AiPlaygroundWM

 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...

1024 *1024 as the training resolution But  A test that started with the question: How high can you go with generated resolution? LobotomyMix (I guess merged with ilxl v0.1 base) ILXL 1.0 trained with a resolution of 1500 *1500 Assume the limit of the models merged with ILXL 0.1 is 1500 *1500. The resolution implemented was 1400 * 1752 (4:5 ratio) 1304 * 1624 Conclusion : There are a lot of NSFW images, so I can't post them all on the blog,  To summarize the observed patterns, Additional human body generation, human body distortion, stretched proportions (similar to what was created in SD1.5 when I increased the base resolution) Limitations: 1. only one checkpoint was tested                   2. the subject is a monster and I applied the oversized hands prompt. P.S.   All image has exif info. You can find me on  instagram  ,  deviantart