Update README.md
Browse files
README.md
CHANGED
|
@@ -45,3 +45,10 @@ image = pipe(
|
|
| 45 |
).images[0]
|
| 46 |
image.save('image.jpg')
|
| 47 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
).images[0]
|
| 46 |
image.save('image.jpg')
|
| 47 |
```
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
## Limitation
|
| 51 |
+
Due to the fact that only 1024*1024 pixel resolution was used during the training phase,
|
| 52 |
+
the inference performs best at this size, with other sizes yielding suboptimal results.
|
| 53 |
+
We will initiate multi-resolution training in the future, and at that time, we will open-source the new weights.
|
| 54 |
+
|