This model was originally uploaded to HuggingFace / Civitai. If it's yours, please contact us so we can transfer it to your account!
2023/3/11 update
Update dataset and model. Reduce loss to 0.09 using Lion optimizer. If you want to stably generate good results, pls make sure your sampler settings are identical to the following settings (and make sure your clip_skip is set as 2):
eta for DDIM: 1 (0.67~1 should be ok)
eta for ancestral samplers: 1 (must be set as 1)
sigma noise: 1
eta seed noise delta: 31337
Introduction
A LORA model trained with ~28 images of Shiranui Mai by Akiryo. The trigger tags are 'akiryo-mai' and 'shiranui mai'. 0.6~0.8 weights are good. The preview images are generated using latest version of YesMix and EasyNegative embedding.
Download (70.4 MB)
Download available on desktop only
🙈 Heads up! This is not an AI model, but a model addon. This file doesn't produce images by itself – it needs to be used in combination with one of our image AI models. Learn how to do it with our crash course.
Popularity
11k
2k
Info
Base model: SD 1.5
Latest version (v1.5): 1 File
akiryosMai_v15.safetensors
(70.4 MB)
To download these files, please visit this page from a desktop computer.
About this version: v1.5
Update dataset and model. Reduce loss to 0.09 using Lion optimizer.
2 Versions
😥 There are no Akiryo's Mai v1.5 prompts yet!
Go ahead and upload yours!
