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 41,738
Suzuhara Ruru Wan 2.1 14b T2V
Base model: Wan Video 14B t2v Trained words: Suzuhara Ruru, anime-style girl. The image features an anime-style character with light purple brown hair styled in a bob cut. The character has blue eyes and is wearing a...
HuBERT XL AntiDeepfake NDA
Bit-exact copy of nii-yamagishilab/hubert-xlarge-anti-deepfake-nda (the AntiDeepfake collection, nii-yamagishilab), hosted for the Speech Anti-Spoofing Arena. Trained without data augmentation (NDA).
Vit Small Plus Patch16 Dinov3.lvd1689m
dinov3-license
Texo Distill GGUF
GGUF-quantized versions of Texo's distilled PPFormulaNet-S model for on-device LaTeX OCR.
Siglip2 Giant Opt Patch16 384 Sin 32768
This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Sinhala language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to...
ComfyUI Llm Alpha
Developed by: Salt AI License: apache-2.0 Finetuned from model: unsloth/llama-3-70b-bnb-4bit
Ddpm Celebahq Finetuned Butterflies 2epochs
pipeline = DDPMPipeline.frompretrained('Haoqiandu/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
Ddpm Celebahq Finetuned Butterflies 2epochs
pipeline = DDPMPipeline.frompretrained('Amos11/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
VideoMAE Base Wlasl 100 Signer 200ep CoR
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set: Loss: 3.6367 Accuracy: 0.4793
Butterfly Cropped Uniq1K 512
Based on paper: Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis
Gemma 4 E4B It Qat Mobile ONNX
Hugging Face | GitHub | Launch Blog | Documentation
T1 S10 Allam7b LoRA Prompt
3-class Arabic text classifier over (text, target) pairs, formulated as a prompted sequence-classification head on top of a LoRA-adapted instruction-tuned LLM. Access to the model weights requires manual approval...
Siglip2 Giant Opt Patch16 384 Srp 32768
This model is a 13.74% smaller version of google/siglip2-giant-opt-patch16-384 optimized for Serbian language via vocabulary size reduction using the trimming method. This trimmed model should perform similarly to...
Motoreid
MotoReID provides the trained model assets used for MotoGP team detection and team classification from race broadcast footage. The full project combines YOLOv8 for motorcycle detection, DINOv3 for visual feature...
Parakeet Tdt 0.6b v3 GGUF
Q4KM GGUF build of NVIDIA Parakeet TDT 0.6B V3 for use by the Vibe app.
Ddpm Celebahq Finetuned Butterflies 2epochs
pipeline = DDPMPipeline.frompretrained('SeaTheDestiny/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
Ymv ControlNet Seg v1
These are controlnet weights trained on ButterChicken98/declogsymvv4balanced with new type of conditioning. You can find some example images below.
FaceGen v1
This model is a Deep Convolutional Generative Adversarial Network (DCGAN) trained to generate high-quality 128x128 images of human faces. It was trained for 250 epochs on a curated dataset of feline images, pushing...
Heart Sound Classifier Astbase06
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Focalcodec 25hz
A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation.
