DALLE-reproduction
This repository is for sharing pre-trained OpenAI DALLE model and generating images from given texts.
All models are trained by lucidrains/DALLE-pytorch + VQGAN (Taming transformer) with different training code and BPE model.
If you want to train DALLE, please go to lucidrains/DALLE-pytorch and support them to reproduce better DALLE models
The notebook includes
1. Text to image generation
2. Pre-trained CLIP reranking
- CUB200
- COCO
3. Generate rest of image based on the given cropped image
- CUB200
- COCO
Usage
- Install requirements
$ pip install -r requirements
- Install DeepSpeed
- Follow the instruction here and install DeepSpeed
Models
- Download models below and save them in pretrained folder
- Check the link in Details for the model specifics
| Dataset | Download | Password | Optimizer | Size | Details |
|---|---|---|---|---|---|
| CUB200 | link | v9ge | Adam | 1.1GB | link |
| CUB200 | link | 47w1 | AdamW | 1.1GB | link |
| COCO | link | p3ki | Adam | 1.5GB | link |