modele/Flat Color - Style - v2.0 [Illustrious]

Flat Color - Style - v2.0 [Illustrious]

|
7/18/2025
|
11:56:41 AM
| Discussion

Zalecane podpowiedzi

flat color, no lineart, blending, negative space, {{tags}}, masterpiece, best quality, very aesthetic, newest

flat color, no lineart, blending, negative space, masterpiece, best quality, very awa, absurdres <lora:illustrious_flat_color_v2:1>

Zalecane negatywne podpowiedzi

(worst quality, low quality, sketch:1.1), error, bad anatomy, bad hands, watermark, ugly, distorted, censored, lowres

Zalecane parametry

samplers

Euler

steps

30

cfg

10

clip skip

2

resolution

832x1216

other models

illustrious_flat_color_v2 (75ef486a9f3f), illustriousXL_v01 (356c995b45)

Zalecane parametry wysokiej rozdzielczości

upscaler

4x-UltraSharp

upscale

2

steps

10

denoising strength

0.3 - 0.4

Wskazówki

LoRA works best when applied to their respective base models.

For Noobai V-Pred, use a ComfyUI workflow with DynamicThresholding, Upscaling, and FaceDetailer.

The style reduces color bleeding and strengthens blacks, making evaluation during training easy.

Najważniejsze informacje o wersji

Trained on Illustrious XL 0.1

With the updated dataset for v2

Sponsorzy twórcy

For Noobai V-Pred, a ComfyUI workflow reference with DynamicThresholding, Upscaling, and FaceDetailer can be found here.

Flat Color - Style

Trained on images without visible lineart, flat colors, and little to no indication of depth.

ℹ️ LoRA work best when applied to the base models on which they are trained. Please read the About This Version on the appropriate base models and workflow/training information.

This is a small style LoRA I thought would be interesting to try with a v-pred model (noobai v-pred), for the reduced color bleeding and strong blacks in particular.

The effect is quite nice and easy to evaluate in training, so I've extended the dataset with videos in following versions for text-to-video models like Wan and Hunyuan, and it is what I am generally using to test LoRA training on new models now.

Recommended prompt structure:

Positive prompt:

flat color, no lineart, blending, negative space,
{{tags}}
masterpiece, best quality, very aesthetic, newest

For Noobai V-Pred, a ComfyUI workflow reference with DynamicThresholding, Upscaling, and FaceDetailer can be found here: https://civitai.com/posts/11457095

Poprzedni
Adventure Diffusion - v1.0
Następny
blue-and-white style 2D - v1.0

Szczegóły modelu

Typ modelu

LORA

Model bazowy

Illustrious

Wersja modelu

v2.0 [Illustrious]

Hash modelu

1e18995b96

Wytrenowane słowa

flat color
no lineart

Twórca

Dyskusja

Proszę się log in, aby dodać komentarz.