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

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

7/27/2025

4:44:22 AM

Related Keywords & Tags

10r 3e cdo-0.5,advokat,aesthetic lora,aesthetic lora for flux,anime,flux,flux.1 d,girls,lora,lora model for stable diffusion,painterly style,semirealistic,style,woman

Close-up portrait of a fierce woman Sith Lord holding a red lightsaber with piercing blue eyes, dark braided hair, and battle-worn robes in an ancient ruins background, illustrated with hatched color pencil sketch style.

A contemplative young man with tousled dark hair and muscular arms sits at a rustic wooden table bathed in warm golden sunlight, reading an open book in a cozy room with wooden accents and greenery outside.

Close-up face with a vintage clock replacing one eye, blood streaks dripping from the clock and lips, dark Victorian styled makeup.

A serene sylphlike woman with raven hair adorned with blue blossoms, surrounded by glowing bioluminescent blue butterflies in a dark forest.

A serene ethereal woman with raven hair adorned with blue blossoms in a midnight blue gown, surrounded by glowing bioluminescent butterflies in an enchanted forest.

Silhouette of a woman in a flowing dress surrounded by soft, diffused fog with a serene and dreamy ambiance against a white background.

Recommended Parameters

samplers

Euler

steps

Tips

Recommended LoRA strength depends heavily on your workflow.

The model may have dramatic effect on some prompts and none on others.

For best results use with the [Simple+Advanced] FLUX.1 ComfyUI Workflows - LoRA Support v2 (No CLIP).

The preview images use the Impressionist Landscape LoRA for enhanced effect.

Version Highlights

Another attempt at this LoRA using a different training tragedy.

Creator Sponsors

Impressionist Landscape LoRA for FLUX

[Simple+Advanced] FLUX.1 ComfyUI Workflows - LoRA Support v2 (No CLIP)

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