Image generation research paper, code, and models
Top 22.0% on sourcepulse
This repository provides code and pre-trained models for Image GPT (iGPT), a generative model for images based on the GPT-2 architecture. It enables researchers and engineers to experiment with pixel-level generative pre-training for image synthesis and analysis.
How It Works
iGPT adapts the GPT-2 transformer architecture for image generation by treating pixels as a sequence. It uses a novel 9-bit color palette quantization and a start-of-sequence token to enable autoregressive generation. This approach allows for flexible image generation and evaluation, leveraging the proven transformer framework for visual data.
Quick Start & Requirements
conda
to create an environment and install dependencies:
conda create --name image-gpt python=3.7.3
conda activate image-gpt
conda install numpy=1.16.3 tensorflow-gpu=1.13.1 imageio=2.8.0 requests=2.21.0 tqdm=4.46.0
download.py
.Highlighted Details
Maintenance & Community
Chen et al., "Generative Pretraining from Pixels", 2020
.Licensing & Compatibility
Limitations & Caveats
The project is archived, indicating no further development or support. It requires specific, older versions of TensorFlow (1.13.1) and Python (3.7.3), which may pose compatibility challenges with modern systems and libraries. The provided datasets are center-cropped, not randomly cropped, which may affect replication of training results.
3 years ago
Inactive