Artist Style LoRA – jrjresq
Artist: jrjresq
LoRA Type: Artist Style
Trigger Word: jrjr3sq
Recommended Weight: 0.9–1.2 (ideal around 1.15)
Base Model: Illustrious v1.1
Overview
This LoRA is designed to capture the signature artistic look of jrjresq—a style defined by stylized flat and sketched color design and a playful effect.
Training Information
Steps / Epochs: 3870 steps across 29 epochs
Clip Skip: 2
Dataset Size: 86
Optimizer: Prodigy / Cosine
Training was performed on Illustrious v1.1, so models within the Illustrious ecosystem pair most accurately with this LoRA.
Recommended Generation Settings
To get results that match the intended style:
Sampler: Euler_a
Steps: 30
CFG: 4.5
Positive Prompt Suggestions
These optional tags help guide the aesthetic:
film grain, colored sketchNegative Prompt Suggestions
lowres, bad anatomy, bad hands, malformed hands, extra fingers, fused fingers, missing fingers, extra limbs, deformed, disfigured, multiple views, text, watermark, signature, username, copyright, error, jpeg artifacts, old, oldest, jaggy lines, latex, shiny skin, guroCompatibility
This LoRA works well with the following checkpoint:
WAI (Current Version): https://civarchive.com/models/827184/wai-illustrious-sdxl
Support the Artist
Please consider following or supporting jrjresq.
This LoRA was created to help their style reach new audiences across the AI art community.
Respect the original artist and credit them whenever appropriate.
Have a question or suggestion?
I can usually be reached on Discord at: piper260
Description
Dataset:
Refined tags to maintain <225 token/img
Re-scaled all images to fit a similar profile
Removed unnecessary images that did not fit the consistent style
Separated three different styling techniques the artist uses (countershading, simple shading, and flat colors)
FAQ
Comments (7)
Are you interested in doing Koiyaroid's artstyle?
I like the almost "disney-like x kemono" style they have.
https://x.com/koiyaroid
https://kemono.cr/discord/server/1369919167742087188/1369921706314960897
Thanks for asking! Unfortunately, it just doesn’t happen to be a style I’d train. If you happen to throw a dataset together or whatnot I can definitely train it for you though.
@Piper260 Oh, I see... Well, I'm not very knowledgeable in what it takes to make a good dataset. Your model trainings are faithful to the original style it tries to copy. I'm using the zackary sketch style one myself. I thought this stile would be similar enough to that.
@RedBoy_Prime One I've been meaning to get a new version out for too. I setup the dataset pretty quickly so it still has some watermarks etc... That one's definitely on the list. I poked around to some more of the images Koiyaroid does and I kinda spoke too soon. There's some they do that are pretty good. I'll check it out a little more.
@Piper260 So, are you considering on training the model in the end?
@RedBoy_Prime Yeah, thought I’d be able to get to some training before I left, but couldn’t. I’ll be back around the 23rd.
7 months ago ;P did he make more art can you update it to make it much better