Create README.md
Browse files
fixed-textencode-node/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Replace your nodes_qwen.py file with one of these, which will improve your "native" TextEncodeQwenEditPlus node.
|
| 2 |
+
|
| 3 |
+
* It increases the number of image inputs from 3 to 4.
|
| 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.
|