AiPlaygroundWM

 Hires fix with my check point model PL3rdilxl semireal Sexy kalifa in fishnetstockings Hot hancock in stockings Morrigan aensland : Ready for battle!! Lilith aensland : Waiting for my sister. Naga the serpent in stockings Helen parr . Dating with bob Sohryu Asuka Langley Power girl!!!! Wonder woman in pantyhose Jessica rabbit Lady death Nico Robbin Kiryuin Satsuki  FAMT2A15thR_PLIOR v2 Ivy valentine Yamato Chacha Shadow heart Belldandy  Kasumi Lucy Yeah~~ pretty good results! 1200 * 1504 hires 2x  It takes about 10 minutes!!!!! hires 1.7 about over 5minute!!   All image has exif info. You can find me on  instagram  ,  deviantart  ,  pinterest  ,  patreon  ,  civitai

Applying hires fix (hires) has led to an ongoing issue in which an artificial hexagonal texture has been appearing in the results.   This is an image I created when I first started using SDXL Cropped zoom in for a closer look You can find some artificial traces in a hexagonal shape. I realized this issue was caused by the tiled VAE extension, and I haven't used it since. But yesterday, I think I've found a way to somewhat solve the problem. Check point model is : LobotomyMix Image size : 1200x1504 Hires : 1.7 x Crop and resize Now clean. The solution is to increase the decoder tile size value. Default value is 96. Hires before However, there is another problem. It's that the detail is excessive. It appears that a careful adjustment of the denoising strength and decoder tile size values is necessary. All image has exif info. You can find me on  instagram  ,  deviantart  

Theme is futuristic armor? multiple theme armor? Oni warrior? Queen? Japanese shogun style? Magic rune casting Fantasy knight Wanna piece of me? Sexy Japanese warrior. Trying  Wallpaper ratio Pretty good.

 PL3rdILXLsemireal   I've just completed my first attempt at making ILXL model, just merging not actual traning. The base model is the uncannyValley_ilxl10Noob version. I applied mbw to the lobotomyMix_v1 merging and then applied mbw again to the illustrioussatIOR merging. I adjusted the brightness, contrast, and detail/noise appropriately. The goal was to make the base model slightly darker and the textures more realistic, aiming for something close to realism while still maintaining a high level of prompt comprehension. I aimed to achieve two things: increasing the texture detail while adjusting the facial style to match my desired look. However, it’s not perfect. There was a very slight loss in prompt comprehension, but there’s a small improvement in background or texture expression. (More attempts bring more frustration. The more I merge, the more the results deviate from what I want) For now, this is the best I can do. If you want to save time and achieve images closer...