sat/app.py [1069:1109]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            model.to(device)

            samples_z = sample_func(
                c,
                uc=uc,
                batch_size=1,
                shape=(T, C, H // F, W // F),
                video_flow=video_flow,
            )
            samples_z = samples_z.permute(0, 2, 1, 3, 4).contiguous()

            # Unload the model from GPU to save GPU memory
            model.to("cpu")
            torch.cuda.empty_cache()
            first_stage_model = model.first_stage_model
            first_stage_model = first_stage_model.to(device)

            latent = 1.0 / model.scale_factor * samples_z

            # Decode latent serial to save GPU memory
            recons = []
            loop_num = (T - 1) // 2
            for i in range(loop_num):
                if i == 0:
                    start_frame, end_frame = 0, 3
                else:
                    start_frame, end_frame = i * 2 + 1, i * 2 + 3
                if i == loop_num - 1:
                    clear_fake_cp_cache = True
                else:
                    clear_fake_cp_cache = False
                with torch.no_grad():
                    recon = first_stage_model.decode(
                        latent[:, :, start_frame:end_frame].contiguous(), clear_fake_cp_cache=clear_fake_cp_cache
                    )

                recons.append(recon)

            recon = torch.cat(recons, dim=2).to(torch.float32)
            samples_x = recon.permute(0, 2, 1, 3, 4).contiguous()
            samples = torch.clamp((samples_x + 1.0) / 2.0, min=0.0, max=1.0).cpu()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



sat/sample_video.py [334:373]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                model.to(device)
                samples_z = sample_func(
                    c,
                    uc=uc,
                    batch_size=1,
                    shape=(T, C, H // F, W // F),
                    video_flow=video_flow,
                )
                samples_z = samples_z.permute(0, 2, 1, 3, 4).contiguous()

                # Unload the model from GPU to save GPU memory
                model.to("cpu")
                torch.cuda.empty_cache()
                first_stage_model = model.first_stage_model
                first_stage_model = first_stage_model.to(device)

                latent = 1.0 / model.scale_factor * samples_z

                # Decode latent serial to save GPU memory
                recons = []
                loop_num = (T - 1) // 2
                for i in range(loop_num):
                    if i == 0:
                        start_frame, end_frame = 0, 3
                    else:
                        start_frame, end_frame = i * 2 + 1, i * 2 + 3
                    if i == loop_num - 1:
                        clear_fake_cp_cache = True
                    else:
                        clear_fake_cp_cache = False
                    with torch.no_grad():
                        recon = first_stage_model.decode(
                            latent[:, :, start_frame:end_frame].contiguous(), clear_fake_cp_cache=clear_fake_cp_cache
                        )

                    recons.append(recon)

                recon = torch.cat(recons, dim=2).to(torch.float32)
                samples_x = recon.permute(0, 2, 1, 3, 4).contiguous()
                samples = torch.clamp((samples_x + 1.0) / 2.0, min=0.0, max=1.0).cpu()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -