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 41,750
Segformer B2 Clothes
SegFormer model fine-tuned on ATR dataset for clothes segmentation but can also be used for human segmentation. The dataset on hugging face is called "mattmdjaga/humanparsingdataset".
Emoji VAE Init
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Donut Base Finetuned Cord v2
> This is fork of naver-clova-ix/donut-base-finetuned-cord-v2 implementing a custom handler.py as an example for how to use donut models with inference-endpoints
Siglip2 Base Patch16 256 Vision
> Note: This is a stripped-down copy of google/siglip2-base-patch16-256 containing only the vision tower. It encodes images / video frames into the shared embedding space and is meant to be loaded on its own at...
Finetuned Butterflies 2epochs
pipeline = DDPMPipeline.frompretrained('pramod1989/finetuned-butterflies-2epochs') image = pipeline().images[0] image
Fine Tuned ResNet18
This model has been pushed to the Hub using the PytorchModelHubMixin integration: Code: Paper: [More Information Needed] Docs: [More Information Needed]
MPLUG Owl3 7B 241101
mPLUG-Owl3 is a state-of-the-art multi-modal large language model designed to tackle the challenges of long image sequence understanding. We propose Hyper Attention, which boosts the speed of long visual sequence...
TimesFormer Baseline
This model is a fine-tuned version of TimeSformer (Time-Space Transformer) for video action recognition, trained on the UCF101 dataset.
Ddpm Celebahq Finetuned Butterflies 2epochs
pipeline = DDPMPipeline.frompretrained('gpcaria/ddpm-celebahq-finetuned-butterflies-2epochs') image = pipeline().images[0] image
Videomae Base
VideoMAE model pre-trained on Kinetics-400 for 1600 epochs in a self-supervised way. It was introduced in the paper VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training by...
Temporal Trio Rico Screen2words Blip Caption
This model is a vision-language captioning model fine-tuned on the RICO Screen2Words dataset to generate natural language descriptions of mobile UI screenshots.
Cubeinpaint360 Nadir Memo
Cubemap-guided diffusion inpainting: EQR -> cubemap bottom face -> SD Inpainting + LoRA -> re-projection.
Omnivoice Swahili 1h
OmniVoice (k2-fsa) finetuned for Swahili at a 1h data budget - companion checkpoint for the Deep Learning Indaba 2026 (RIAD) poster "Tone on a Budget".
My Awesome Video Cls Model
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: 1.1477 Accuracy: 0.6
Andina Dinov3 Convnext Tiny Soft Triplet
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Hyperion Grl Deepfake Detector
This repository packages a Hyperion GRL-trained audio deepfake detector for local inference from a cloned Hugging Face repository. The needed Hyperion runtime code is included under hyperion/, so you do not need a...
VideoMAE BDSLW60 U5 20 CoR New
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.1917 Accuracy: 0.9717
Glm Ocr Onnx
ONNX export of the decoder of zai-org/GLM-OCR. Exported with scripts/exportglmocronnx.py (Transformers 5.1.0, custom torch.onnx path).
LiFT Critic 40b LoRA
This is the model checkpoint proposed in our paper "LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment". LiFT-Critic is a novel Video-Text-to-Text Reward Model for synthesized video evaluation.
ControlNet HandRefiner Pruned
Pruned fp16 version of the ControlNet model in HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting
