Disclaimer:
This model is a demonstration of the training results and I am not responsible for any images generated by this model. Please handle the generated images with care and at your own risk.
I generally do not support the use of this model to generate any adult content. When using this model, users should abide by local laws and regulations and shall not violate any other's right to reputation, privacy or portrait.
Resale of this model is not permitted. Any commercial use is not permitted.
Any use that negatively affects the development of the AI community or any use that violates the rights or privacy of individuals is prohibited.
Use at your own risk!
本人原则上不支持使用此模型生成任何成人内容。用户在使用本模型时，请务必遵守当地法律法规，勿侵犯他人的名誉权、隐私权或肖像权。
Tips
model used: chilloutmix_NiPrunedFp32Fix
use hires.fix when generating full body image/when face distorted
Settings I prefer: (Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 7, Hires upscale: 2, Hires upscaler: Latent (bicubic), Denoising strength: 0.8)
Some useful prompt (or negative) for v2-5:
looking_at_viewer
mole 痣
mole_on_cheek 脸颊上的痣
mole_under_mouth 嘴巴下的痣
Description
Retrain using different captioning style, same v2 parameter with lesser steps, not sure if it perform better, try it out yourself.
FAQ
Comments (1)
Is there a mistake here somewhere? The LORA file is tiny plus when i run it stable diffusion says it can't find the lora with that name
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.