Trained by NoobAI-XL, With new training method. It should perform better than my past LoRA models.Plus: Past models RETRAINING are in progress now.IF you want a dedicated and beautiful output image, I suggest to follow these few rules:<ul><li>Use the BASE model what I use for training to generate your image, I will mention it at the begining of the description. (IF you strongly not willing to download an new model. don't use PONY, it will perform extremely bad. please use animagineXL, somehow it should work.)</li><li>Open the Hires-fix. (optional)</li><li>The original datasets what I use for training were no more than 2048px, so theoretically it will perform bad images when you trying to generate oversize images.</li><li>The steps for generate image should be greater than 24 steps.</li><li>This is an anime model, so it SHOULD performed very bad when generating realistic images.</li><li>If you are a ComfyUI user, Almost every images I post on CivitAI has my workflow.</li><li>This guide was concluded with my experience so it is still in updating, find any problems please leave me a comment.</li></ul>Im poor at English, so please remind me if I had any typo or some confuse description&gt;&lt;Have any problems just leave me a comment :)

Files with SHA256: f747ad31a460a3e360bf7721d9ef2f6f2b463bd1fffe0b69afdf5df8f8ba8048