
Artist Style LoRA – Letodoesart
Artist: Letodoesart
LoRA Type: Artist Style
Trigger Word: l3todo3sart
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 Letodoesart—a style defined by soft cinematic tones and a mix of stylization.
Training Information
Steps / Epochs: 3024 steps across 30 epochs
Clip Skip: 2
Dataset Size: 71
Optimizer: AdamW8Bit / Cosine w Res
Training was performed on Illustrious v0.1, 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:
colored sketch, dramatic lighting, cinematic, film grainNegative Prompt Suggestions
(female:1.35, nipples:1.35), worst quality, lowres, bad anatomy, bad hands, latexCompatibility
This LoRA works well with the following checkpoint:
WAI (Current Version): https://civarchive.com/models/827184/wai-illustrious-sdxl
StableMond (Current Version): https://civarchive.com/models/1280186/stablemondai-sdg
Support the Artist
Please consider following or supporting Letodoesart.
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
Implemented Leto Varian
Improved the dataset with multiple upscalings
Retrained through a new preset
Began using StableMondAI model with Euler a / SGM Uniform with a 4.0 CFG and upscaling.
FAQ
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.




