Ablation Study and Design Evaluation.
We provide additional results including text-prompting and image-prompting generation samples,
teaser materials, and additional comparisons, alongside a Nearest
Neighbor analysis, showing that our method doesn’t simply copy from the dataset.
We also provide additional comparisons and the materials used for the teaser scene.
For editing, we showcase SDEdit for material editing and prompt mixing, as well as material editing
and mixing via inpainting. Furthermore, we offer the full list of prompts used to generate the
textures sample with SDXL
and some representative texture samples.
Finally, we evaluate our different steps in the pipeline through an ablation study of the training
strategy, assessments of high-resolution approaches, evaluations of tileability, and ablation of the
refinement step. Finally, we provide a comparison between LDM and LCM.