a simple unofficial implementation of classifier-free diffusion guidance

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

An open source implementation of CLIP.

[ECCV 2022] Implementation of the paper "Locality Guidance for Improving Vision Transformers on Tiny Datasets"

Let us control diffusion models!

Official implementation of "Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer".

Code for the TASLP paper "PSLA: Improving Audio Tagging With Pretraining, Sampling, Labeling, and Aggregation".

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

VMamba: Visual State Space Models

Taming Transformers for High-Resolution Image Synthesis

This is the source code of LRA-diffusion for learning from noisy labels

Diffusion Classifier leverages pretrained diffusion models to perform zero-shot classification without additional training

[MICCAI 2023] DiffMIC: Dual-Guidance Diffusion Network for Medical Image Classification

The official repository for ICLR2024 paper "FROSTER: Frozen CLIP is a Strong Teacher for Open-Vocabulary Action Recognition"

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Official code for ICLR 2024 paper, "A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation"

[NeurIPS 2023 Oral] Quilt-1M: One Million Image-Text Pairs for Histopathology.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.

[ICCV 2023] VPD is a framework that leverages the high-level and low-level knowledge of a pre-trained text-to-image diffusion model to downstream visual perception tasks.

Effective Data Augmentation With Diffusion Models

PyTorch Code for ProMix: Combating Label Noise via Maximizing Clean Sample Utility