lucidrains/DALLE-pytorch
A PyTorch reimplementation of OpenAI's DALL-E transformer for text-to-image generation.
Velocity · 7d
+2.8
★ / day
Trend
→steady
star history
This repository provides a PyTorch implementation of DALL-E, OpenAI’s multimodal transformer model that generates images from textual descriptions. It includes CLIP integration for ranking and evaluating generated images. The project supports training on custom datasets and offers a Colab notebook for DeepSpeed-based training.