nightknocker commited on
Commit
67da84f
·
verified ·
1 Parent(s): e16bd3a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -2
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