Hello, everyone!

I'm excited to share my first LoRA featuring Molang, the adorable rabbit. This model captures Molang in various poses and styles, perfect for creating heartwarming and cute images.

Recommended Model: For the best results, I suggest using this LoRA with the SD 1.5 CHECKPOINT model:
Cuteyukimixadorable Style

Keyword List for optimal results:

• no humans

• rabbit

• simple background

• animal

• animal focus

• :3

• blush

• solo

• looking at viewer

• blush stickers

• bird

• chick

• smile

• standing

• closed eyes

• holding

• full body

• solid circle eyes

• open mouth

• pink background

• white background

• blue background

• food

• star (symbol)

• sky

• ._.

• fruit

• :<

• cloud

• monochrome

• heart

• checkered background

• closed mouth

• yellow background

• rainbow

• food focus

• artist name

• signature

• strawberry

• grass

• green background

• creature

• one eye closed

• bear

• sparkle

• moon

• purple background

• crescent moon

Test Configuration:

• Sampling Method: Euler A, DPM++ 2S a

• Scheduler Type: Automatic, Karras

• Sampling Steps: 30 to 60 depending on the sampling method, with 40 being an optimal choice for most cases.

High Resolution Fix (HIRES FIX):

• Upscaling Model: R-ESRGAN 4x+ Anime6B

• Hires Steps: 10-20 (I recommend experimenting for best results)

• Denoising Strength: Between 0.5 and 0.7

• Upscale by: x2 (adjust based on desired resolution and texture optimization)

Additional Recommended Settings:

• Clip Skip: 1

• CFG Scale: 7

• LoRA Strength: Between 0.5 and 0.8 (using 1 can lead to too many Molangs popping up... haha!)

I hope you enjoy this LoRA as much as I enjoyed creating it. Looking forward to sharing more models in the future!

Cheers and happy generating!

¡You can support me by clicking here!

描述:

• Face Generation: The model generally generates Molang’s face well, but occasionally creates extra parts or details that weren't intended.

• Extra Animals: Sometimes, additional animals or elements appear in the image. This behavior seems to vary depending on the base model used.

训练词语: no humans,rabbit,simple background ,:3