Flat Color - Style

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

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, so I've extended the dataset in following versions, including Hunyuan Video.

Recommended prompt structure:

Positive prompt:

flat color, no lineart, blending, negative space,

{{tags}}

masterpiece, best quality, very awa, absurdres

Negative prompt:

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

描述:

v2 changelog:

- large dataset update to better target flat color and no lineart styles and techniques, including blending

Trained on NoobAI-XL (NAI-XL) V-Pred 1.0-Version

With the kohya_ss dev branch, v_paratemization ,zero_terminal_ssr enabled, and noise offet set to 0.

Previews are generated in Forge with DynamicThresholding (CFG-Fix) Integrated enabled, settings:

dynthres_enabled: True, dynthres_mimic_scale: 5, dynthres_threshold_percentile: 1, dynthres_mimic_mode: Half Cosine Down, dynthres_mimic_scale_min: 1, dynthres_cfg_mode: Half Cosine Down, dynthres_cfg_scale_min: 3, dynthres_sched_val: 1, dynthres_separate_feature_channels: enable, dynthres_scaling_startpoint: ZERO, dynthres_variability_measure: STD, dynthres_interpolate_phi: 1

A ComfyUI workflow reference with DynamicThresholding, Upscaling, and FaceDetailer can be found here: https://civitai.com/posts/11457095