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

Flat Color - Style - v2.0 [Illustrious]

7/18/2025

11:56:41 AM

Mots-clés et tags associés

anime,flat,flat color,flat color style,flat color - style,illustrious,lora,motimalu,no lineart,noobai v-pred,style,text-to-video models,v-pred model,v2.0 [illustrious],wan

A slender woman with short shaggy brown hair wearing a white lace blouse and mini skirt leans against a tree holding a rake in autumn suburbia with colorful leaves and a small house in the background.

Surreal image of a woman with white hair and blue eyes lying on her back, depicted from above, blending into a vivid multicolor sea of ink splashes on a simple turquoise background.

Digital portrait of a tribal goddess with teal hair, glowing turquoise sacred geometry patterns on her body, and an ornate fiery headdress against a dark background.

Two chibi anime girls, Ishtar and Ereshkigal, hugging in space with stars and planets around, featuring flat color style and detailed eyes.

Close-up of a beautiful woman with large blue gray eyes, detailed iris, freckles, glossy skin, and dramatic speckled lighting on her face.

A noble blonde female knight with green eyes and braided hair wearing shiny, dirty metal armor, holding a huge sword over her shoulder amidst rain and cloudy skies.

Figure with a red skull mask and gray coat holding a survival lamp, standing in a staff room with apocalyptic red and gray color tones and smoke rising.

A cybernetic elf girl with white hair, laurel crown, and blue glowing eyes sits holding a glowing turquoise sword, wearing a white hoodie and thigh-high prosthetic boots.

Illustration of a summer girl wearing a sunflower crown and flowing sundress, walking barefoot on the beach with waves and a warm sunset in the background

Close-up of a blue iris eye with intricate detail and long eyelashes, illuminated by pink neon gothic style lighting, part of a girl's face visible

Flat vector illustration of a chubby girl with glasses and wavy dark brown hair tripping forward mid-air with motion lines, dropping books and glasses on an orange background.

A fierce large polar bear with battle scars stands behind a female viking warrior holding a sword and shield in a snowy night landscape under a starry sky.

Prompts recommandés

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>

Prompts négatifs recommandés

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

Paramètres recommandés

samplers

Euler

steps

cfg

clip skip

resolution

832x1216

other models

illustrious_flat_color_v2 (75ef486a9f3f), illustriousXL_v01 (356c995b45)

Paramètres haute résolution recommandés

upscaler

4x-UltraSharp

upscale

steps

denoising strength

0.3 - 0.4

Conseils

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.

Points forts de la version

Trained on Illustrious XL 0.1

With the updated dataset for v2

Sponsors du créateur

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