min-dalle-test/README.md

92 lines
3.4 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
2022-07-01 23:12:43 +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)
 
2022-06-29 19:24:09 +00:00
[![Replicate](https://replicate.com/kuprel/min-dalle/badge)](https://replicate.com/kuprel/min-dalle)
2022-07-01 23:12:43 +00:00
 
[![Join us on Discord](https://img.shields.io/discord/823813159592001537?color=5865F2&logo=discord&logoColor=white)](https://discord.gg/xBPBXfcFHd)
2022-06-27 21:26:05 +00:00
2022-07-03 21:29:53 +00:00
This is a fast, minimal implementation of Boris Dayma's [DALL·E Mega](https://github.com/borisdayma/dalle-mini). It has been stripped down for inference and converted to PyTorch. The only third party dependencies are numpy, requests, pillow and torch.
2022-07-03 21:29:53 +00:00
It takes
- **35 seconds** to generate a 3x3 grid with a P100 in Colab
- **16 seconds** to generate a 4x4 grid with an A100 on Replicate
- **TBD** to generate a 4x4 grid with an H100 (@NVIDIA?)
2022-06-27 17:51:48 +00:00
2022-07-01 23:19:02 +00:00
The flax model and code for converting it to torch can be found [here](https://github.com/kuprel/min-dalle-flax).
2022-07-01 23:03:18 +00:00
## Install
2022-06-27 17:51:48 +00:00
2022-07-01 22:52:40 +00:00
```bash
2022-07-01 22:30:22 +00:00
$ pip install min-dalle
```
2022-06-27 21:26:05 +00:00
2022-07-01 23:03:18 +00:00
## Usage
2022-06-27 21:28:40 +00:00
2022-07-02 00:27:29 +00:00
Load the model parameters once and reuse the model to generate multiple images.
2022-07-01 22:30:22 +00:00
2022-07-01 22:32:48 +00:00
```python
from min_dalle import MinDalle
2022-07-01 22:30:22 +00:00
2022-07-02 00:24:19 +00:00
model = MinDalle(is_mega=True, models_root='./pretrained')
2022-06-27 19:46:04 +00:00
```
2022-07-02 00:25:49 +00:00
The required models will be downloaded to `models_root` if they are not already there. Once everything has finished initializing, call `generate_image` with some text and a seed as many times as you want.
2022-07-01 22:54:05 +00:00
```python
2022-07-03 20:49:38 +00:00
text = 'Dali painting of WALL·E'
2022-07-03 20:26:49 +00:00
image = model.generate_image(text, seed=0, grid_size=4)
display(image)
2022-06-27 17:38:35 +00:00
```
2022-07-03 20:49:38 +00:00
<img src="https://github.com/kuprel/min-dalle/raw/main/examples/dali_walle.jpg" alt="min-dalle" width="300"/>
2022-07-02 17:06:03 +00:00
```python
text = 'Rusty Iron Man suit found abandoned in the woods being reclaimed by nature'
image = model.generate_image(text, seed=0, grid_size=3)
display(image)
```
2022-07-03 20:49:38 +00:00
<img src="https://github.com/kuprel/min-dalle/raw/main/examples/ironman.jpg" alt="min-dalle" width="300"/>
2022-07-01 23:15:31 +00:00
2022-07-03 19:40:58 +00:00
```python
text = 'court sketch of godzilla on trial'
image = model.generate_image(text, seed=6, grid_size=3)
display(image)
```
2022-07-03 20:49:38 +00:00
<img src="https://github.com/kuprel/min-dalle/raw/main/examples/godzilla_trial.jpg" alt="min-dalle" width="300"/>
2022-07-03 19:40:58 +00:00
2022-07-02 16:55:59 +00:00
```python
text = 'a funeral at Whole Foods'
image = model.generate_image(text, seed=10, grid_size=3)
display(image)
```
2022-07-03 20:49:38 +00:00
<img src="https://github.com/kuprel/min-dalle/raw/main/examples/funeral.jpg" alt="min-dalle" width="300"/>
2022-07-02 16:55:59 +00:00
```python
text = 'Jesus turning water into wine on Americas Got Talent'
image = model.generate_image(text, seed=2, grid_size=3)
display(image)
```
2022-07-03 20:49:38 +00:00
<img src="https://github.com/kuprel/min-dalle/raw/main/examples/jesus.jpg" alt="min-dalle" width="300"/>
2022-07-02 16:55:59 +00:00
```python
text = 'cctv footage of Yoda robbing a liquor store'
image = model.generate_image(text, seed=0, grid_size=3)
display(image)
```
2022-07-03 20:49:38 +00:00
<img src="https://github.com/kuprel/min-dalle/raw/main/examples/yoda.jpg" alt="min-dalle" width="300"/>
2022-07-02 16:55:59 +00:00
2022-07-01 23:15:31 +00:00
### Command Line
2022-07-01 23:19:02 +00:00
Use `image_from_text.py` to generate images from the command line.
2022-07-01 23:15:31 +00:00
```bash
$ python image_from_text.py --text='artificial intelligence' --seed=7
```
2022-07-03 20:49:38 +00:00
<img src="https://github.com/kuprel/min-dalle/raw/main/examples/artificial_intelligence.jpg" alt="min-dalle" width="200"/>
2022-07-01 23:15:31 +00:00
```bash
2022-07-02 13:26:30 +00:00
$ python image_from_text.py --text='trail cam footage of gollum eating watermelon' --mega --seed=1 --grid-size=3
2022-07-01 23:15:31 +00:00
```
2022-07-03 20:49:38 +00:00
<img src="https://github.com/kuprel/min-dalle/raw/main/examples/gollum_trailcam.jpg" alt="min-dalle" width="300"/>