Flat Vector Lora, trained on 400 images in a flat color and no lineart style, excels at generating images with minimalist and vibrant aesthetics. It creates visuals with clean, saturated colors, avoiding traditional lines and shadows, resulting in stylish and expressive silhouettes. This model is perfect for generating characters, scenes, and objects with a simplified yet striking aesthetic, favoring vector and flat styles. It captures elements with clear shapes and contrasting colors, making it ideal for flat design-style artworks.For the face, it is necessary to use ADetailer🎞️ Watch video example: <a target="_blank" rel="ugc" href="https://civarchive.com/images/70459219">https://civarchive.com/images/70459219</a>📸 For full-length works or long-range plans: The examples use Img2img - Inpaint<hr />🧪 Samplers:Recommended:<ul><li>Sampler: Euler a / DPM++ 2M + Karras</li><li>Sampling Steps: 25–45</li><li>CFG Scale: 5–7 (For portraits: 5–6)</li></ul>

Flat Vector

New dataset, new training parameters.

Flat_Vector_V2.safetensors

v2.0

v1.0

Flat Vector Lora, trained on 272 images in a flat color and no lineart style, excels at generating images with minimalist and vibrant aesthetics. It creates visuals with clean, saturated colors, avoiding traditional lines and shadows, resulting in stylish and expressive silhouettes. This model is perfect for generating characters, scenes, and objects with a simplified yet striking aesthetic, favoring vector and flat styles. It captures elements with clear shapes and contrasting colors, making it ideal for flat design-style artworks.

Files with SHA256: be1781c53a8d2da2433da0a3f033e2075b01b68d66de0c52efd8a4bb8e3bb58e