
Posted for civitai.com and tensor.art only
Each of these LoRAs take me dozens of hours and GPU usage out of pocket. Every review is appreciated and encourages me to do more of these.
-MoC
See about this version for model details ?
?Biography?
?Mila M?
Mila M Rumcola, also known as Mila M, Mila Calzini, Mila Piruzi, Rumcola, StunningAna, and Vicky Z, is a Ukrainian model and former webcam performer. Born on September 10, 1990, in Ukraine, she gained popularity in the industry.
Mila M, at the age of 33, has a slim physique with brown hair and captivating green eyes. Standing at a height of 5'8" (or 172 cm), she is known for her natural beauty and captivating appearance. Her body measurements are 34-22-35, with a bra size of D.
During her career, which spanned from 2013 to 2016, Mila M established herself as an adult model, starting at the age of 22. Her unique features and charm earned her a dedicated fan base.
Mila M has a tattoo on her left wrist and ear piercings, which add a touch of individuality to her overall look.
描述:
-
The earlier versions of this model was my first SDXL LoRA attempts. This version is with my latest training methodology.
-
Dataset gathered and trained on a single concept (model had a short active career period).
-
~7.5 hour Kohya_ss training in 16530 steps across 19 epochs @base dim (rank): 32.
-
1248x1248px training resolution base
-
Used a wide variety of resolutions in training data, however by far the most common bucketed resolution was @ 1216x1216px.
-
Comparing results and my datasets since the v1 and v1.05 versions of this LoRA to my other LoRAs have given me even more ideas on quality improvements. Stay tuned...
The earlier versions of this model was my first SDXL LoRA attempts. This version is with my latest training methodology.
Dataset gathered and trained on a single concept (model had a short active career period).
~7.5 hour Kohya_ss training in 16530 steps across 19 epochs @base dim (rank): 32.
1248x1248px training resolution base
Used a wide variety of resolutions in training data, however by far the most common bucketed resolution was @ 1216x1216px.
Comparing results and my datasets since the v1 and v1.05 versions of this LoRA to my other LoRAs have given me even more ideas on quality improvements. Stay tuned...
训练词语: ohwx
名称: MilaM_SDXL_v1.1.safetensors
大小 (KB): 223096
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success