Update README.md

README.md

@@ -1,3 +1,18 @@
 Experimental merge of NoobAI-XL 1.0, introducing natural language prompting. No Lightning or other low-step bake-ins. Too early to tell, but I do notice it performs measurably worse at multi-subject outputs that exceed more than 2-3 characters. Some tag associations get lost in meaning with natural language being present now. Despite that, I find the current state of the merge "fun". As there is most likely room for improvement, what I will initially upload will be with the caveat that it's an early version and in no way final. Euler A + Beta scheduler seems reasonably safe. Due to the merging process and addition of natural language prompting, some lower tag-count characters and concepts may require some upweighting and/or supporting tags. Some NSFW interactions require really delicate prompting to get what you want.
 
-This model is give or take capable of the same content as NoobAI-XL 1.0, which consists of most if not all of Danbooru and E621 posts, given the respective cutoff dates. Meaning this checkpoint can and will produce NSFW content!
+This model is give or take capable of the same content as NoobAI-XL 1.0, which consists of most if not all of Danbooru and E621 posts, given the respective cutoff dates. Meaning this checkpoint can and will produce NSFW content!
+
+[November 11th, 2024]
+
+EasyFluffXLVpredIter is a further along checkpoint that utliizes NoobAI-XL's 0.5 V-Prediction checkpoint to convert the model to Vpred, which brings some advantages ranging from better colors and better prompt following. It also merges in Itercomp. I have not thoroughly tested but do notice improvements compared to without.
+I will try to upload the versions without Itercomp later, so there will be more options available and users can judge which one suits their preferences better.
+Epsilon-prediction checkpoints are a WIP as it's hard to bring parity in performance between the two.
+LoRas trained on Noob 1.0 should still work adequately on this merge. If training a LoRA, I still reccomend training directly on NoobAI-XL 1.0 or NoobAI-XL 0.5 V-Prediction.
+
+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.
+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.
+
+