modèles/Eldritch Digital Art - v1.3

Eldritch Digital Art - v1.3

11/4/2025

5:22:32 PM

Mots-clés et tags associés

concept sketches,digital painting,digital painting lora,eldritch digital art,eldritchadam,gestural digital painting,loose digital sketch,lora,matte paintings,sdxl 1.0,style,v1.3

A Samhain celebrant wearing a mask and crimson robes, face half-lit by the glow of a jack-o'-lantern and lantern on an autumn table.

A still life featuring a steaming cup of coffee surrounded by small pumpkins, an open book, a lit candle, and occult-themed objects in a dimly lit autumnal setting.

A freckled young hedge witch with curly auburn hair, sunflower tattoo on her neck, and glowing herbs behind her ear, surrounded by sunflowers in an autumn setting.

Prompts recommandés

Digital Painting

Paramètres recommandés

samplers

DPM++ SDE Karras

steps

cfg

4.5

Conseils

Write 'Digital Painting' as a prompt for best results.

Use this LoRA for fast, loose, gestural digital art without requiring photorealistic detail.

This model preserves broad subject matter flexibility without needing artist name prompts.

Points forts de la version

fixes some face issues and a few other edge cases

version 1.3 - brings better portraits (still very loose and gestural!) and aerial scenes.

Just write 'Digital Painting' and your straightforward prompt ideas

Fine detail? Meticulous rendering? Photorealism? Sometimes you don't want any of those - you just want a fast digital sketchy loose feeling. With this LoRA, you can crank out those quick Cintiq-drawn matte paintings and concept sketches all day long.

Probably, this is the style I should have been pursuing when training LaxPeintXL, but kept steering away toward greater detail and rendering. That model converged a lot with ClassiPeintXL. So let's take a step back, start over, and go all-in for that digital sketch aesthetic.

Why train a model like this? Can't you get this look out of the base SDXL model?

You can get much this look with the right prompts straight out of the base SDXL model using artist names like Marc Simonetti, Ismail Inceoglu, Craig Mullins etc. But these artist prompts also tend to push the subject matter toward particular time periods or genres. This LoRA will get that loose gestural digital look without needing to use any artist's name, and so retain much broader subject matter flexibility. Period piece, sci-fi, still life, landscape - prompt for anything and consistently get this same aesthetic.