jinx/ComfyUI
1
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-08-02 23:14:49 +08:00
Code Issues Activity

Support the WAN 2.1 fun control models.

Browse Source 
Use the new WanFunControlToVideo node.
This commit is contained in:
comfyanonymous
2025-03-26 19:54:54 -04:00
parent 84fdaf7b0e
commit 3661c833bc
3 changed files with 75 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
comfy_extras/nodes_wan.py
View File

@@ -3,6 +3,7 @@ import node_helpers
import torch
import comfy.model_management
import comfy.utils
import comfy.latent_formats
class WanImageToVideo:
@@ -49,6 +50,56 @@ class WanImageToVideo:
return (positive, negative, out_latent)
class WanFunControlToVideo:
@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", ),
"control_video": ("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, control_video=None):
latent = torch.zeros([batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
concat_latent = torch.zeros([batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
concat_latent = comfy.latent_formats.Wan21().process_out(concat_latent)
concat_latent = concat_latent.repeat(1, 2, 1, 1, 1)
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)
concat_latent_image = vae.encode(start_image[:, :, :, :3])
concat_latent[:,16:,:concat_latent_image.shape[2]] = concat_latent_image[:,:,:concat_latent.shape[2]]
if control_video is not None:
control_video = comfy.utils.common_upscale(control_video[:length].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
concat_latent_image = vae.encode(control_video[:, :, :, :3])
concat_latent[:,:16,:concat_latent_image.shape[2]] = concat_latent_image[:,:,:concat_latent.shape[2]]
positive = node_helpers.conditioning_set_values(positive, {"concat_latent_image": concat_latent})
negative = node_helpers.conditioning_set_values(negative, {"concat_latent_image": concat_latent})
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,
"WanFunControlToVideo": WanFunControlToVideo,
}