creator: deatharms2010

Reference from Azur Lane Character, Sovetsky Soyuz .

llustrious & NoobAI running same prompt like of general SD1.5 and SDXL.For more information about this base model, please look into below link:https://civitai.com/models/795765/illustrious-xlhttps://civitai.com/models/833294?modelVersionId=1116447

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

https://civitai.com/models/257749/pony-diffusion-v6-xl

Commission request.

to request any character commission, please click here

If you wish to just support me with single dollar please provide me 1 Kofi at here, Thank you!

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.

Illustrious Recommendation:

• default weight is recommended.

• Hires and Adetailer a recommended.

• Quality Prompt ``masterpiece, best quality``.

• Recommend to run with Fallen's PaSanctuary

Pony Recommendation:

• 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.

• Recommend to run with Honey Mix [XL]/IncursioMeme(Pony)/AutismMix(Pony) and Ponydiffusion.

Simplify about Model:

• 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 due to burn behavior.

• the color of character hair and first outfit will not be consistent due to low step training.

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

This model has been train with lower step due to easily overbake, as such the gen of main outfit will only able to gain a similar theme of main outfit but not entire of it design.

full main outfit prompt:

https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/fe0786ab-f277-41d8-b593-daa8c003277c/width=525/fe0786ab-f277-41d8-b593-daa8c003277c.jpeg

remove or move fur hat and fur-trimmed coat to negative:

https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/826a6acd-d60c-4b1a-b864-a58cfb07af8a/width=525/826a6acd-d60c-4b1a-b864-a58cfb07af8a.jpeg

the second outfit should be fine, except the side slit are unlikely work at most time:

https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e299a62b-c1d9-40cb-b05b-b83878006a40/width=525/e299a62b-c1d9-40cb-b05b-b83878006a40.jpeg

About Image Gen:

• The image preview are generate with forge webui.

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

• Some of gen are run with Unpublish Custom Style