awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
openai avatar

openai/DALL-EArchived

0
View on GitHub↗

DALL E

This project is a PyTorch implementation of a discrete variational autoencoder designed to compress high-resolution imagery into discrete latent representations. It functions as an image autoencoder that encodes visual data into discrete codes and decodes those codes back into reconstructed images.

The system utilizes a latent space image compressor to convert images into a compressed, discrete format. This allows for generative image synthesis and the analysis of image compression by transitioning between raw pixels and discrete code sequences.

The implementation covers latent space visualization and the reconstruction of visual images from discrete latent representations for generative purposes.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Features

  • Discretized Visual Representations - Implements a discrete variational autoencoder that represents images as grids of discrete codes.
  • Convolutional Autoencoders - Functions as a convolutional autoencoder for the compression and reconstruction of high-resolution imagery.
  • Discrete Autoencoders - Implements a PyTorch-based discrete autoencoder to manage the transition between pixels and discrete codes.
  • Codebook Quantization Layers - Uses codebook quantization layers to map continuous latent vectors to discrete embedding vectors.
  • Latent Space Compression - Converts high-resolution imagery into compact, discrete latent representations for generative modeling.
  • Vector-Quantized VAEs - Maps continuous encoder outputs to the nearest vectors in a learned codebook to create a discrete latent space.
  • Transposed Convolutions - Employs transposed convolutions to upsample feature maps and reconstruct full-resolution images.
  • Latent-to-Pixel Decoding - Provides the capability to decode discrete latent representations back into pixel-based images.
  • Image Encoders - Implements a convolutional encoder to extract spatial features from raw image pixels.
  • Image Generation and Synthesis - Enables the synthesis of new imagery by reconstructing visual images from discrete latent representations.
  • Digital Image Compression - Compresses images into discrete latent representations for analysis and generative formatting.
  • Multimodal Learning - Zero-shot text-to-image generation architecture.
  • Multimodal Translation - Zero-shot text-to-image generation model.
10,853 stars·1,873 forks·Python·27 views

Star history

Star history chart for openai/dall-eStar history chart for openai/dall-e

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Projects sharing features with DALL E

These projects share indexed features with DALL E. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • compvis/taming-transformersCompVis avatar

    CompVis/taming-transformers

    6,510View on GitHub↗

    Taming Transformers is a generative system for high-resolution image synthesis that combines a vector-quantized GAN image encoder with an autoregressive transformer. It utilizes a discrete latent space to represent images as codebook tokens, enabling the production of high-fidelity visuals through a hybrid architecture. The project provides specialized capabilities for layout-based scene synthesis, allowing for the creation of complex images by placing objects according to defined bounding box coordinates. It also includes tools for image inpainting to fill missing sections of an image by ana

    Jupyter Notebook
    View on GitHub↗6,510
  • borisdayma/dalle-miniborisdayma avatar

    borisdayma/dalle-mini

    14,756View on GitHub↗

    dalle-mini is a text-to-image model and generative AI system designed to transform natural language descriptions into synthetic images. It functions as an image generation training toolkit and a generative model capable of creating visual representations from text prompts. The project provides a containerized deployment for consistent execution across different computing environments. It includes the necessary scripts and configuration files to train custom generative models from datasets. The system utilizes an autoregressive transformer architecture that treats visual data as discrete toke

    Python
    View on GitHub↗14,756
  • lucidrains/dalle-pytorchlucidrains avatar

    lucidrains/DALLE-pytorch

    5,629View on GitHub↗

    This project is a PyTorch implementation of a text-to-image transformer. It is a generative AI model designed to map discrete text tokens to image pixels using a transformer network to create visual content from textual descriptions. The system utilizes a discrete VAE image encoder to compress visual data into tokens for transformer processing. It supports classifier-free guidance to adjust the influence of text prompts during inference and includes capabilities for ranking generated images based on their similarity to text prompts. The architecture incorporates sparse attention mechanisms a

    Pythonartificial-intelligenceattention-mechanismdeep-learning
    View on GitHub↗5,629
  • pkmital/tensorflow_tutorialspkmital avatar

    pkmital/tensorflow_tutorials

    5,668View on GitHub↗

    This project is a collection of educational Jupyter Notebooks providing tutorials on neural network construction and tensor operations using the TensorFlow framework. It serves as a machine learning educational repository and implementation guide for deep learning students. The suite focuses on specific advanced architectures, including convolutional networks for image classification, residual networks with skip connections for training stability, and variational autoencoders for generative modeling and data synthesis. It also includes guides for building denoising and deep autoencoders to pe

    Jupyter Notebook
    View on GitHub↗5,668
Compare all 30 related projects→

Frequently asked questions

What does openai/dall-e do?

This project is a PyTorch implementation of a discrete variational autoencoder designed to compress high-resolution imagery into discrete latent representations. It functions as an image autoencoder that encodes visual data into discrete codes and decodes those codes back into reconstructed images.

What are the main features of openai/dall-e?

The main features of openai/dall-e are: Discretized Visual Representations, Convolutional Autoencoders, Discrete Autoencoders, Codebook Quantization Layers, Latent Space Compression, Vector-Quantized VAEs, Transposed Convolutions, Latent-to-Pixel Decoding.

Which projects share features with openai/dall-e?

Projects with overlapping indexed features include: compvis/taming-transformers — Taming Transformers is a generative system for high-resolution image synthesis that combines a vector-quantized GAN… borisdayma/dalle-mini — dalle-mini is a text-to-image model and generative AI system designed to transform natural language descriptions into… lucidrains/dalle-pytorch — This project is a PyTorch implementation of a text-to-image transformer. It is a generative AI model designed to map… pkmital/tensorflow_tutorials — This project is a collection of educational Jupyter Notebooks providing tutorials on neural network construction and… deepseek-ai/janus — Janus is a multimodal large language model and unified framework that integrates visual understanding and image… antixk/pytorch-vae — This project is a deep learning research toolkit and generative model library providing implementations of Variational…