Tag
This paper proposes a multi-conditioned diffusion-based synthesis pipeline using Stable Diffusion XL and ControlNet to generate synthetic sand boil imagery for low-resource earthen-levee inspection, addressing the scarcity of annotated defect examples.
This model introduces a depth-conditioned ControlNet-LoRA for Krea-2, enabling depth-map-guided image generation with high depth consistency (0.98-0.99 Pearson correlation). It supports both Raw and Turbo variants and includes easy inference scripts and Comfy UI integration.
The zimage-ncnn tool adds LanPaint inpainting and ControlNet control features. No Python/PyTorch/CUDA required, only depends on C++ and ncnn, supports fully local offline operation on Vulkan or CPU.