CPU-friendly Stable Diffusion v1.5 + Scribble ControlNet (best for machines without CUDA). src/sparky_image_generation_tool_gpu_sdxl_controlnet.py GPU (CUDA) Stable Diffusion XL + Scribble ControlNet ...
We present two models, SDXS-512 and SDXS-1024, achieving inference speeds of approximately 100 FPS (30x faster than SD v1.5) and 30 FPS (60x faster than SDXL) on a single GPU. Assuming the image ...