Arcane Style LoRA
Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
Greatest show of 2021, time to bring this style to 2023 Stable Diffusion with LoRA.
This should be used with AnyLoRA (that's neutral enough) at around 1 weight for the offset version, 0.65 weight for the original one (with highres fix R-ESRGAN 0.4 denoise for better results). Trigger is arcane style but I noticed this often works even without it.
Allow me to remind this is not a character LoRA (I didn't tag characters in the dataset). Still ,as you can see, it can get pretty close to the original characters with accurate prompting. This should also work with most of my character LoRA's (used Ahri and Lucy to test).
Please enjoy.
How to use LoRA's in auto1111:
Update webui (use
git pulllike here or redownload it)Copy the file to
stable-diffusion-webui/models/loraSelect your LoRA like in this video
Make sure to change the weight if needed (by default it's
:1)
Description
FAQ
Comments (20)
why is my pic so blur,please
probably the vae. Use anything4 vae, not anything3. Like never use anything 3 (it's basically like having no vae).
This was actually so much better than expected as it helps the composition so much even when added with other styles or embeddings! Using with dreamshaper has been pure gold!
really? Show me!
I try to reach the same results but I only get this
and you give 2 stars because you're unable to get the same result probably due to your settings? Other people reproduced the result just fine, check the other reviews.
bro change your size from 512x512 to 512x768 and then after use high res fix (4x anime sharp) .. also use cfg scale 7.. the result is your fault not the loras!!!
seems mods changed it to comment.
@Lykon Sorry, it's my fault, I'm new to the platform, I thought it was just a simple comment. What I am looking for is help to reach the results that they recovered, I really liked the lora
@plsdontultme Ty bro, I'll try to do it as you mention.
@plsdontultme what's high res fix (4x anime sharp)? is there a guide for this? thanks.
@zdig no prob. Feel free to ask for help. Just don't give bad reviews when you do so :)
why am I getting a noise image that looks more like a normal map of the ground? (using InvokeAi)
never used invokeAI, but you're probably doing something wrong. Are you using this as a model instead of lora?
@Lykon hey, I've found out that InvokeAi doesn't support Lora yet, maybe in the next updates
@raphaelcatossi826 Yeah it's a bummer how slow they are with updates. I've switched to Automatic for now.
@Lubenoodle it supports lora now btw
为什么我是这样的
How can I get better faces? For some reason, my faces always look kinda weird
Are you using the right base model? Are you making full body images? That's a common problem in SD yhen, use highres fix and/or inpainting of the face only at higher res. Also disable the face fix, ad that'll ruin everything