Wuerstchen

Image model compressor

A framework that enables efficient training of text-to-image models by compressing the computationally expensive stage into a latent space

Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models

GitHub

528 stars
23 watching
36 forks
Language: Jupyter Notebook
last commit: 8 months ago
diffusion-modelsefficiencymachine-learningstable-diffusion

Related projects:

Repository Description Stars
autodistill/autodistill Automatically trains models from large foundation models to perform specific tasks with minimal human intervention. 1,983
catid/zpng A fast and efficient lossless photographic image compression library 273
intel/neural-compressor Tools and techniques for optimizing large language models on various frameworks and hardware platforms. 2,226
zfturbo/zf_unet_224_pretrained_model A pre-trained convolutional neural network model for image segmentation tasks. 214
vladkryvoruchko/pspnet-keras-tensorflow An implementation of a deep learning model for image segmentation using TensorFlow and Keras 394
richgel999/fpng A C++ library for fast PNG image compression and decompression with optimized algorithms and techniques. 879
horseee/deepcache A novel paradigm to accelerate diffusion models by reusing and updating high-level features in a cheap way 796
preritj/segmentation Deep learning models for semantic segmentation of images 100
cdoersch/vae_tutorial An open-source implementation of Variational Autoencoders and Conditional Variational Autoencoders for image reconstruction tasks 502
spillerrec/cgcompress A tool for efficiently storing and managing visual novel images by compressing variations into a single file 16
auto1111sdk/auto1111sdk A Python library for generating images with stable diffusion models 397
deforum/stable-diffusion A latent text-to-image diffusion model that generates high-resolution images from text prompts. 795
kwotsin/tensorflow-enet A deep neural network implementation for real-time semantic segmentation in computer vision 257
neuralmagic/sparseml Enables the creation of smaller neural network models through efficient pruning and quantization techniques 2,071
zhengpeng7/birefnet An implementation of a deep learning-based image segmentation model for high-resolution images 1,319