118 lines
4.4 KiB
Markdown
Vendored
118 lines
4.4 KiB
Markdown
Vendored
# min(DALL·E)
|
|
|
|
[](https://colab.research.google.com/github/kuprel/min-dalle/blob/main/min_dalle.ipynb)
|
|
|
|
[](https://replicate.com/kuprel/min-dalle)
|
|
|
|
[](https://discord.com/channels/823813159592001537/912729332311556136)
|
|
|
|
This is a fast, minimal port of Boris Dayma's [DALL·E Mini](https://github.com/borisdayma/dalle-mini) (with mega weights). 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 4x4 grid of DALL·E Mega images it takes:
|
|
- 89 sec with a T4 in Colab
|
|
- 48 sec with a P100 in Colab
|
|
- 13 sec with an A100 on Replicate
|
|
|
|
Here's a more detailed breakdown of performance on an A100. Credit to [@technobird22](https://github.com/technobird22) and his [NeoGen](https://github.com/technobird22/NeoGen) discord bot for the graph.
|
|
<br />
|
|
<img src="https://github.com/kuprel/min-dalle/raw/main/performance.png" alt="min-dalle" width="450"/>
|
|
<br />
|
|
|
|
The flax model and code for converting it to torch can be found [here](https://github.com/kuprel/min-dalle-flax).
|
|
|
|
## Install
|
|
|
|
```bash
|
|
$ pip install min-dalle
|
|
```
|
|
|
|
## Usage
|
|
|
|
Load the model parameters once and reuse the model to generate multiple images.
|
|
|
|
```python
|
|
from min_dalle import MinDalle
|
|
|
|
model = MinDalle(
|
|
models_root='./pretrained',
|
|
dtype=torch.float32,
|
|
is_mega=True,
|
|
is_reusable=True
|
|
)
|
|
```
|
|
|
|
The required models will be downloaded to `models_root` if they are not already there. Set the `dtype` to `torch.float16` to save GPU memory. If you have an Ampere architecture GPU you can use `torch.bfloat16`. Once everything has finished initializing, call `generate_image` with some text as many times as you want. Use a positive `seed` for reproducible results. Higher values for `supercondition_factor` result in better agreement with the text but a narrower variety of generated images. Every image token is sampled from the `top_k` most probable tokens. The largest logit is subtracted from the logits to avoid infs. The logits are then divided by the `temperature`.
|
|
|
|
```python
|
|
image = model.generate_image(
|
|
text='Nuclear explosion broccoli',
|
|
seed=-1,
|
|
grid_size=4,
|
|
temperature=1,
|
|
top_k=256,
|
|
supercondition_factor=32,
|
|
is_verbose=False
|
|
)
|
|
|
|
display(image)
|
|
```
|
|
<img src="https://github.com/kuprel/min-dalle/raw/main/examples/nuclear_broccoli.jpg" alt="min-dalle" width="400"/>
|
|
|
|
Credit to [@hardmaru](https://twitter.com/hardmaru) for the [example](https://twitter.com/hardmaru/status/1544354119527596034)
|
|
|
|
|
|
### Saving Individual Images
|
|
The images can also be generated as a `FloatTensor` in case you want to process them manually.
|
|
|
|
```python
|
|
images = model.generate_images(
|
|
text='Nuclear explosion broccoli',
|
|
seed=-1,
|
|
image_count=7,
|
|
temperature=1,
|
|
top_k=256,
|
|
supercondition_factor=16,
|
|
is_verbose=False
|
|
)
|
|
```
|
|
|
|
To get an image into PIL format you will have to first move the images to the CPU and convert the tensor to a numpy array.
|
|
```python
|
|
images = images.to('cpu').numpy()
|
|
```
|
|
Then image $i$ can be coverted to a PIL.Image and saved
|
|
```python
|
|
image = Image.fromarray(images[i])
|
|
image.save('image_{}.png'.format(i))
|
|
```
|
|
|
|
### Interactive
|
|
|
|
If the model is being used interactively (e.g. in a notebook) `generate_image_stream` can be used to generate a stream of images as the model is decoding. The detokenizer adds a slight delay for each image. Setting `log2_mid_count` to 3 results in a total of `2 ** 3 = 8` generated images. The only valid values for `log2_mid_count` are 0, 1, 2, 3, and 4. This is implemented in the colab.
|
|
|
|
```python
|
|
image_stream = model.generate_image_stream(
|
|
text='Dali painting of WALL·E',
|
|
seed=-1,
|
|
grid_size=3,
|
|
log2_mid_count=3,
|
|
temperature=1,
|
|
top_k=256,
|
|
supercondition_factor=16,
|
|
is_verbose=False
|
|
)
|
|
|
|
for image in image_stream:
|
|
display(image)
|
|
```
|
|
<img src="https://github.com/kuprel/min-dalle/raw/main/examples/dali_walle_animated.gif" alt="min-dalle" width="300"/>
|
|
|
|
### Command Line
|
|
|
|
Use `image_from_text.py` to generate images from the command line.
|
|
|
|
```bash
|
|
$ python image_from_text.py --text='artificial intelligence' --no-mega
|
|
```
|
|
<img src="https://github.com/kuprel/min-dalle/raw/main/examples/artificial_intelligence.jpg" alt="min-dalle" width="200"/>
|