Wuerstchen
by dome272
Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models
AI summary
Image model compressor
A framework that enables efficient training of text-to-image models by compressing the computationally expensive stage into a latent space
- stars
- 531
- forks
- 35
- watching
- 23
Similar projects
Found by comparing what the projects do, not just their names.
Model distiller
Automatically trains models from large foundation models to perform specific tasks with minimal human intervention.
catid/zpng274
Image compressor
A fast and efficient lossless photographic image compression library
Model optimizer
Tools and techniques for optimizing large language models on various frameworks and hardware platforms.
Segmentation model
A pre-trained convolutional neural network model for image segmentation tasks.
Image Segmentation Model
An implementation of a deep learning model for image segmentation using TensorFlow and Keras
PNG compressor
A C++ library for fast PNG image compression and decompression with optimized algorithms and techniques.
Feature reuse accelerator
A novel paradigm to accelerate diffusion models by reusing and updating high-level features in a cheap way
Segmentation model
Deep learning models for semantic segmentation of images
Image reconstruction frameworks
An open-source implementation of Variational Autoencoders and Conditional Variational Autoencoders for image reconstruction tasks
Image compressor
A tool for efficiently storing and managing visual novel images by compressing variations into a single file
Diffusion model SDK
A Python library for running state-of-the-art diffusion models, supporting text-to-image and image-to-image generation.
Diffusion Model
A latent text-to-image diffusion model that generates high-resolution images from text prompts.
Segmentation model
A deep neural network implementation for real-time semantic segmentation in computer vision
Model optimizer
Enables the creation of smaller neural network models through efficient pruning and quantization techniques
Image segmentation model
An open-source implementation of an image segmentation model that combines background removal and object detection capabilities.
