Update README.md
Browse files
README.md
CHANGED
|
@@ -7,8 +7,23 @@ tags:
|
|
| 7 |
- diffusion-models-class
|
| 8 |
datasets:
|
| 9 |
- mnist
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
## Usage
|
| 13 |
|
| 14 |
```python
|
|
|
|
| 7 |
- diffusion-models-class
|
| 8 |
datasets:
|
| 9 |
- mnist
|
| 10 |
+
library_name: diffusers
|
| 11 |
+
pipeline_tag: unconditional-image-generation
|
| 12 |
+
thumbnail: https://upload.wikimedia.org/wikipedia/commons/f/f7/MnistExamplesModified.png
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# Unconditional MNIST DDPM
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Description
|
| 20 |
+
|
| 21 |
+
This model is a very lightweight UNet2D trained on the MNIST dataset. \
|
| 22 |
+
This model is unconditional, meaning that you cannot pick which number you'd like to generate. \
|
| 23 |
+
This model was trained in ~40min on an L4 GPU Google Colab instance. You can see the training logs in the [Training metrics](https://huggingface.co/1aurent/ddpm-mnist/tensorboard) tab.
|
| 24 |
+
|
| 25 |
+
A conditional model is available at [1aurent/ddpm-mnist-conditional](https://huggingface.co/1aurent/ddpm-mnist-conditional), though it is pretty buggy.
|
| 26 |
+
|
| 27 |
## Usage
|
| 28 |
|
| 29 |
```python
|