<h1 id="flat-color-style">Flat Color - Style</h1>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 tags:<pre><code>flat color, no lineart, blending, negative space, {{color}} background</code></pre>

Flat Color - Style

Trained on <a target="_blank" rel="ugc" href="https://civitai.com/models/795765/illustrious-xl">Illustrious XL 0.1</a>With the updated dataset for v2

illustrious_flat_color_v2.safetensors

v2.0 [Illustrious]

v3.0 [anima-preview-3]

v2.1 [z-image-base]

v2.1 [z-image-turbo]

v2.1 [klein-4b]

v2.0 [qwen]

v2.0 [wan-ti2v-5b]

v2.0 [hidream]

v2.0 [wan-t2v-1.3b]

v2.0 [wan-t2v-14b]

v2.0 [hunyuan]

v2.0 [noobai-v-pred-1]

v1.0 [hunyuan]

v1.0 [Illustrious]

v1.0 [noobai-v-pred-1]

<h1 id="flat-color-style-o3xd284uz">Flat Color - Style</h1>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:<pre><code>flat color, no lineart, blending, negative space,
{{tags}}
masterpiece, best quality, very awa, absurdres</code></pre>Negative prompt:<pre><code>(worst quality, low quality, sketch:1.1), error, bad anatomy, bad hands, watermark, ugly, distorted, censored, lowres, abstract, signature, bkub</code></pre>

&lt;p&gt;Trained on &lt;a target=&#34;_blank&#34; rel=&#34;ugc&#34; href=&#34;https://civitai.com/models/795765/illustrious-xl&#34;&gt;&lt;strong&gt;Illustrious XL 0.1&lt;/strong&gt;&lt;/a&gt;&lt;/p&gt;&lt;p&gt;With the updated dataset for v2&lt;/p&gt;

V2 illust

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

v2.0

<h1 id="flat-color-style">Flat Color - Style</h1>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:<pre><code>flat color, no lineart, blending, negative space,
{{tags}}
masterpiece, best quality, very aesthetic, newest</code></pre>

Files with SHA256: 1e18995b9664e600feb47837d9af04c1be51ecd426ac137f7b340dec63fa05bf