What's the difference between x0 and flow for denoising_loss_type config?

[wikiwen]

Great work!
I noticed denoising_loss_type can be flow or other choice. _convert_x0_to_flow_pred or convert_x0_to_noise will be compute In the file model/dmd.py. What's the difference between x0 and flow for denoising_loss_type? （x0 in wan2.2 5b, flow in wan 2.1 1.3b)

Should we always use flow as it's flow in all config yaml files in this repo?

        # Step 3: Compute the denoising loss for the fake critic
        if self.args.denoising_loss_type == "flow":
            from utils.wan_wrapper import WanDiffusionWrapper
            flow_pred = WanDiffusionWrapper._convert_x0_to_flow_pred(
                scheduler=self.scheduler,
                x0_pred=pred_fake_image.flatten(0, 1),
                xt=noisy_generated_image.flatten(0, 1),
                timestep=critic_timestep.flatten(0, 1)
            )
            pred_fake_noise = None
        else:
            flow_pred = None
            pred_fake_noise = self.scheduler.convert_x0_to_noise(
                x0=pred_fake_image.flatten(0, 1),
                xt=noisy_generated_image.flatten(0, 1),
                timestep=critic_timestep.flatten(0, 1)
            ).unflatten(0, image_or_video_shape[:2])

        denoising_loss = self.denoising_loss_func(
            x=generated_image.flatten(0, 1),
            x_pred=pred_fake_image.flatten(0, 1),
            noise=critic_noise.flatten(0, 1),
            noise_pred=pred_fake_noise,
            alphas_cumprod=self.scheduler.alphas_cumprod,
            timestep=critic_timestep.flatten(0, 1),
            flow_pred=flow_pred
        )

[wikiwen]

related issue: #quanhaol/Wan2.2-TI2V-5B-Turbo#9