Use -Realvis versions together with RealisticVision 5.1 for replicable results.Suggested weights Weight: 0.6 - 0.7 Bleeds quite a bit into the model. Was trained on an internal model so you wont get the exact crisp results as in the promotion images. Models like cyberrealistic, realisticVision and photoMovie tend to come close with the original LoRA. Otherwise use the -RealVis version.

Emma Watson 2009-2010

This version is tuned for RealisticVision v5.x instead of internal models.Suggested weights Weight: 0.65 - 0.7 Bleeds into the weights of the underlying checkpoint a lot, which means you might have to fight for some changes quite a bit.This is an early revision. I will post updated versions, when the internal version is a few weeks old.

Files with SHA256: 972ce0b9b2326a5d6680161fb109a8bfc0bcb69aa76c37748f46a0a07dd64d02