<p>I was going to submit this as a merged model, but the LoRA does what it needs to under 160MB. A further training of my<a target="_blank" rel="ugc" href="https://civarchive.com/models/2662268/toony-e621?modelVersionId=2993177"> toony e621 </a>LoRA with even more e621 generalized content, including a selection of top artists and styles. This LoRA is better at recognizing general e621 concepts and very loosely- some artist tags. (19 cherry-picked images max per top artist so don't expect miracles here.) There are about 30 of the top e621 artists represented. Play with it and see what you get! Despite the toon-centric nature of this LoRA, it can handle a wide variety of styles. e621 prompting works great, as well as natural language. Trained without flip_aug, so text generation is preserved.</p>

Files with SHA256: 967b81e96ab5565db24554c1e659ade2d041eb644a5db8f12a67e83134183297