comfy_extras/nodes_wan.py

import nodes
import node_helpers
import torch
import comfy.model_management
import comfy.utils


class WanImageToVideo:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {"positive": ("CONDITIONING", ),
                             "negative": ("CONDITIONING", ),
                             "vae": ("VAE", ),
                             "width": ("INT", {"default": 832, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
                             "height": ("INT", {"default": 480, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
                             "length": ("INT", {"default": 81, "min": 1, "max": nodes.MAX_RESOLUTION, "step": 4}),
                             "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
                },
                "optional": {"clip_vision_output": ("CLIP_VISION_OUTPUT", ),
                             "start_image": ("IMAGE", ),
                }}

    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
    RETURN_NAMES = ("positive", "negative", "latent")
    FUNCTION = "encode"

    CATEGORY = "conditioning/video_models"

    def encode(self, positive, negative, vae, width, height, length, batch_size, start_image=None, clip_vision_output=None):
        latent = torch.zeros([batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
        if start_image is not None:
            start_image = comfy.utils.common_upscale(start_image[:length].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
            image = torch.ones((length, height, width, start_image.shape[-1]), device=start_image.device, dtype=start_image.dtype) * 0.5
            image[:start_image.shape[0]] = start_image

            concat_latent_image = vae.encode(image[:, :, :, :3])
            mask = torch.ones((1, 1, latent.shape[2], concat_latent_image.shape[-2], concat_latent_image.shape[-1]), device=start_image.device, dtype=start_image.dtype)
            mask[:, :, :((start_image.shape[0] - 1) // 4) + 1] = 0.0

            positive = node_helpers.conditioning_set_values(positive, {"concat_latent_image": concat_latent_image, "concat_mask": mask})
            negative = node_helpers.conditioning_set_values(negative, {"concat_latent_image": concat_latent_image, "concat_mask": mask})

        if clip_vision_output is not None:
            positive = node_helpers.conditioning_set_values(positive, {"clip_vision_output": clip_vision_output})
            negative = node_helpers.conditioning_set_values(negative, {"clip_vision_output": clip_vision_output})

        out_latent = {}
        out_latent["samples"] = latent
        return (positive, negative, out_latent)


NODE_CLASS_MAPPINGS = {
    "WanImageToVideo": WanImageToVideo,
}