modelli/Flux1. D - Chaotic Effects / Textures N' Pattern - Chroma - v2.0

Flux1. D - Chaotic Effects / Textures N' Pattern - Chroma - v2.0

|
11/5/2025
|
5:45:42 PM
| Discussion|
0
An expressive oil painting of a futuristic street warrior with spiked blue hair, heavy oversized jacket, and huge mechanical gauntlets, standing against a vivid purple background in thick impasto brushstrokes.
A solitary figure stands in a vast alien desert under a glowing pink-orange crescent moon against a darkening sky with distant mountains and cinematic lighting.
Black and white high contrast digital drawing of a shadowy silhouette wearing a hat standing on the edge of a steep cliff with industrial buildings in the background

Parametri Consigliati

samplers

DPM++ 2M_sgm_uniform

steps

20

cfg

4.5

clip skip

1

vae

ae_flux.safetensors

other models

Chroma_Flux1_S_Base\Chroma1-HD.safetensors (d446d9695d)

Suggerimenti

Keep the LoRA weight low between 0.5 and 0.6 for best results.

LoRA ON and OFF comparisons show the added detail and texture effects.

Model is designed to add detail and chaos rather than replicate training images.

Flux Krea FP8 was used for training this model.

Potential future adoption of Chroma model once V50 is released.

Punti Salienti della Versione

More stuff

Sponsor del Creatore

Check out the Chroma model here: https://civitai.com/models/1330309/chroma

  1. First and second picture - Lora ON / Second picture Lora OFF

  2. The rest in reverse - Lora OFF / ON

Since i train a lot of models atm for experimentation and got asked a few times why the LoRAs can't be found on Civit i thought i could at least release this one.

It's a merge of 2 models i've trained, both limited to about 50 images. Seems to be the better solution instead of training 100 images at the same time. The model is very strong, so i would suggest keeping it low ( 0.5 - 0.6 ). Just used a higher weight in the example images to show better what it does... kinda

Main reason for the model is pretty much to add a bit of detail, chaos and texture. Like always, i'm not aiming for the images it was trained on, but to add something to otherwise bland looking stuff.

All made with Flux Krea FP8.

Something as a side note. I will most likely switch completely to Chroma https://civitai.com/models/1330309/chroma once V50 gets released ( and Krea for some things ). Hope Chroma will finally get it's own category after full release, because there is nothing that can hold a candle to this fucker imho. That is if Civit survives the whole censoring, Visa/Mastercard bullshit and the general decline that is going on in the moment.

Precedente
✨ JANKU v4.0 - Trained + NoobAI EPS + RouWei N/SFW Illustrious XL✨ - v5.0 🆕🔥
Successivo
Pony gradient play - V1

Dettagli del Modello

Tipo di modello

LORA

Modello base

Chroma

Versione del modello

Chroma - v2.0

Hash del modello

ee7ecd82c3

Discussione

Per favore log in per lasciare un commento.

Immagini di Flux1. D - Chaotic Effects / Textures N' Pattern - Chroma - v2.0

Immagini con chaotic

Immagini con concept

Immagini con effect

Immagini con textures