Screen-chanTV Merge Illustrious
Steps: 15-30+
CFG scale: 3-7
Sampler: euler a or DPM++ 2M Karras
Vae Included
positive prompts:
newest,very awa,masterpiece,high quality,high resolution,amazing quality,best quality, good lighting,detailed eyes,anime coloring,anime screencapnegative prompts:
worst quality,bad quality,low quality,lowres,scan artifacts,jpeg artifacts,sketch,bad quality,jpeg,artifacts,signature,username,text,logo,bad anatomy,artist name,artist logo,extra limbs,extra digit,extra legs,extra arms,blurry background,simple background Description
FAQ
Comments (4)
V2.0 is legitimately one of the best anime models currently on the site (and I try most of the new models that pop up). I'm getting especially good results with seeds 3 and beta57 but it seems to play well with a lot of sched/sampler combos. I do use a custom clip but, right out of the box, this model has excellent prompt adherence and unusually high resistance to the typical sdxl/ill/pny errors so it requires fewer negative prompt tokens which can degrade the final output. It's a very solid model.
You labeled v3.0 as v1.0 lol
That's not it; what's happening is that this would be version 1.0 of Anima, which is a different model.
@CuervoTensor ah