Update README.md

This commit is contained in:
Extraltodeus
2024-05-15 02:19:10 +02:00
committed by GitHub
parent ae5c8c973d
commit 134e1e8f51
+1 -1
View File
@@ -16,7 +16,7 @@ My own version "from scratch" of a self-rescaling CFG / anti-burn. It ain't much
- But also to apply a custom modification on cross attention middle layer 0. The "patch_cond" and "patch_uncond" toggles are about this modification.
- While the modification is definitely not very ressource costy, the light patch uses less VRAM.
- The multiplier influences the cross attention and reinforces prompt-following. But like for real. Works better with the "light patch" toggle ON.
- I have only tested it with SDXL.
- I have ~~only~~ mostly tested it with SDXL.
- You can find a grid example of this node's settings in the "grids_example" folder.
- For some reason the Juggernaut model does not work with it and I have no idea why.
- Attention modifier presets! Try them with the preset loader!