Commit
•
9567af1
1
Parent(s):
22426be
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,16 @@ image = pipe(prompt, width=256, height=256).images[0]
|
|
| 15 |
image.save('test.jpg')
|
| 16 |
```
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
## License
|
| 19 |
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:
|
| 20 |
|
|
|
|
| 15 |
image.save('test.jpg')
|
| 16 |
```
|
| 17 |
|
| 18 |
+
## Training details
|
| 19 |
+
|
| 20 |
+
Fine tuned from the stable-diffusion 1.4 checkpoint as follows:
|
| 21 |
+
|
| 22 |
+
- 22,000 steps fine-tuning only the attention layers of the unet, learn rate=1e-5, batch size=256
|
| 23 |
+
- 66,000 steps training the full unet, learn rate=5e-5, batch size=552
|
| 24 |
+
|
| 25 |
+
- GPUs provided by [Lambda GPU Cloud](https://lambdalabs.com/service/gpu-cloud)
|
| 26 |
+
- Trained on [LAION Improved Aesthetics 6plus](https://huggingface.co/datasets/ChristophSchuhmann/improved_aesthetics_6plus).
|
| 27 |
+
|
| 28 |
## License
|
| 29 |
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:
|
| 30 |
|