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

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectServer MCPDespreCum realizăm clasamentulPresă
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
NVlabs avatar

NVlabs/imaginaire

0
View on GitHub↗
4,074 stele·445 fork-uri·Python·11 vizualizări

Imaginaire

Imaginaire este o bibliotecă PyTorch pentru sinteza imaginilor și un framework de traducere neuronală a imaginilor, conceput pentru a genera conținut vizual sintetic de înaltă rezoluție. Funcționează ca un generator vizual de deep learning care mapează imagini și videoclipuri semantice în versiuni fotorealiste, folosind atât metode supervizate, cât și nesupervizate.

Proiectul include un instrument specializat pentru randarea mediilor 3D, care convertește reprezentările de tip bloc în scene fotorealiste, menținând în același timp consistența vizuală pe termen lung. De asemenea, suportă traducerea video fotorealistă care utilizează imagini de referință pentru a asigura stabilitatea temporală a secvențelor.

Framework-ul acoperă o gamă largă de capabilități de sinteză vizuală, inclusiv transferul de stil multi-domeniu, maparea imagine-la-imagine și generarea de imagini și videoclipuri sintetice bazate pe cercetări de deep learning.

Features

  • Deep Learning Image Translators - Implements optimized neural network models for synthesizing high-resolution visuals and translating images between visual domains.
  • Multi-Domain Synthesis - Implements a shared model with domain-specific conditioning to map images across several distinct visual categories.
  • Example-Guided Generation - Provides video translation that utilizes reference images to ensure temporal stability and photorealistic mapping.
  • Unsupervised Style Translation - Shifts image styles between disparate visual domains without requiring matching pairs via style-guided mapping.
  • Synthetic Content Generators - Creates synthetic images and videos using optimized PyTorch models based on established machine learning research.
  • Image Synthesis Libraries - Ships as a collection of PyTorch models for generating synthetic images and videos based on deep learning research.
  • Paired Image Translation - Learns direct translations between semantic maps and photorealistic images using paired training datasets.
  • Unpaired Image Translation - Maps images between different visual domains without paired data using style-guided or multi-domain translations.
  • Image and Video Synthesis Toolkits - Provides a comprehensive toolkit of optimized models for synthesizing high-resolution synthetic images and videos.
  • Image Translation Frameworks - Provides a framework for mapping semantic images and videos into photorealistic versions using supervised and unsupervised methods.
  • Semantic Video Translation - Converts semantic video sequences into photorealistic footage using example images to guide the mapping.
  • Block-Based Scene Representations - Implements a specialized system for converting block-based world representations into photorealistic 3D scenes.
  • 3D Environment Rendering - Converts block-based world representations into realistic 3D environments while maintaining long-term visual consistency.
  • Generative Model Implementations - NVIDIA library for image and video synthesis models.

Istoric stele

Graficul istoricului de stele pentru nvlabs/imaginaireGraficul istoricului de stele pentru nvlabs/imaginaire

Căutare AI

Explorează mai multe repository-uri excelente

Descrie ce ai nevoie în limbaj simplu — AI-ul sortează mii de proiecte open source selectate în funcție de relevanță.

Start searching with AI

Întrebări frecvente

Ce face nvlabs/imaginaire?

Imaginaire este o bibliotecă PyTorch pentru sinteza imaginilor și un framework de traducere neuronală a imaginilor, conceput pentru a genera conținut vizual sintetic de înaltă rezoluție. Funcționează ca un generator vizual de deep learning care mapează imagini și videoclipuri semantice în versiuni fotorealiste, folosind atât metode supervizate, cât și nesupervizate.

Care sunt principalele funcționalități ale nvlabs/imaginaire?

Principalele funcționalități ale nvlabs/imaginaire sunt: Deep Learning Image Translators, Multi-Domain Synthesis, Example-Guided Generation, Unsupervised Style Translation, Synthetic Content Generators, Image Synthesis Libraries, Paired Image Translation, Unpaired Image Translation.

Care sunt câteva alternative open-source pentru nvlabs/imaginaire?

Alternativele open-source pentru nvlabs/imaginaire includ: yunjey/stargan — StarGAN is a PyTorch image-to-image translation framework designed to synthesize visual styles and attributes across… taki0112/ugatit — UGATIT is an unsupervised generative adversarial network and image-to-image translation model implemented in… phillipi/pix2pix — pix2pix is a framework for image-to-image translation using conditional generative adversarial networks. It functions… junyanz/cyclegan — CycleGAN is a generative adversarial network framework designed for unpaired image-to-image translation. It enables… paddlepaddle/paddlegan — PaddleGAN is a generative AI framework and deep learning computer vision library built on the PaddlePaddle framework.… junyanz/pytorch-cyclegan-and-pix2pix — This project is a deep learning framework designed for training and deploying image-to-image translation models. It…

Alternative open-source pentru Imaginaire

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Imaginaire.
  • taki0112/ugatitAvatar taki0112

    taki0112/UGATIT

    6,117Vezi pe GitHub↗

    UGATIT is an unsupervised generative adversarial network and image-to-image translation model implemented in TensorFlow. It serves as the official research implementation of an ICLR 2020 paper, providing a framework for converting images between different visual styles without requiring paired training examples. The system utilizes an unsupervised generative attentional network and attention maps to deform geometric shapes and modify textures during the translation process. It employs a cycle-consistent framework to ensure translation quality by requiring images to return to their original st

    Python
    Vezi pe GitHub↗6,117
  • yunjey/starganAvatar yunjey

    yunjey/stargan

    5,292Vezi pe GitHub↗

    StarGAN is a PyTorch image-to-image translation framework designed to synthesize visual styles and attributes across multiple domains. It implements a generative adversarial network that serves as a deep learning image translator for modifying specific visual characteristics within an image dataset. The framework uses a single unified model to handle translations between multiple image domains rather than requiring separate pairs of models. It is a research implementation that learns mappings between different image attributes without the need for paired training data. The project covers the

    Python
    Vezi pe GitHub↗5,292
  • phillipi/pix2pixAvatar phillipi

    phillipi/pix2pix

    10,644Vezi pe GitHub↗

    pix2pix is a framework for image-to-image translation using conditional generative adversarial networks. It functions as a supervised trainer and visual domain mapper designed to learn a mapping between input and output images for style and domain transfer. The system utilizes a U-Net encoder-decoder architecture combined with a PatchGAN local discriminator to enforce high-frequency local consistency. It employs L1 loss regularization to ensure generated outputs remain structurally close to the ground truth. The project covers a broad range of computer vision capabilities, including semantic

    Lua
    Vezi pe GitHub↗10,644
  • junyanz/cycleganAvatar junyanz

    junyanz/CycleGAN

    12,861Vezi pe GitHub↗

    CycleGAN is a generative adversarial network framework designed for unpaired image-to-image translation. It enables the conversion of images between two distinct visual domains using datasets that do not require direct one-to-one matching examples. The project implements a deep learning style transfer tool capable of artistic style transfer, object transfiguration, and domain-to-domain conversion. It uses a dual-generator architecture and cycle-consistency loss to ensure that images translated to a target domain and back recover their original state. The framework covers core machine learnin

    Lua
    Vezi pe GitHub↗12,861
  • Vezi toate cele 30 alternative pentru Imaginaire→