I trained this LoRa with screenshots from the 「Fate/Grand Order」Memorial Movie 2023

I used the same training images as Fate GO: Memorial - Illustrious Style. I got rid of some images that in my opining where not helping the overall concept. The purpose of this concept LoRa was to make it able to recreate the illustration feeling rather that the actual drawing style.

I'm not sure if I succeeded but I liked the outcome. Check it out and let me now what you think.

This model is a bit different than my previous Ufotable LoRa. The training images are different.

Activation Prompt: F4t3M3m0C

Recommended Prompts (For better illustration feeling): fantasy, novel illustration, cover image

Negative Prompt: keychain, lowres, worst aesthetic, (worst quality, bad quality, low quality:1.2), bad anatomy, old, signature, watermark, artist name, 3d

*This ^^^ negative prompt works best.

To get the same results like the sample images follow this prompting formula: Your Prompt + BREAK Prompt + LoRa + Recommended Prompts

Break Prompt: BREAK character_concept, cowboy_shot, (dutch_angle:1.25), masterpiece, best quality, amazing quality, very aesthetic, absurdres, modern, recent, newest

Prompt Example: 1girl, solo, virgin ribbed sweater, destroyer sweater, dark violet green sweater, navel, thighhighs, smile, looking at viewer, library, thick thighs, wide hips, large breasts, curvy, BREAK character_concept, cowboy_shot, (dutch_angle:1.25), masterpiece, best quality, amazing quality, very aesthetic, absurdres, modern, recent, newest, <lora:FateGO-Memorial2023_IL_Concept_epoch_7:1> F4t3M3m0C, fantasy, novel illustration, cover image

*This prompt formula works best if you are using reForge or StableDiffusion locally. Based on my tests it does not work as good if you generate them here on the site.

Weight: 1

Sampler: Euler a - Automatic

Recommended Base Models: RoseMIX_XL

Make sure to post your favorite generations on the Gallery by simply clicking +Add Post button.