This LyCORIS allows you to generate images with the same style as the animation studio Ufotable.
Version 3.0 has been trained on approximatively 1200 screenshots from the three Fate/Stay Night Heaven's Feel movies, and gave pretty satisfactory results, but everything looked like it came from the Fate/ franchise, which was the main reason why I created the version 4.0.
Version 4.0 of this LyCORIS has been trained on way more images of multiples works from Ufotable.
Firstly, the same screenshots from Heaven's Feel are present, but I added an extra 600 screenshots from the movies.
Then, I added more than 1800 screenshots from Unlimited Blade Works, more than 1200 screenshots from both seasons of the anime Tales of Zestiria the X, 800 screenshots from Kagetsuki/Touken Ranbu, and hundred of screenshots coming from the last three Tales of games openings, God Eater games openings, and some of Fate/Grand Order PV animations which were made by Ufotable.
Unfortunately, with great improvements come a big downside. The LyCORIS seems to have learn that women should have the weird bangs of Alisha, from Tales of Zestiria.
I already tried to retrain the LyCORIS with a hundred images of Alisha removed from the dataset, but it changed nothing.
To remove these weird bangs, I recommend you to add (crossed bangs, bangs, hair between eyes:2.0) to your negative prompt.
The trigger word is ufotable style, and I recommend a weight of 1 for this LyCORIS.
Description
New dataset containing Tales of, Touken Ranbu, and more !
FAQ
Comments (9)
hey uhh why did you change the versions, or does this work fine without us not being able to notice {SD XL- SD 1.5 is what I mean}
The SDXL version was quite catastrophic in my opinion, and I decided to delete it.
If I ever recreate an SDXL version, I will do it in a separate post, as it would make more sense to have a post per model version.
I'm sorry for any inconvenience that may have caused, but I was really not proud of the SDXL version and couldn't bear the weight of this attrocious failure.
Hey, me again, I forgot this since you've updated the description, what model would you say works best with this lora/lycoris?
Hi again ! I mainly used AnyLora and AnythingV5, both of which worked very well with this LoRA
@ToshiBaguette gotcha, thanks!
@ToshiBaguette Hey, got another question, how well does the lora/lyco work with nsfw prompts and stuff like that?
Hey, me again XD. Quick question, what weight should I have other lora/lyco's set at when using this style? Like clothing loras/lycos, character loras/lycos, and stuff like that? Also, am I able to use Easynegative and bad-image in the negative prompts without messing with the style? Or do those not work well with V3 and V4?
Hi there ! Generally, I try to use this LoRA with a weight of 1.0 as much as possible, but sometimes it happens that I have to set it lower, like 0.8, because some characters don't look great with Ufotable's way to represent hair for exemple.
You should be able to use EasyNegative etc without a problem. Personally, I use bad-promptv2 and it doesn't mess the style up
have you ever thought of making a Lora of this style? i think it Will be more popular tha a lycoris
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.