Update README.md
Browse files
README.md
CHANGED
|
@@ -42,8 +42,6 @@ Character adapters created by kohya-ss/sd-scripts are compatible with the BERT t
|
|
| 42 |
|
| 43 |
- In an SVO sentence structure, CLIPs focus too much on the subject, text encoders are undertrained for certain verbs and cannot reliably identify the object's position.
|
| 44 |
|
| 45 |
-
- This repo is an experiment to address these issues. The spatial knowledge is explicitly encoded, so the attention modules are not overwhelmed by the task.
|
| 46 |
-
|
| 47 |
## Inference
|
| 48 |
|
| 49 |
```python
|
|
|
|
| 42 |
|
| 43 |
- In an SVO sentence structure, CLIPs focus too much on the subject, text encoders are undertrained for certain verbs and cannot reliably identify the object's position.
|
| 44 |
|
|
|
|
|
|
|
| 45 |
## Inference
|
| 46 |
|
| 47 |
```python
|