Yihong Luo
commited on
Commit
•
c8ff945
1
Parent(s):
54d572c
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,7 @@ This model is fine-tuning from PixArt, enabling one-step inference to perform te
|
|
| 6 |
|
| 7 |
We wanna highlight that the YOSO-PixArt was originally trained on 512 resolution. However we found that we can construct a YOSO that enables generating samples with 1024 resolution by merging with PixArt-1024 (Eq(15) in the paper) as follows:
|
| 8 |
|
|
|
|
| 9 |
|
| 10 |
## usage
|
| 11 |
```python
|
|
|
|
| 6 |
|
| 7 |
We wanna highlight that the YOSO-PixArt was originally trained on 512 resolution. However we found that we can construct a YOSO that enables generating samples with 1024 resolution by merging with PixArt-1024 (Eq(15) in the paper) as follows:
|
| 8 |
|
| 9 |
+
The impressive performance indicates the robust generalization ability of our YOSO.
|
| 10 |
|
| 11 |
## usage
|
| 12 |
```python
|