models/Impressionism - Flux

Impressionism - Flux

|
8/24/2025
|
11:17:16 PM
| Discussion|
0
A villager walking in a rainy country village under a colorful umbrella emitting a vibrant glow, reflecting on the wet path amid blooming flowers and glowing lanterns.
A vibrant painting of a fishing village at sunset featuring colorful houses, a cobblestone path along a canal with boats, and a glowing sky.
A cute, round rusted robot with a large glowing blue eye, standing in a rocky futuristic junkyard environment, hunting for scraps.
Impressionistic oil painting of chalk cliffs bathed in dawn light with coastal landscape, wildflowers, and morning mist over the Baltic Sea.
Hand-drawn sketch of a pale-skinned teenager with large yellow eyes and wide sinister grin holding a scarlet carnation against a dark background.
Vibrantly glowing rainbow colored grapes with a painterly texture and surreal bokeh background in high resolution.
Ancient black and gold robotic dragon drinking water from a stream with a small waterfall in a forest setting.

Recommended Prompts

ArsMJStyle, ((Impressionism ))

Recommended Parameters

samplers

DDIM, Euler

steps

20 - 30

cfg

7.5

resolution

512x512

Tips

Start from higher LoRA strength/weight when using MJ7.

Works without the trigger words ArsMJStyle or Impressionism.

Visible effects start appearing at 0.4+ strength; optimal use between 0.6 - 1.5 depending on preference.

Quality tags and negatives reduce the effect of the LoRA model.

The LoRA weight can be set quite high depending on the base model used.

Version Highlights

The model works great in the 0.4 - 1.5 strength range.

I personally prefer using 1.5 strength on the Flux Dev GGUF Q4

MJ7 Update:

The MJ7 dataset was recreated using MidJourney V7.
It has a better versatility, but it is not as strong as the previous 2 versions.

You can start from higher LoRA strength/weight when using it.

The Lora is trained on MidJourney Images that use my "Personalised Style" + Impressionism
V2 is highly flexible, but the effects are not as prominent as V1.

Works without the trigger words ArsMJStyle, Impressionism

Will start adding visible effects at 0.4+
Works great in the 0.6 - 1.5 range, depending on your preference

It depends on the model, but you can go pretty high with this Lora's weight.

Quality tags and negatives reduce the effect.

Contributor

Previous
Skooldaze Closeup Portrait Style - V1
Next
Wan Video 2.2 - 5B Text-Image-to-Video

Model Details

Model type

LORA

Base model

Flux.1 D

Model version

Flux

Model hash

94874233f8

Trained words

ArsMJStyle, impressionism

Creator

Discussion

Please log in to leave a comment.