I'm having a hard time while conguring a Keras/tensorflow model

i'm trying to create this ai model that can help me to generate, modify videos. I've faced some error previously but i was able to bypass them. Anyway noww i'm stuck in a terrible, annoying error and my head hurt me while trying to solve it, i'm tired i readlly need some help please:

The error says that the sizes of X samples(input arrays) =16 and Y samples(target arrays) =32 are not equal, this is the full error:

and here is my full code :

import os
import cv2
import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Dense, Reshape, BatchNormalization, Conv2DTranspose, Conv2D, LeakyReLU, Flatten
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam

processed_data_folder = 'data/processed_data/'
model_folder = 'models/'
image_size = 64
batch_size = 16
epochs = 50
learning_rate = 0.0002
beta_1 = 0.5

def build_generator():
    model = Sequential()

    model.add(Dense(4 * 4 * 512, input_shape=(100,)))
    model.add(Reshape((4, 4, 512)))
    model.add(BatchNormalization())
    model.add(Conv2DTranspose(256, kernel_size=5, strides=2, padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2DTranspose(128, kernel_size=5, strides=2, padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2DTranspose(64, kernel_size=5, strides=2, padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2DTranspose(3, kernel_size=5, strides=2, padding='same', activation='tanh'))

    return model

def build_discriminator():
    model = Sequential()

    model.add(Conv2D(64, kernel_size=5, strides=2, padding='same', input_shape=(image_size, image_size, 3)))
    model.add(LeakyReLU(alpha=0.2))
    model.add(Conv2D(128, kernel_size=5, strides=2, padding='same'))
    model.add(LeakyReLU(alpha=0.2))
    model.add(Conv2D(256, kernel_size=5, strides=2, padding='same'))
    model.add(LeakyReLU(alpha=0.2))
    model.add(Conv2D(512, kernel_size=5, strides=2, padding='same'))
    model.add(LeakyReLU(alpha=0.2))
    model.add(Flatten())
    model.add(Dense(1, activation='sigmoid'))

    return model

generator = build_generator()
discriminator = build_discriminator()

discriminator.compile(loss='binary_crossentropy', optimizer=Adam(lr=learning_rate, beta_1=beta_1), metrics=['accuracy'])

discriminator.trainable = False
gan = Sequential([generator, discriminator])
gan.compile(loss='binary_crossentropy', optimizer=Adam(lr=learning_rate, beta_1=beta_1))

X_train = []
for video_folder in os.listdir(processed_data_folder):
    frames_folder = os.path.join(processed_data_folder, video_folder, 'frames')
    frames = []
    for frame_file in os.listdir(frames_folder):
        frame_path = os.path.join(frames_folder, frame_file)
        frame = cv2.imread(frame_path)
        frame = cv2.resize(frame, (image_size, image_size))
        frames.append(frame)
    X_train.append(frames)
X_train = np.array(X_train)

X_train = np.reshape(X_train, (-1, image_size, image_size, 3))
print(X_train.shape)

X_train = X_train / 127.5 - 1.

def generate_noise(batch_size, noise_shape):
    return np.random.normal(0, 1, size=(batch_size, noise_shape))

for epoch in range(epochs):

    noise = generate_noise(batch_size, 100)

    generated_images = generator.predict(noise)

    idx = np.random.randint(0, X_train.shape[0], batch_size)
    
    real_images = X_train[idx]

    real_labels = np.ones((batch_size, 1))
    
    fake_labels = np.zeros((batch_size, 1))
    
    d_loss_real = discriminator.train_on_batch(real_images, real_labels)
    
    d_loss_fake = discriminator.train_on_batch(generated_images, fake_labels)

    X = np.concatenate([real_images, generated_images])
    y = np.concatenate([real_labels, fake_labels])

    g_loss = gan.train_on_batch(noise, y)

    print(f"Epoch {epoch+1}/{epochs} [D real loss: {d_loss_real[0]:.4f}, D fake loss: {d_loss_fake[0]:.4f}, G loss: {g_loss:.4f}]")
    
    discriminator.trainable = True 
    
    generator_history = generator.fit(X_train, np.ones((X_train.shape[0], 1)), batch_size=batch_size, epochs=10, shuffle=True) 
    
    discriminator_history = discriminator.fit(X_train, y_train, batch_size=batch_size, epochs=10, shuffle=True)
    
generator.save(os.path.join(model_folder, 'video_generator.h5'))

The batch size was 32 and i had to reduce because of some lack in my system memory.

Basically i tried everything, from resizing the frame images to 32 then to 16, reducing the batch size from 64 to 32 to 16. limited the frames to 1000 frame.... alot of methods and updtes...i am not able to remember.

As mentioned by @m13op22, the problem comes from g_loss = gan.train_on_batch(noise, y). Should it be this instead?:

g_loss = gan.train_on_batch(X, y)