Update README.md
This commit is contained in:
@@ -24,12 +24,6 @@ Requires pytorch 2.3 and above.
|
||||
|
||||
Changing the UNET temperature allows to obtain better results a different resolutions. While it is not the full solution to the scaling issues of Stable Diffusion, it is a strong clue indicating the possibility to sample at much higher (or lower) resolutions.
|
||||
|
||||
# Patreon
|
||||
|
||||
Consider giving an incentive to contributors.
|
||||
|
||||
https://www.patreon.com/extraltodeus
|
||||
|
||||
# Examples
|
||||
|
||||
### Here using SDXL at a resolution of 328x328. First row temperature at 1, second row using dynamic scaled attention:
|
||||
@@ -48,8 +42,9 @@ The temperature was applied to all layers except input 1 and 2, output 9, 10 and
|
||||

|
||||

|
||||
|
||||
### Other simple example with SD 1.5, with/without are obvious enough (these two are workflows):
|
||||
|
||||

|
||||
# Patreon
|
||||
|
||||

|
||||
Consider giving an incentive to contributors.
|
||||
|
||||
https://www.patreon.com/extraltodeus
|
||||
|
||||
Reference in New Issue
Block a user