Method process

diffsynth/pipelines/wan_video_new.py:1111–1124

(self, pipe: WanVideoPipeline, inputs_shared, inputs_posi, inputs_nega)

            return {"s2v_pose_latents": pose_conds[0]}

    def process(self, pipe: WanVideoPipeline, inputs_shared, inputs_posi, inputs_nega):
        if (inputs_shared.get("input_audio") is None and inputs_shared.get("audio_embeds") is None) or pipe.audio_encoder is None or pipe.audio_processor is None:
            return inputs_shared, inputs_posi, inputs_nega
        num_frames, height, width, tiled, tile_size, tile_stride = inputs_shared.get("num_frames"), inputs_shared.get("height"), inputs_shared.get("width"), inputs_shared.get("tiled"), inputs_shared.get("tile_size"), inputs_shared.get("tile_stride")
        input_audio, audio_embeds, audio_sample_rate = inputs_shared.pop("input_audio", None), inputs_shared.pop("audio_embeds", None), inputs_shared.get("audio_sample_rate", 16000)
        s2v_pose_video, s2v_pose_latents, motion_video = inputs_shared.pop("s2v_pose_video", None), inputs_shared.pop("s2v_pose_latents", None), inputs_shared.pop("motion_video", None)

        audio_input_positive = self.process_audio(pipe, input_audio, audio_sample_rate, num_frames, audio_embeds=audio_embeds)
        inputs_posi.update(audio_input_positive)
        inputs_nega.update({"audio_embeds": 0.0 * audio_input_positive["audio_embeds"]})

        inputs_shared.update(self.process_motion_latents(pipe, height, width, tiled, tile_size, tile_stride, motion_video))
        inputs_shared.update(self.process_pose_cond(pipe, s2v_pose_video, num_frames, height, width, tiled, tile_size, tile_stride, s2v_pose_latents=s2v_pose_latents))
        return inputs_shared, inputs_posi, inputs_nega

    @staticmethod
    def pre_calculate_audio_pose(pipe: WanVideoPipeline, input_audio=None, audio_sample_rate=16000, s2v_pose_video=None, num_frames=81, height=448, width=832, fps=16, tiled=True, tile_size=(30, 52), tile_stride=(15, 26)):