V1 uses autotagged images



Experimental LoRA to capture Jean Metzinger's cubist style, and explore limits of diffusion models with fractured / non-standard perspectives (e.g. cubism)
For base images sharing similar subject matter (e.g. portraits), cubist perspective starts taking shape from around 0.8 and up.
For base images where the subject matter is foreign (i.e. not represented in the paintings), higher weights has the interesting effect of squaring the perspective and rearranging the composition in groups of blocks.
V1 uses autotagged images
1. Права на репостнутые модели принадлежат оригинальным создателям.
2. Для подтверждения авторства модели создателям следует обратиться к сотрудникам SeaArt AI через официальные каналы. Нажмите, чтобы подтвердить
