
I actually only trained this lora for myself, but since I like it,
I would like to make it available to you as well.
The Lora is not perfect, but it does the job. Maybe I will work on a 2nd version if there is interest.
Works best with portraits.
Trained on 82 photos for 16 epochs.
_______________________________________________________________________________________________
Recommended Settings:
-
Distilled CFG Scale:
-
2-3.5
-
-
Sampling method and Schedule type:
-
I personally use DEIS/Beta.
You have to decide for yourself if other combinations deliver better results.
-
-
Steps:
-
30
-
-
Resolution/Aspect Ratio:
-
The Lora is trained on 1:1 aspect ratio.
You will have to test if other aspect ratios work.
-
-
Lora Weight:
-
1-1.3
But it depends on your own taste.
-
-
Trigger:
-
No trigger.
But you can use sentences like
“The photograph is taken with a ring light, which creates a soft, even lighting effect around her face, highlighting her features.”
to strengthen the effect.
-
_______________________________________________________________________________________________
I would be very grateful if you could leave me your feedback here
and post pictures with your results. I would really appreciate it if you guys would leave me a small Buzz tip here so I can train more Loras.
描述:
训练词语: The photograph is taken with a ring light, which creates a soft, even lighting effect around her face, highlighting her features.
名称: Flux-Ring Light.safetensors
大小 (KB): 17808
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success