HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration

ArXi:2603.07815v1 Announce Type: new Diffusion models have nstrated a remarkable ability in Text-to-Image (T2I) generation applications. Despite the advanced generation output, they suffer from heavy computation overhead, especially for large models that contain tens of billions of parameters. Prior work has illustrated that replacing part of the denoising steps with a smaller model still maintains the generation quality. However, these methods only focus on saving computation for some timesteps, ignoring the difference in compute demand within one timestep.