Abstract: Based on non Markov chain denoising diffusion implicit model (DDIM), we proposed  probability method of denoising diffusion based on  rough sets. The rough set theory was used to equivalently partition the sampled original sequence, construct the upper and lower approximation sets and roughness of the subsequences on the original sequence, and obtain the effective subsequences of the non Markov chain DDIM when the roughness was the lowest. The comparative experiments were conducted by the denoising diffusion probability model (DDPM) and DDIM,  and the experimental results  show that the sequence obtained by proposed method is an effective subsequence, and the sampling efficiency on this sequence is better than that of the DDPM.

Key words: rough set, denoising diffusion probability model, non Markov chain denoising diffusion probability model, Markov chain