Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/kuprel/min-dalle
min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch
https://github.com/kuprel/min-dalle
artificial-intelligence deep-learning pytorch text-to-image
Last synced: 3 days ago
JSON representation
min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch
- Host: GitHub
- URL: https://github.com/kuprel/min-dalle
- Owner: kuprel
- License: mit
- Created: 2022-06-27T15:53:59.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2022-11-21T14:12:29.000Z (about 2 years ago)
- Last Synced: 2024-10-29T15:27:21.970Z (about 2 months ago)
- Topics: artificial-intelligence, deep-learning, pytorch, text-to-image
- Language: Python
- Homepage:
- Size: 46.5 MB
- Stars: 3,483
- Watchers: 25
- Forks: 257
- Open Issues: 25
-
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE
Awesome Lists containing this project
- StarryDivineSky - kuprel/min-dalle - E是一个可以通过文本描述中生成图像的AI程序。 通过120亿参数版本的GPT-3 Transformer模型来理解自然语言输入并生成相应的图片。可生成现实、现实中不存在的对象。 (其他_机器视觉 / 网络服务_其他)
README
# min(DALL·E)
[](https://colab.research.google.com/github/kuprel/min-dalle/blob/main/min_dalle.ipynb)
[](https://huggingface.co/spaces/kuprel/min-dalle)
[](https://replicate.com/kuprel/min-dalle)
[](https://discord.com/channels/823813159592001537/912729332311556136)
[YouTube Walk-through](https://youtu.be/x_8uHX5KngE) by The AI Epiphany
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 3x3 grid of DALL·E Mega images it takes:
- 55 sec with a T4 in Colab
- 33 sec with a P100 in Colab
- 15 sec with an A10G on Hugging Face
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.
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,
device='cuda',
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`. Set the `device` to either "cuda" or "cpu". 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`. If `is_seamless` is true, the image grid will be tiled in token space not pixel space.
```python
image = model.generate_image(
text='Nuclear explosion broccoli',
seed=-1,
grid_size=4,
is_seamless=False,
temperature=1,
top_k=256,
supercondition_factor=32,
is_verbose=False
)
display(image)
```
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,
grid_size=3,
is_seamless=False,
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))
```
### Progressive Outputs
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. Set `progressive_outputs` to `True` to enable this. An example is implemented in the colab.
```python
image_stream = model.generate_image_stream(
text='Dali painting of WALL·E',
seed=-1,
grid_size=3,
progressive_outputs=True,
is_seamless=False,
temperature=1,
top_k=256,
supercondition_factor=16,
is_verbose=False
)
for image in image_stream:
display(image)
```
### 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
```
