SamDoesArts (Sam Yang) 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 ☕
There are already countless models for this artstyle, but I still wanted to test out how LoRA's can handle it. I also wanted to experiment with AnyPastel (or Anime Pastel Dream - Soft). This LoRA didn't come out super strong, so it has the right flexibility to get a style that's closer to Sam Yang's on AnyPastel, while still reminding of him on other models. Check the examples (mainly the model hash) to get what I mean. Triggers with sam yang and I suggest AnyPastel as base model (or, if you don't care about having a more matching artstyle, AnyLoRA or AbyssOrangeMix2). Use weight=1 for the offset version or 0.65 for the original (check "original" tab for a comparison).
The pic of Melina is also using my Melina LoRA.
Pic 3 and last 4 ones (all the realistic ones) have been made by kaynite using NED.
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 according to the instructions (by default it's
:1)
Description
resized to 32 dim
FAQ
Comments (24)
why does it this lora keeps showing up from time to time as "updated" in the newest filter even tho it hasn't been updated?
I added the 32dim version. It's the second tab, so maybe you didn't notice.
@Lykon oh right, MB, it just that I saw it happening before, and checked and there was nothing new or changed so I thought it was that again, seen it happen with other models too, weird
Any changes in the 32dim from the offset and/or original?
What VAE is used for this model?
just go with the baked vae of the base models I used. In this case it's Anime Pastel Dream (Soft) and AnyPastel + wd vae
do you have any info on how you train the LORA to have an offset? that always confused me
it's just a multiplier I add at the end to scale them up or down.
wonder if i could suggest genkai zero/darkartskai or zeronis for possible models?
I'll think about it
I was very curious, who is "zeronis"? :)
I was very curious, who is "zeronis"? :)
even though I downloaded all three and put them in lora folder why does it keeps saying "Couldn't find Lora with name samdoesartsSamYang_normal"... Please help...
You should put the file into models/Lora and then if the file si XXX.safetensors you should use <lora:XXX:1> in the prompt. Also if you did that correctly you should see the lora listed in the lora tab as I showed in the video you find in the description
@Lykon you add right_file_size lora file names end, thats why... Problem solved... :)
Will you be updating this for sdxl? Probably my favorite lora
not sure it would be needed, anyway my Art Diffusion XL model already includes this style (even if it's just an alpha).
Oh ok I thought loras from 1.5 couldn't be used with sdxl, but ok I'll look forward to the full release of your model
@Asscancer you're right, they can't be used with xl. Anyway you can already test Art Diffusion XL, I've added Sam Yang style there.
Fantastic.
Please add flux version)
Nice