min-dalle-test/README.md

36 lines
1.7 KiB
Markdown
Raw Normal View History

2022-06-27 19:46:04 +00:00
# min(DALL·E)
2022-06-27 17:38:35 +00:00
2022-06-28 00:59:39 +00:00
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/kuprel/min-dalle/blob/main/min_dalle.ipynb)
2022-06-27 21:26:05 +00:00
2022-06-29 14:43:46 +00:00
This is a minimal implementation of [DALL·E Mini](https://github.com/borisdayma/dalle-mini). It has been stripped to the bare essentials necessary for doing inference, and converted to PyTorch. The only third party dependencies are `numpy`, `torch`, and `flax`. PyTorch inference with DALL·E Mega takes about 10 seconds in colab.
2022-06-27 17:51:48 +00:00
2022-06-27 18:34:10 +00:00
### Setup
2022-06-27 17:51:48 +00:00
Run `sh setup.sh` to install dependencies and download pretrained models. The `wandb` python package is installed to download DALL·E mini and DALL·E mega. Alternatively, the models can be downloaded manually here:
2022-06-28 00:59:39 +00:00
[VQGan](https://huggingface.co/dalle-mini/vqgan_imagenet_f16_16384),
[DALL·E Mini](https://wandb.ai/dalle-mini/dalle-mini/artifacts/DalleBart_model/mini-1/v0/files),
[DALL·E Mega](https://wandb.ai/dalle-mini/dalle-mini/artifacts/DalleBart_model/mega-1-fp16/v14/files)
2022-06-27 21:26:05 +00:00
2022-06-28 00:59:39 +00:00
### Usage
2022-06-27 21:28:40 +00:00
2022-06-29 14:47:08 +00:00
Use the python script `image_from_text.py` to generate images from the command line. Note: the command line script loads the models and parameters each time. The colab notebook demonstrates how to load a model once and run it multiple times.
Here are some examples:
2022-06-27 17:38:35 +00:00
```
2022-06-29 14:43:46 +00:00
python3 image_from_text.py --text='artificial intelligence' --torch
2022-06-27 19:46:04 +00:00
```
2022-06-29 14:43:46 +00:00
![Alien](examples/artificial_intelligence.png)
2022-06-27 19:46:04 +00:00
2022-06-27 20:49:42 +00:00
2022-06-27 19:46:04 +00:00
```
2022-06-29 14:43:46 +00:00
python image_from_text.py --text='a comfy chair that looks like an avocado' --torch --mega --seed=10
2022-06-27 17:38:35 +00:00
```
![Avocado Armchair](examples/avocado_armchair.png)
```
2022-06-28 02:08:29 +00:00
python image_from_text.py --text='court sketch of godzilla on trial' --mega --seed=100
2022-06-27 17:38:35 +00:00
```
2022-06-29 14:47:08 +00:00
![Godzilla Trial](examples/godzilla_trial.png)