openai/DALL-E
DALL-E
PyTorch package for the discrete VAE used for DALL·E.
Builder
OpenAI
openai • ai-lab
Stars
10,871
Using upstream star count
Forks
1,888
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Feb 23, 2021
Project creation date
README Summary
This repository contains the PyTorch implementation of the discrete Variational Autoencoder (dVAE) used in OpenAI's DALL·E model. The dVAE learns to encode images into discrete tokens that can be processed by transformer models. It provides the image tokenization component that enables DALL·E to generate images from text descriptions.
AI Dev Skills
Unmapped
Discrete Variational AutoencodersGenerative Adversarial NetworksText-to-Image GenerationComputer VisionDeep Learning ArchitecturePyTorch ImplementationRepresentation LearningVector Quantization
Tags
Discrete Variational AutoencodersGenerative Adversarial NetworksText-to-Image GenerationComputer VisionDeep Learning ArchitecturePyTorch ImplementationRepresentation LearningVector QuantizationDiscrete Representation LearningImage GenerationGenerative ModelingMultimodal AIImageDigital ArtVision-Language ModelsMultimodal AI ResearchGenerative AIFoundation ModelsSelf-hostedImage CompressionMedia and EntertainmentImage TokenizationCreative IndustriesMarketing and AdvertisingVisual Content CreationResearch EnvironmentVariational AutoencodersPython
Taxonomy
Deployment Context
Modalities
Skill Areas
Recent Activity
Updated 2 years ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- medium
- Maturity
- research
Categories
Model TrainingPrimaryComputer VisionNLP & TextGenerative MediaLearning ResourcesSearch & KnowledgeOther AI / MLMultimodal AISafety & AlignmentFoundation Models
PM Skills
Product Discovery
Languages
Python100.0%
Timeline
- Project created
- Feb 23, 2021
- Forked
- Mar 14, 2026
- Your last push
- 2 years ago
- Upstream last push
- 2 years ago
- Tracked since
- Jan 31, 2024
Similar Repos
pgvector cosine similarity · $0
Loading…