Reference from Azur Lane Character, Sovetsky Soyuz .

Pony is running under different base then usual SD format quality prompt, please look into Ponydiffusion page checkpoint or refer to below instruction.

If you feel your VRAM are not up to SDXL gen, consider try out SD Forge:
https://github.com/lllyasviel/stable-diffusion-webui-forge
Is a improved and way better A1111 which giving you an edge to use SDXL gen with lower VRAM

Simplify about Model:

• Lora version 2.0 is a joint collaboration of Royal Navy contents between several Lora Creator.

• default weight is recommended

• Hires and Adetailer a recommended

• Quality Prompt ``score_9, score_8_up, score_7_up``

• Avoid using negative prompt as much possible, it could affecting the quality of your image.

• The lora are train with extremely low step and unstable due to lack of dataset

• Recommend to run with Anime Confetti/IncursioMeme(Pony)/AutismMix(Pony) and Ponydiffusion

Outfit 1

Outfit 2

About Image Gen:

• The image preview are generate with forge webui.

• Most Image are produce with Model IncursioMeme(Pony).