This Checkpoint remains equally clear, clean, and creative, with stable body structures and poses, diverse compositions, and no need for AD.
Hope you all have fun with it!
Steps: 15-40, CFG scale: 4-7, Sampler: Euler a/dpmpp_sde/dpmpp2m_sde, scheduler: karras/sgm_uniform/exponential/beat
The VAE is already integrated
My usual settings are: 25, 6, dpmpp_sde, beat, 832x1536,
Prompt words and Danbooru tags are the key to making the most of all Illustrious and NOOB features. Everyone, give it a try. Have a great time!
Description
I used a large number of Flux-generated images to create this upgrade file. It makes generating Asian faces easier, reduces the rate of distorted hands, and delivers sharper focus.
Hope you all have fun with it!
Parameters:Steps: 15-40, CFG scale: 4-7
Samplers: Euler a/dpmpp_sde/dpmpp2m_sde
Schedulers: karras/sgm_uniform/exponential/beat
VAE is pre-integrated.
My go-to settings: 30 steps, CFG 6, dpmpp_sde sampler, beat scheduler, 832x1536 resolution.
Please note: reselling this model or selling merged versions of it is strictly prohibited.
The base model used in the merging process is xRicaMix_ILXL_v5.2. For facial restoration, please switch to XLVAE.