<h3 id="go-to-https:huggingface.cozatochueasyfluffxl-for-v-prediction-checkpoints-that-i'm-not-ready-to-upload-here-yet.-also-a-version-of-pre-is-available-with-less-artifacts-on-fine-details.-nh21oftvu">Go to <a target="_blank" rel="ugc" href="https://huggingface.co/zatochu/EasyFluffXL">https://huggingface.co/zatochu/EasyFluffXL</a> for V-Prediction checkpoints that I'm not ready to upload here yet. Also a version of Pre is available with less artifacts on fine details.</h3>Experimental merge (plus training of several LoRas consisting of several thousand diverse natural language captioned images) of <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1022833">NoobAI-XL 1.0</a>, 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!

Files with SHA256: d394e263dbccfa22cea46669e9455af30faa179e3b56c23832257e86061fd1ec