A new generative multispectral texture model based on discrete distribution mixtures is introduced. Statistical texture properties are represented by a discrete distribution mixture of product components. A natural colour or multispectral texture is spectrally factorized and discrete mixtures models are learned and used to synthesize single orthogonal monospectral components. Texture synthesis is based on easy computation of arbitrary conditional distributions from the model. Finally single synthesized monospectral texture components are transformed into the required synthetic colour texture. This model can easily serve for texture segmentation, retrieval or to model single factors in complex Bidirectional Texture Function (BTF) space models. The advantages and weak points of the presented approach are demonstrated on several colour texture applications.