Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch
| Date | Stars |
|---|---|
| 2026-07-24 | 3494 |
| 2026-07-25 | 3494 |
| 2026-07-28 | 3494 |
| 2026-07-30 | 3494 |
| 2026-08-07 | 3497 |
| 2026-08-16 | 3496 |
| 2026-08-18 | 3495 |
| 2026-08-19 | 3495 |
| 2026-08-27 | 3494 |
| 2026-08-29 | 3494 |
| 2026-08-30 | 3494 |
| 2026-09-05 | 3491 |
| 2026-09-08 | 3492 |
| 2026-09-09 | 3490 |
| 2026-09-15 | 3489 |
| 2026-09-20 | 3488 |
Today
-1 stars today
This week
-2 stars this week
This month
-7 stars this month
Momentum
0.0
growth rate 0.00%/day
# min(DALL·E)
[<img src="https://devin.ai/assets/deepwiki-badge.png" alt="Ask DeepWiki.com" height="20"/>](https://deepwiki.com/kuprel/min-dalle)
[](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.
<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,
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)
```
<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,
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
IfExcerpt of 5,024 characters
Read on GitHub
353
4
Ahsen Khaliq · Huggingface
2
Chenxi
2
2
2
2
2
2
1
Omar Sanseviero · Google · Switzerland
1
1
1
1
Haydn Jones · University of Pennsylvania · United States
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8af4875279a67573, topic:deep-learning, topic:pytorch
matched fp:8af4875279a67573, topic:text-to-image