Update README.md

2024-04-15 19:32:08 +02:00
parent b2dde6753b
commit 22490695ed
1 changed files with 3 additions and 3 deletions
@@ -11,9 +11,9 @@ Updated:
 15.04.24

 - Added "no uncond" node which completely disable the negative and doubles the speed while rescaling the latent space in the post-cfg function up until the sigmas are at 1 (or really, 6.86%). By itself it is not perfect and I'm searching for solutions to improve the final result. It seems to work better with dpmpp3m_sde/exponential if you're not using anything else. If you are using the PAG node then you don't need to care about the sampler but will generate at a normal speed. Result will be simply different (I personally like them).
- To use the [PAG node](https://github.com/pamparamm/sd-perturbed-attention/tree/master) without the complete slow-down (if using the no-uncond node) or at least take advantage of the boost feature:
-  - in the "pag_nodes.py" file look for "disable_cfg1_optimization=True"
-  - set it to "disable_cfg1_optimization=False".
+- To use the [PAG node](https://github.com/pamparamm/sd-perturbed-attention/tree/master) ~~without the complete slow-down (if using the no-uncond node) or at least take advantage of the boost feature:~~
+  ~~- in the "pag_nodes.py" file look for "disable_cfg1_optimization=True"~~
+  ~~- set it to "disable_cfg1_optimization=False".~~ This is not necessary anymore because the dev modified it already :)
 - For the negative lerp function in the other nodes the scale has been divided by two. So if you were using it at 10, set it to 5.
  
 # In short: