This paper presents an FPGA based hardware architecture, named FlexWAFE, for high resolution, high troughput real-time digital film processing. Complex algorithms require several hundred arithmetic operations per pixel which is beyond the scope of current DSP processors. To simplify programming and yet achieve high clock rates, the architecture combines component configuration with weak programmability. It alleviates the memory bottleneck by an efficient use of internal memory blocks and a multi-stream SDRAM memory scheduler with tightly bounded latency. Several examples of a Discrete Wavelet Transform and a complex noise reducer demonstrate the architecture efficiency.