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. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
