Version History:Beta 1: Initial ReleaseLazyEye-XTC BetaThe goal for this merge was to have a stable and clean model for lora training with good knowledge about personalitiesand also being able to produce natural real-life like output for generation.This model was tuned to be used with DMD2 Lora, CFG=1 at 12 Steps,but it should work with common basic settings like Euler-A, CFG:7, 25 Steps.If you use Character-Loras with DMD2 lower the Character-Lora weight to about 0.65.If you want to use DMD2 with Euler-A or other unifrom schedulers, lower the DMD2 Lora weight (i.e. 0.75).To improve further i need your feedback. Please test and report.Thank you.Additional notes:For example images i simply used the positive prompt of some of the most popular SDXL gens on this site from this year.Just the raw model without Loras, Embeddings or negative prompt. Yes i am a lazy fart.

LazyEye

lazyeye_v10Beta1.safetensors

v1.0 Beta 1

v1.0 Beta 2

LazyEye-XTC Beta 1The goal for this merge was to have a stable and clean model for lora training with good knowledge about personalitiesand also being able to produce natural real-life like output for generation.It should work with common basic settings like Euler-A, CFG:5, 25 Steps.For DMD2 use LCM:1 and 12 Steps. If you use (character) Loras with DMD2 lower the character Lora weight to about 0.65.If you want to use DMD2 with Euler-A, lower the DMD2 Lora weight a bit. Please note that DMD2 is designed for LCM scheduler for best quality but LCM mostly ignores negative prompts. Solution is to use Euler-A or other uniform schedulers with lower DMD2 weight. Writing prompts more precisely may help too (i.e. shirt with no text). Also note that LCM replaces the CFG setting, CFG should be 1 and higher/lower guidance is done via DMD2 lora weight. (up to 1.2).Its not the strongest in NSFW but it does the basic stuff.To improve further i need your feedback. Please test and report.Thank you.Additional notes:For example images i simply used the positive prompt of the most popular SDXL gens on this site from this year.Just the raw model without Loras, Embeddings or negative prompt. Yes i am a lazy fart.Todo / Upcoming:Better promptable face expressions and figure poses

Initial preview release for testing

Files with SHA256: a72f34c4889d17064a67a4651d4f48f110033c6a59f106a767af9388dab59b81