Limitations of Sequential Model 

It is not straightforward to define models that may have multiple different input sources, produce multiple output destinations or models that re-use layers.

Functional model API allows you to define multiple input or output models as well as models that share layers. More than that, it allows you to define ad hoc acyclic network graphs.

KERAS FUNCTIONAL API 

from keras.models import Model

visible = Input(shape=(64,64,1))

conv1 = Conv2D(32, kernel_size=4, activation='relu')(visible)

pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)

conv2 = Conv2D(16, kernel_size=4, activation='relu')(pool1)

pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)

flat = Flatten()(pool2)

hidden1 = Dense(10, activation='relu')(flat)

output = Dense(1, activation='sigmoid')(hidden1)

model = Model(inputs=visible, outputs=output)