fix autograd which i broke for no good reason when implementing SDXL

        # restoring original mean is likely not correct, but it seems to work well to prevent artifacts that happen otherwise

        batch_multipliers = torch.asarray(batch_multipliers).to(devices.device)

        original_mean = z.mean()

        z *= batch_multipliers.reshape(batch_multipliers.shape + (1,)).expand(z.shape)

        z = z * batch_multipliers.reshape(batch_multipliers.shape + (1,)).expand(z.shape)

        new_mean = z.mean()

        z *= (original_mean / new_mean)

        z = z * (original_mean / new_mean)

        return z