
The goal of this model is to reproduce a Halloween atmosphere, a foggy night with some orange luminous touches. Rather oriented towards the creation of sceneries and landscapes, but it can fit well with characters LoRa.
Originally, this LoRa was meant to be trained for Flux1Dev, but due to a bug during the training process, it didn't take into account the selected model, and therefore the captions and settings were not intended for this PonyXL model.
By the time I claimed the invested buzz, I was unable to release my initially planned model at the beginning of the Halloween contest, and now that a bunch of other good models have been released, there's not much point in redoing the training for Flux. I'm still publishing the final result obtained, which is therefore overtrained. However, I'm publishing several epochs so that you can find the setting that suits you best, so don't forget to play with the LoRa settings to gain flexibility, and lower steps or CFG to reduce the overtraining effect.
Despite everything, SHOW ME WHAT THIS LoRa IS CAPABLE OF!
This is the simpliest way to help me to earn some BUZZ to train new better LoRa.
I would be very grateful if you could donate some Tips to help me if you can. Officially, it would allow me to improve my GPU which is not powerful enough to training locally at the moment. Honestly I know I will never receive enough for this, but it will already be perceived as a very much appreciated comfort and encouragement from you.
Thanks for your interest, and have fun!
描述:
Don't use too much steps,
20 sampling steps are quite enough.
训练词语: Hallomist
名称: Misty-Halloween_pXL_LOREVER-000008.safetensors
大小 (KB): 41864
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success