Flowchart comparing the current state-of-the-art inference pipeline (left side) with this work (right side). In current state-of-the-art pipelines, we use a single realisation of the ICs to estimate the mean 1D 21 cm PS. Moreover, the simulated 1D PS is computed by spherically averaging over different wave modes than those used to compute the observed 1D PS. In this work, we account for sample variance by applying 21cmPSDenoiser a score-based diffusion model trained to estimate the mean 21 cm PS from a single realisation. We also account for 21 cm PS anisotropy by averaging the 2D PS only over modes above μ_min = 0.97, the region of 2D PS that is closest to where current 21 cm PS instruments observe. Applying a cut in μ_min significantly exacerbates the problem of sample variance and would not be practical without the use of 21cmPSDenoiser.