Merged model for anime style. No VAE. All image are generated in Stable Diffusion A1111 web-ui at 768x1024, 18 step, 11cfg, Sampler: DPM++ 2M Karras. No face restore. All sample image have prompt attached. Suggested negative: (worst quality, low quality:1.5), bad anatomy, fewer digits, text, old, signature, watermark, username, artist name, bad proportions Model made for simple and advance prompt. Check my other models. You can marge this model with other model, but giving back-link to this model on your description. About model: This model is intended for free use and free sharing image. Not use it for selling generated image or merged checkpoint. This is long time merging, testing, merging, etc... so don't ask for details because i don't remember all of it( sorry). About you: Feel free to test and give feedback, detailed feedback get me know what work or not work, so i do my better to fix on next release. |