Commit
•
bf14d65
1
Parent(s):
91ac3ef
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
RuDOLPH: One Hyper-Modal Transformer can be creative as DALL-E and smart as CLIP
|
| 4 |
|
| 5 |
-
<img src="https://raw.githubusercontent.com/sberbank-ai/ru-dolph/master/pics/rudolph-generated.png" height="60" border="2"/>
|
| 6 |
|
| 7 |
|
| 8 |
Model was trained by [Sber AI](https://github.com/sberbank-ai) and [SberDevices](https://sberdevices.ru/) teams.
|
|
@@ -23,7 +23,7 @@ Model was trained by [Sber AI](https://github.com/sberbank-ai) and [SberDevices]
|
|
| 23 |
|
| 24 |
The primary proposed method is to modify the sparse transformer's attention mask to better control multi-modalities and up to the next level with "hyper-modality". It allows us to calculate the transitions of modalities in both directions, unlike another similar work DALL-E Transformer, which used only one direction, "text to image". The proposed "image to right text" direction is achieved by extension sparse attention mask to the right for auto-repressively text generation with image condition without attention to left text.
|
| 25 |
|
| 26 |
-
<img src="https://raw.githubusercontent.com/sberbank-ai/ru-dolph/master/pics/attention_masks.png" height="40" border="2"/>
|
| 27 |
|
| 28 |
# Authors
|
| 29 |
|
|
|
|
| 2 |
|
| 3 |
RuDOLPH: One Hyper-Modal Transformer can be creative as DALL-E and smart as CLIP
|
| 4 |
|
| 5 |
+
<img src="https://raw.githubusercontent.com/sberbank-ai/ru-dolph/master/pics/rudolph-generated.png?token=GHSAT0AAAAAABQH6MSSZP3PVXVAVWPGGYHKYOYRU4A" height="60" border="2"/>
|
| 6 |
|
| 7 |
|
| 8 |
Model was trained by [Sber AI](https://github.com/sberbank-ai) and [SberDevices](https://sberdevices.ru/) teams.
|
|
|
|
| 23 |
|
| 24 |
The primary proposed method is to modify the sparse transformer's attention mask to better control multi-modalities and up to the next level with "hyper-modality". It allows us to calculate the transitions of modalities in both directions, unlike another similar work DALL-E Transformer, which used only one direction, "text to image". The proposed "image to right text" direction is achieved by extension sparse attention mask to the right for auto-repressively text generation with image condition without attention to left text.
|
| 25 |
|
| 26 |
+
<img src="https://raw.githubusercontent.com/sberbank-ai/ru-dolph/master/pics/attention_masks.png?token=GHSAT0AAAAAABQH6MSTFSJ6ICVIJOU7S7OAYOYRVGQ" height="40" border="2"/>
|
| 27 |
|
| 28 |
# Authors
|
| 29 |
|