Type | |
Stats | 2,904 |
Reviews | (405) |
Published | Sep 28, 2023 |
Base Model | |
Hash | AutoV2 50EC9BF265 |
My First SDXL Model! 🎉
Incorporating Faeia's fantastic FaeTastic, a huge mix of anime and cartoon focused models, and three or four LoRA I trained (using the Civitai on-site LoRA trainer!) and merged in block by block, I finally feel like I've accomplished my goal for my my first SDXL model - cartoony, semi-realistic outputs, with an SD 1.5 feel, but with the flexibility of SDXL prompting.
Like my other models, I tried my best to fix hands using some of the common block-merge hand-repair techniques, editing the IN00, IN01, IN02 blocks, and they've turned out not bad, have seen worse, still not great. Sometimes you've just gotta roll the dice (a hundred times)!
What's it good at?
It excels at anime and semi-realistic portraits. It does quite good nsfw (softcore), with good... lady parts (special attention was paid!), but it doesn't really do photorealistic - that's been merged out.
Check my prompts for some examples of what it's best at!