This paper presents an efficient algorithm for realistic texture synthesis, which is both fast and capable of generating high-quality results. The algorithm is easy to use, requiring only a sample texture as input. It generates textures with perceived quality equal to or better than those produced by previous techniques, but runs two orders of magnitude faster. This allows the application of texture synthesis to problems that were traditionally considered impractical, such as constrained synthesis for image editing and temporal texture generation. The algorithm is derived from Markov Random Field (MRF) texture models and uses a deterministic searching process. To accelerate the synthesis process, tree-structured vector quantization (TSVQ) is employed, which reduces the computational complexity from linear to logarithmic. The paper includes a detailed description of the algorithm, synthesis results, and comparisons with other methods. It also discusses the application of the algorithm to constrained synthesis and temporal texture synthesis, highlighting its potential for various real-world applications.This paper presents an efficient algorithm for realistic texture synthesis, which is both fast and capable of generating high-quality results. The algorithm is easy to use, requiring only a sample texture as input. It generates textures with perceived quality equal to or better than those produced by previous techniques, but runs two orders of magnitude faster. This allows the application of texture synthesis to problems that were traditionally considered impractical, such as constrained synthesis for image editing and temporal texture generation. The algorithm is derived from Markov Random Field (MRF) texture models and uses a deterministic searching process. To accelerate the synthesis process, tree-structured vector quantization (TSVQ) is employed, which reduces the computational complexity from linear to logarithmic. The paper includes a detailed description of the algorithm, synthesis results, and comparisons with other methods. It also discusses the application of the algorithm to constrained synthesis and temporal texture synthesis, highlighting its potential for various real-world applications.