Go to file
2022-06-30 20:55:42 -04:00
examples update readme 2022-06-30 15:33:53 -04:00
min_dalle updated readme 2022-06-30 16:50:04 -04:00
.gitattributes add gitattributes file 2022-06-29 12:45:41 -04:00
.gitignore examples 2022-06-27 13:39:00 -04:00
cog.yaml Update cog.yaml 2022-06-29 19:14:25 -04:00
image_from_text.py is_reusable 2022-06-30 11:25:24 -04:00
LICENSE license and cleanup 2022-06-27 14:34:10 -04:00
min_dalle.ipynb reusable mega torch model works in standard colab runtime 2022-06-30 20:55:42 -04:00
predict.py updated replicate predict.py file 2022-06-29 15:53:25 -04:00
README.md updated readme 2022-06-30 16:50:04 -04:00
requirements.txt Update requirements.txt 2022-06-30 13:13:33 -04:00
setup.sh Update setup.sh 2022-06-29 21:45:05 -04:00

min(DALL·E)

Open In Colab   Replicate

This is a minimal implementation of Boris Dayma's DALL·E Mini. It has been stripped to the bare essentials necessary for doing inference, and converted to PyTorch. To run the torch model, the only third party dependencies are numpy and torch. Flax is used to convert the weights (which are saved with torch.save the first time the model is loaded), and wandb is only used to download the models.

It currently takes about 10 seconds to generate an avocado armchair with DALL·E Mega in PyTorch on Colab with a reusable model and high-RAM GPU runtime.

Setup

Run sh setup.sh to install dependencies and download pretrained models. The models can also be downloaded manually here: VQGan, DALL·E Mini, DALL·E Mega

Usage

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. To load a model once and generate multiple times, initialize either MinDalleTorch or MinDalleFlax, then call generate_image with some text and a seed. See the colab for an example.

Examples

python image_from_text.py --text='artificial intelligence' --torch

Alien

python image_from_text.py --text='a comfy chair that looks like an avocado' --torch --mega --seed=10

Avocado Armchair

python image_from_text.py --text='court sketch of godzilla on trial' --mega --seed=100

Godzilla Trial