Phr00t commited on
Commit
a16b312
·
verified ·
1 Parent(s): 8a5bcdc

Update fixed-textencode-node/README.md

Browse files
Files changed (1) hide show
  1. fixed-textencode-node/README.md +1 -1
fixed-textencode-node/README.md CHANGED
@@ -4,6 +4,6 @@ Replace your nodes_qwen.py file with one of these, which will improve your "nati
4
  * It slightly tweaks the system input to be a bit more versatile.
5
  * It fixes an issue where the image would get cut off and mirror itself sometimes by cropping better.
6
 
7
- The "original" allows you to input a "target_size" which will scale the input images to better match your output size (which can fix zooming issues).
8
 
9
  v2 takes a latent as an input, which should contain your target image size. The node will automatically scale input images to best match that target latent size. If you do not provide a latent input, it will not do any scaling.
 
4
  * It slightly tweaks the system input to be a bit more versatile.
5
  * It fixes an issue where the image would get cut off and mirror itself sometimes by cropping better.
6
 
7
+ The "original" allows you to input a "target_size" which will scale the input images to better match your output size (which can fix zooming issues). Usually setting it to 90% of your largest image size works.
8
 
9
  v2 takes a latent as an input, which should contain your target image size. The node will automatically scale input images to best match that target latent size. If you do not provide a latent input, it will not do any scaling.