
Get early access to build and test build, be able to try all epochs and test them by yourself on Patreon or contact me for support on Discord
To support me you can buy me a coffe or commission me at https://ko-fi.com/antonioriolo
Recommended settings:
-
Make sure you are aware on the usage instructions of LORA
-
Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers)
-
CFG Scale : 5 to 10
-
LORA weight for txt2img: reccomended 0.5-0.9.
-
Keys: top_view_perspective
My advice is to use the keyword with 1.3 weight and atleast 0.5 on the model.
Doesn't work with any other model, i tryied many, it worked with most of them, but with some of them didn't reach the expected perspective in the generated images.
It's very likely to get a selfie with this perspective since most of the training images are selfies.
Seems to work very well with anime.
Enjoy!
If you'd like to support my efforts and have access to early and bleeding edge builds, please think about joining my Patreon: https://www.patreon.com/betterCuteAsians
描述:
训练词语: top_view_perspective
名称: top_view_perspective-10.safetensors
大小 (KB): 147572
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success