tanner/min-dalle-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'main' into patch-1

Browse Source
This commit is contained in:
Brett Kuprel
2022-07-02 09:32:15 -04:00
committed by GitHub
parent 0d2d4a6331 9e7d6edc30
commit 8b77428102
13 changed files with 124 additions and 104 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
Vendored
+7 -7
View File
@@ -8,7 +8,7 @@
This is a minimal implementation of Boris Dayma's [DALL·E Mini](https://github.com/borisdayma/dalle-mini) in PyTorch. It has been stripped to the bare essentials necessary for doing inference. The only third party dependencies are numpy, requests, pillow and torch.
It currently takes **7.4 seconds** to generate an image with DALL·E Mega on a standard GPU runtime in Colab.
It currently take **35 seconds** to generate a 3x3 grid with DALL·E Mega on a standard GPU runtime in Colab.
The flax model and code for converting it to torch can be found [here](https://github.com/kuprel/min-dalle-flax).
@@ -33,18 +33,18 @@ model = MinDalle(is_mega=True, models_root='./pretrained')
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.
```python
text = "a comfy chair that looks like an avocado"
text = 'a comfy chair that looks like an avocado'
image = model.generate_image(text)
display(image)
```
![Avocado Armchair](https://github.com/kuprel/min-dalle/raw/main/examples/avocado_armchair.png)
```python
text = "trail cam footage of gollum eating watermelon"
image = model.generate_image(text, seed=1)
text = 'court sketch of godzilla on trial'
image = model.generate_image(text, seed=6, grid_size=3)
display(image)
```
![Gollum Trailcam](https://github.com/kuprel/min-dalle/raw/main/examples/gollum_trailcam.png)
![Godzilla Trial](https://github.com/kuprel/min-dalle/raw/main/examples/godzilla_trial.png)
### Command Line
@@ -57,6 +57,6 @@ $ python image_from_text.py --text='artificial intelligence' --seed=7
![Artificial Intelligence](https://github.com/kuprel/min-dalle/raw/main/examples/artificial_intelligence.png)
```bash
$ python image_from_text.py --text='court sketch of godzilla on trial' --mega
$ python image_from_text.py --text='trail cam footage of gollum eating watermelon' --mega --seed=1 --grid-size=3
```
![Godzilla Trial](https://github.com/kuprel/min-dalle/raw/main/examples/godzilla_on_trial.png)
![Gollum Trailcam](https://github.com/kuprel/min-dalle/raw/main/examples/gollum_trailcam.png)