Update README.md

README.md

@@ -4,12 +4,11 @@ datasets:
 - Nacholmo/controlnet-closesttoblack
 ---
 
-# Controlnet model for use in qr codes
+# Controlnet model for use in qr codes (Still on training)
 
-Conditioning only 15% of the pixels closest to black, so as not to affect the luminance of the rest of the image.  ̶I̶t̶ ̶g̶o̶e̶s̶ ̶1̶5̶0̶0̶ ̶s̶t̶e̶p̶s̶ ̶s̶o̶ ̶f̶a̶r̶ ̶a̶n̶d̶ ̶i̶s̶ ̶q̶u̶i̶t̶e̶ ̶p̶r̶o̶m̶i̶s̶i̶n̶g̶
+# 15 jun | New model "control_v7u_sd15_qr_pattern" added to the repo.
 
-### The concept seems to work, now I have to improve the dataset and do the training again, tomorrow I think I will.
-Also I want to make a Preprocessor to have a blur slider. 1500.ckpt is the automatic1111 controlnet extension compatible weight, 1500.yaml is also important.
+Conditioning only 15% of the pixels closest to black, so as not to affect the luminance of the rest of the image. Also I want to make a Preprocessor to have a blur slider. 1500.ckpt is the automatic1111 controlnet extension compatible weight, 1500.yaml is also important.
 
 
 ## 1.5k steps cherry picked examples (not scannable yet)
@@ -24,7 +23,4 @@ controlNet is more important
 ![1.png](https://s3.amazonaws.com/moonup/production/uploads/62fb24dc86456e533456ebd1/8TmIVPjW_fIpOQYYLCmUu.png)
 ![2.png](https://s3.amazonaws.com/moonup/production/uploads/62fb24dc86456e533456ebd1/pxMIsT-0GepdXgdsyDknl.png)
 ![3.png](https://s3.amazonaws.com/moonup/production/uploads/62fb24dc86456e533456ebd1/dJ0OaHZ3zKJKhaDYZYCCn.png)
-![4.png](https://s3.amazonaws.com/moonup/production/uploads/62fb24dc86456e533456ebd1/iGzLqg7sFrsyQKYs5f4PN.png)
-
-
-# New weights up to 7k steps
+![4.png](https://s3.amazonaws.com/moonup/production/uploads/62fb24dc86456e533456ebd1/iGzLqg7sFrsyQKYs5f4PN.png)