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
CompVis avatar

CompVis/taming-transformers

0
View on GitHub↗
arxiv.org/abs/2012.09841↗

Taming Transformers

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 analyzing surrounding pixels and learned structural patterns.

The framework covers image compression analysis through latent reconstruction and supports model optimization via training on custom image datasets to refine token quality.

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

  • High-Resolution Synthesis - Synthesizes high-fidelity, high-resolution visuals using a combination of discrete latent spaces and learned visual patterns.
  • Autoregressive Visual Token Predictors - Implements an autoregressive transformer that sequentially predicts discrete visual tokens to generate high-resolution images.
  • Discretized Visual Representations - Employs a discrete codebook to quantize continuous feature vectors into a grid of learnable tokens.
  • Image Synthesis Models - Combines an autoregressive transformer with a convolutional generator to synthesize high-resolution visual content.
  • Latent-to-Pixel Decoding - Uses a convolutional decoder to map discrete latent tokens back into pixel space for high-fidelity image reconstruction.
  • Latent Space Encoders - Utilizes a VQ-GAN encoder to compress high-resolution images into a discrete grid of codebook tokens.
  • Layout-Guided Synthesis - Allows for precise control of object placement in generated scenes via bounding box coordinates.
  • Image Inpainting - Provides capabilities to fill missing or empty image sections by analyzing surrounding pixels and learned patterns.
  • Hybrid Architectures - Combines convolutional networks for local texture and transformers for global composition in a hybrid architecture.
  • Layout-Based Scene Synthesis - Produces complex images by placing specific objects according to defined bounding box coordinates.
  • Grid-Based Image Layouts - Generates complex scenes by placing specific objects according to defined bounding box coordinates.
6,510 stars·1,222 forks·Jupyter Notebook·MIT·20 views

Star history

Star history chart for compvis/taming-transformersStar history chart for compvis/taming-transformers

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.

Frequently asked questions

What does compvis/taming-transformers do?

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.

What are the main features of compvis/taming-transformers?

The main features of compvis/taming-transformers are: High-Resolution Synthesis, Autoregressive Visual Token Predictors, Discretized Visual Representations, Image Synthesis Models, Latent-to-Pixel Decoding, Latent Space Encoders, Layout-Guided Synthesis, Image Inpainting.

Which projects share features with compvis/taming-transformers?

Projects with overlapping indexed features include: compvis/latent-diffusion — Latent Diffusion is a framework for high-resolution image synthesis that performs the denoising process within a… openai/dall-e — This project is a PyTorch implementation of a discrete variational autoencoder designed to compress high-resolution… youyuge34/anime-inpainting — Anime-InPainting is a specialized software platform designed for the restoration of anime illustrations and digital… dusty-nv/jetson-inference — jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU… lucidrains/stylegan2-pytorch — This project is a PyTorch implementation of StyleGAN2, providing a library and research framework for training… janspiry/image-super-resolution-via-iterative-refinement — This project is a deep learning framework for AI image super-resolution and facial synthesis. It provides a diffusion…

Projects sharing features with Taming Transformers

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

    CompVis/latent-diffusion

    14,072View on GitHub↗

    Latent Diffusion is a framework for high-resolution image synthesis that performs the denoising process within a compressed latent space. It uses variational autoencoders to encode images into a lower-dimensional representation, reducing the computational cost of noise prediction compared to operating on raw pixels. The project enables text-to-image generation by integrating natural language descriptions through cross-attention conditioning. It also supports image inpainting and restoration, filling masked or missing image areas with generated content, and example-based synthesis using retrie

    Jupyter Notebook
    View on GitHub↗14,072
  • openai/dall-eopenai avatar

    openai/DALL-E

    10,853View on GitHub↗

    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 visuali

    Python
    View on GitHub↗10,853
  • youyuge34/anime-inpaintingyouyuge34 avatar

    youyuge34/Anime-InPainting

    1,128View on GitHub↗

    Anime-InPainting is a specialized software platform designed for the restoration of anime illustrations and digital artwork. It functions as a deep learning-based image editor that utilizes generative models to repair damaged or incomplete images, remove unwanted artifacts, and eliminate visual blemishes such as mosaics. The project distinguishes itself through an edge-guided generative approach, which uses structural edge maps to ensure that reconstructed regions maintain visual and spatial consistency with the surrounding image. Users can interact with the restoration process through a grap

    Pythonanimecomputer-visioncv
    View on GitHub↗1,128
  • dusty-nv/jetson-inferencedusty-nv avatar

    dusty-nv/jetson-inference

    8,734View on GitHub↗

    jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

    C++caffecomputer-visiondeep-learning
    View on GitHub↗8,734
Compare all 30 related projects→