
I've had good generation consistency with Auto/Kerras/Polyexpo on the SDEs and Euler A at LoRA: 0.8 /trigger: 1.1. When it comes to Clip, both 1 and 2 produce good results, though I would recommend 2. Overall, I'm finding Euler A gives the best results.
Prompting -- you can edit the metadata, since A1111/Forge saves it as an external JSON file, to put the LoRA name in the activation text field and adjust the weights to suit the model checkpoint you're using.
For the most part, while I do use other models if I'm not seeing what I want, I will mainly use my checkpoints: UberBoop (SD), XLBoopV2 (SDXL), Equus(Pony), and Fluxzilla (Flux).
Selah Victor
Born April 22, 1981, Bakersfield, California, USA
Height 5′ 7″ (1.70 m)
Selah Victor (say-la) was born in Bakersfield, California, one of eight children. She studied Theater at The University of California, Irvine, and at The University of Birmingham, England. In addition to her film and television work, Selah has been seen in theaters around Los Angeles, including Garry Marshall's Falcon Theater, Second City, Actors Co-op, and Theater West.
描述:
训练词语: (Selah_Victor:1.1)
名称: Selah_Victor-SD.safetensors
大小 (KB): 36980
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success