modelos/Aesthetic LoRA for FLUX - 10R 3E CDO-0.5

Aesthetic LoRA for FLUX - 10R 3E CDO-0.5

8/30/2025

10:06:02 AM

Palabras Clave y Etiquetas Relacionadas

10r 3e cdo-0.5,advokat,aesthetic lora for flux,anime,flux,flux.1 d,flux workflow,girls,impressionist landscape lora,lora,lora model,painterly,semirealistic,style,mujer

Close-up portrait of a fierce Sith Lord woman with piercing blue eyes, dark braided hair, holding a red lightsaber glowing intensely, illustrated in retro anime and hatched drawing style.

A young man with tousled dark hair sits pensively at a rustic wooden table, bathed in warm golden sunlight streaming through a window, reading an open book in a serene room with wooden accents and greenery outside.

Close-up of a woman's face with a clock instead of one eye, blood tears streaming down her pale skin, dark red lipstick, and a lace hood.

A sylphlike woman with raven hair adorned with azure blossoms in a flowing midnight blue gown stands amidst glowing bioluminescent butterflies in a dark forest.

Silhouette of a woman with long hair in a flowing dress enveloped by soft fog against a bright white background, evoking a serene, dreamy atmosphere.

Parámetros Recomendados

samplers

Euler

steps

Consejos

Recommended strength to use really depends on your workflow.

For some prompts the LoRA will have a dramatic effect, for others nothing; a bigger and more diverse dataset might improve results.

Use the Simple+Advanced FLUX.1 ComfyUI Workflows for best compatibility.

Aspectos Destacados de la Versión

Another attempt at this LoRA using a different training tragedy.

Aesthetic
Lora for FLUX

Update 2: Tried using the kohya trainer. The result is the 10R 2E CDO-0.5 version. Previews use my impressionism LoRA. It isn't needed but I liked the results so I stuck with it. Workflow and prompts attached to previews. Just open them in ComfyUI.

Update 1: Added the stronger 10k step trained LoRA model with direct comparison images (left is LoRA strength 0, right is LoRA strength 1.2). Removed misleading (anime) from name, since the LoRA doesn't really make images more anime-like.

Recommended strength to use really depends on your workflow!

Purpose: Imparts a more painterly and wild look at the cost of some coherency. It was trained on painterly vibrant anime art that didn't concern itself with fine details.

This is a proof-of-concept style LoRA for Flux. And only a proof of concept!

NOTE: For some prompts it will have a dramatic effect, for others… nothing, probably needs a bigger and a more diverse dataset then the one I used.

Using the following workflow: [Simple+Advanced] FLUX.1 ComfyUI Workflows - LoRA Support v2 (No CLIP) for ComfyUI