With a complex image, first binarize the image intensity between 0, 1, so as to avoid blurring the image, and then flatten each line of the image for all colour channels ie. Keep the previous logic, but replace the pixel generating pixel for row to generate row. After generation, comparing the origin images, there is very little loss of 0.1160. The only difference between them is which RNN output sections dominate the generation of the next pixel row, in other words, for Many-To-One there's an extra call Assume we have m n c image, m is row number, n is column, c is color channel number. For grey-scale, the input_siz e should be n 1 because there is only one color channel .