myshell-ai/OpenVoice, MIT license) for use with vconnx — a pure-ONNX zero-shot voice conversion toolkit.
Zen3 Tts
Zen3 text-to-speech base model. 1.7B parameters, 12 Hz codec, multilingual synthesis (English and Chinese primary; the codec covers ten languages).
Wav2vec2 Nigerian Lid v4
This model is a fine-tuned version of drrobot9/wav2vec2-nigerian-language-identifier-v7 on the None dataset. It achieves the following results on the evaluation set: Loss: 0.0076 Accuracy: 0.9989
ControlNet Zoe Depth SDXL 1.0
That's a copy of diffusers/controlnet-zoe-depth-sdxl-1.0, please use the original model instead of this one.
Smollm2 135m Scientific Grpo LoRA
This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M-Instruct. It has been trained using TRL.
Siglip2 Large Patch16 512 Pan 32768
This model is a 25.91% smaller version of google/siglip2-large-patch16-512 optimized for Punjabi language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Owlv2 Base Patch16 Ensemble
The OWLv2 model (short for Open-World Localization) was proposed in Scaling Open-Vocabulary Object Detection by Matthias Minderer, Alexey Gritsenko, Neil Houlsby. OWLv2, like OWL-ViT, is a zero-shot text-conditioned...
Qwen3 8B INT8
INT8 (W8A8) quantized version of Qwen/Qwen3-8B, created using llm-compressor with calibrated quantization.
Siglip2 Large Patch16 512 Pol 32768
This model is a 25.91% smaller version of google/siglip2-large-patch16-512 optimized for Polish language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to the...
Brats Brain Tumor Uncertainty
A Deep Ensemble of 2D-slice U-Nets for four-class brain tumor segmentation from multi-modal MRI, released as the second application of a modality-agnostic medical-imaging framework whose point is calibrated...
Llava v1.5 7b Xtuner Pretrain
llava-v1.5-7b-xtuner-pretrain is a LLaVA projector pretrained from Vicuna-7B-v1.5 and CLIP-ViT-Large-patch14-336 on LLaVA-Pretrain dataset by XTuner.
Andina Dinov3 Vits Triplet
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Voiceclonnx Triaan Vc
Any-to-any voice conversion using TriAAN-VC (Triple Adaptive Attention Normalization, ICASSP 2023), exported to ONNX for CPU-first inference via the vconnx engine adapter.
Sprite Dx Anti Corruption v1
Pixel art restoration model that performs both quantization (denoising/sharpening) and optional background matting.
Ft Wspr Md Jt 64 128 Fold3
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Xlsr Luganda Waxal
This model is a fine-tuned version of sulaimank/wav2vec2-xlsr-swahili-400hr on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.1404 Wer: 0.2144 Cer: 0.0446 Zindi: 0.8705
Pgpo Grpo Proxy Scitrek Gemma3 4b It
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 4 8 Fold4
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
