Update README.md

README.md

@@ -10,8 +10,8 @@ LoRas trained on Noob 1.0 should still work adequately on this merge. If trainin
 
 Generally safe settings are 3-6 CFG, Euler A, and Beta sheduler.
 
-I reccomend using an up-to-date Forge/ReForge as they automatically detect the "WithKey" version as V-Prediction/ZSNR. Forge currently doesn't have  RescaleCFG extension built in, but ReForge does. However I have included a backport of RescaleCFG for Forge in this repo that may work unless the code has changed since creating it. Extract it into extensions-builtin.
+I reccomend using an up-to-date Forge/ReForge as they automatically detect the `vpred` and `tznsr` key I've added to the state_dict of both models and inference as V-Prediction/ZSNR. Forge currently doesn't have  RescaleCFG extension built in, but ReForge does. However I have included a backport of RescaleCFG for Forge in this repo that may work unless the code has changed since creating it. Extract it into extensions-builtin.
 Alternatively I reccomend using an up-to-date ComfyUI. As of https://github.com/comfyanonymous/ComfyUI/commit/8b275ce5be29ff7d847c3c4c2f3fea1faa68e07b ComfyUI will also automatically detect that the model is V-Prediction/ZSNR and set it for you.
-If you use the model without the key, you can still set V-Prediction and ZSNR via the ModelSamplingDiscrete node in ComfyUI. I reccomend experimenting with the RescaleCFG as it can help blurry backgrounds and overblown colors. But avoid going too high.
+If for some reason the autodetection doesn't work or you are on an older ComfyUI, use the ModelSamplingDiscrete node to set V-Prediction and ZSNR.