GANs producing black images only for low light images

Question

I have an assignment where I need to train the GAN to product images of a bus. But the dataset given to us, on purpose has only 108 images and only low light images (Taken at night). Here is an example of an augmented batch (Random crops + rotations). The dataset has about 400 images now.

I even used YOLO pretrained weights to crop the images of buses to avoid the backgrounds, normalised it and resized it to 64x64. The problem arises after 200 epochs, where it only produces dark images and the error keeps on decreasing because the background is so dark. What can be done to produce meaningful images. NOTE: I cannot use dataset outside the given dataset to me, but I can use different libraries to augment and stuff.

My DC architecture:

class DC_Gen(nn.Module):
    def __init__(self):
        super().__init__()
        self.model = nn.Sequential(
            # input is Z, going into a convolution
            nn.ConvTranspose2d(nz, ngf * 8, 4, 1, 0, bias=False),
            nn.BatchNorm2d(ngf * 8),
            nn.ReLU(True),
            # state size. (ngf*8) x 4 x 4
            nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 4),
            nn.ReLU(True),
            # state size. (ngf*4) x 8 x 8
            nn.ConvTranspose2d( ngf * 4, ngf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf * 2),
            nn.ReLU(True),
            # state size. (ngf*2) x 16 x 16
            nn.ConvTranspose2d( ngf * 2, ngf, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ngf),
            nn.ReLU(True),
            # state size. (ngf) x 32 x 32
            nn.ConvTranspose2d( ngf, nc, 4, 2, 1, bias=False),
            nn.Tanh()
            # state size. (nc) x 64 x 64
        )

    def forward(self, input):
        return self.model(input)

My Gen architecture:

class DC_Dis(nn.Module):
    def __init__(self):
        super().__init__()
        self.model = nn.Sequential(
            # input is (nc) x 64 x 64
            nn.Conv2d(nc, ndf, 4, 2, 1, bias=False),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf) x 32 x 32
            nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 2),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf*2) x 16 x 16
            nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 4),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf*4) x 8 x 8
            nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),
            nn.BatchNorm2d(ndf * 8),
            nn.LeakyReLU(0.2, inplace=True),
            # state size. (ndf*8) x 4 x 4
            nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),
            nn.Sigmoid()
        )

    def forward(self, input):
        return self.model(input)

Is my model too simple?

I tried Augmentation, but when I used color jitter, it produced different color images after each epochs, so i only used rotation and randomcrops. the dataset has 300 images now. I used YOLO to crop the images of bus only. What else can I do