modelle/Impressionism - Flux

Impressionism - Flux

|
9/1/2025
|
10:38:24 AM
| Discussion|
0
A villager walking on a rainy country path holding a colorful glowing umbrella that lights up the scene, with vibrant reflections on wet ground and blooming flowers around.
A picturesque fishing village along a calm canal at dusk, with colorful houses glowing warmly and boats docked by the water reflecting the vibrant sky.
A cute round rusted robot with a glowing blue eye scavenging scraps in a rocky futuristic junkyard.
Impressionistic oil painting of chalk cliffs at dawn by the Baltic sea, featuring a winding path, wildflowers, trees, and soft morning light.
Hand-drawn sketch of a creepy pale-skinned teenager with exaggerated yellow eyes and a wide sinister grin, holding a scarlet carnation, set against a dark background with textured expressive line-art.
Cluster of rainbow-colored grapes glowing vibrantly with a painterly effect and surreal bokeh background in 8k resolution
A majestic ancient robotic dragon with intricate black and gold armor drinking water from a small waterfall in a lush forest stream.

Empfohlene Prompts

ArsMJStyle, ((Impressionism ))

Empfohlene Negative Prompts

quality tags,negatives

Empfohlene Parameter

samplers

DDIM, Euler

steps

20 - 30

cfg

7.5

resolution

512x512

Tipps

The effect starts to be visible from a weight of 0.4 and works best between 0.6 and 1.5 depending on preference.

Works without the need for trigger words like ArsMJStyle or Impressionism.

Quality tags and negative prompts reduce the effect.

Versions-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

Updated with Flux - check the version for more info.

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.

Mitwirkende

Zurück
Smooth Embeddings - Smooth Negative NoobAI
Weiter
Editijon K:POP - alpha

Modell-Details

Modelltyp

LORA

Basismodell

Flux.1 D

Modellversion

Flux

Modell-Hash

94874233f8

Trainierte Wörter

ArsMJStyle, impressionism

Ersteller

Diskussion

Bitte log in um einen Kommentar zu hinterlassen.

Bilder von Impressionism - Flux

Bilder mit impressionism

Bilder mit lora

Bilder mit midjourney

Bilder mit style