diff --git a/README.md b/README.md
index c01bf17..e500075 100644
--- a/README.md
+++ b/README.md
@@ -34,46 +34,46 @@ 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 = 'Dali painting of WallE'
+text = 'Dali painting of WALL·E'
image = model.generate_image(text, seed=0, grid_size=4)
display(image)
```
-
+
```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)
```
-
+
```python
text = 'court sketch of godzilla on trial'
image = model.generate_image(text, seed=6, grid_size=3)
display(image)
```
-
+
```python
text = 'a funeral at Whole Foods'
image = model.generate_image(text, seed=10, grid_size=3)
display(image)
```
-
+
```python
text = 'Jesus turning water into wine on Americas Got Talent'
image = model.generate_image(text, seed=2, grid_size=3)
display(image)
```
-
+
```python
text = 'cctv footage of Yoda robbing a liquor store'
image = model.generate_image(text, seed=0, grid_size=3)
display(image)
```
-
+
### Command Line
@@ -83,9 +83,9 @@ Use `image_from_text.py` to generate images from the command line.
```bash
$ python image_from_text.py --text='artificial intelligence' --seed=7
```
-
+
```bash
$ python image_from_text.py --text='trail cam footage of gollum eating watermelon' --mega --seed=1 --grid-size=3
```
-
+
diff --git a/README.rst b/README.rst
new file mode 100644
index 0000000..1871749
--- /dev/null
+++ b/README.rst
@@ -0,0 +1,95 @@
+min(DALL·E)
+===========
+
+|Open In Colab| |Replicate| |Join us on Discord|
+
+This is a fast, minimal implementation of Boris Dayma’s `DALL·E
+Mini `__. It has been stripped
+down for inference and converted to PyTorch. The only third party
+dependencies are numpy, requests, pillow and torch.
+
+To generate a 3x3 grid of DALL·E Mega images it takes - **35 seconds**
+with a P100 in Colab - **15 seconds** with an A100 on Replicate -
+**TBD** with an H100 (@NVIDIA?)
+
+The flax model and code for converting it to torch can be found
+`here `__.
+
+Install
+-------
+
+.. code:: bash
+
+ $ pip install min-dalle
+
+Usage
+-----
+
+Load the model parameters once and reuse the model to generate multiple
+images.
+
+.. code:: python
+
+ from min_dalle import MinDalle
+
+ 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.
+
+.. code:: python
+
+ text = 'Dali painting of WallE'
+ image = model.generate_image(text, seed=0, grid_size=4)
+ display(image)
+
+.. code:: 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)
+
+.. code:: python
+
+ text = 'court sketch of godzilla on trial'
+ image = model.generate_image(text, seed=6, grid_size=3)
+ display(image)
+
+.. code:: python
+
+ text = 'a funeral at Whole Foods'
+ image = model.generate_image(text, seed=10, grid_size=3)
+ display(image)
+
+.. code:: python
+
+ text = 'Jesus turning water into wine on Americas Got Talent'
+ image = model.generate_image(text, seed=2, grid_size=3)
+ display(image)
+
+.. code:: python
+
+ text = 'cctv footage of Yoda robbing a liquor store'
+ image = model.generate_image(text, seed=0, grid_size=3)
+ display(image)
+
+Command Line
+~~~~~~~~~~~~
+
+Use ``image_from_text.py`` to generate images from the command line.
+
+.. code:: bash
+
+ $ python image_from_text.py --text='artificial intelligence' --seed=7
+
+.. code:: bash
+
+ $ python image_from_text.py --text='trail cam footage of gollum eating watermelon' --mega --seed=1 --grid-size=3
+
+.. |Open In Colab| image:: https://colab.research.google.com/assets/colab-badge.svg
+ :target: https://colab.research.google.com/github/kuprel/min-dalle/blob/main/min_dalle.ipynb
+.. |Replicate| image:: https://replicate.com/kuprel/min-dalle/badge
+ :target: https://replicate.com/kuprel/min-dalle
+.. |Join us on Discord| image:: https://img.shields.io/discord/823813159592001537?color=5865F2&logo=discord&logoColor=white
+ :target: https://discord.gg/xBPBXfcFHd
diff --git a/cog.yaml b/cog.yaml
index 6a04d58..55d328d 100644
--- a/cog.yaml
+++ b/cog.yaml
@@ -6,7 +6,7 @@ build:
- "libgl1-mesa-glx"
- "libglib2.0-0"
python_packages:
- - "min-dalle==0.2.12"
+ - "min-dalle==0.2.13"
run:
- pip install torch==1.10.0+cu113 -f https://download.pytorch.org/whl/torch_stable.html
diff --git a/setup.py b/setup.py
index 7271488..1949018 100644
--- a/setup.py
+++ b/setup.py
@@ -4,8 +4,8 @@ from pathlib import Path
setuptools.setup(
name='min-dalle',
description = 'min(DALL·E)',
- long_description=(Path(__file__).parent / "README").read_text(),
- version='0.2.12',
+ long_description=(Path(__file__).parent / "README.rst").read_text(),
+ version='0.2.13',
author='Brett Kuprel',
author_email='brkuprel@gmail.com',
url='https://github.com/kuprel/min-dalle',