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

Wan 2.2 support. (#9080)

Browse Source
This commit is contained in:
comfyanonymous
2025-07-28 05:00:23 -07:00
committed by GitHub
parent d0210fe2e5
commit a88788dce6
8 changed files with 926 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
comfy_extras/nodes_wan.py
View File

@@ -685,6 +685,49 @@ class WanTrackToVideo:
out_latent["samples"] = latent
return (positive, negative, out_latent)
class Wan22ImageToVideoLatent:
@classmethod
def INPUT_TYPES(s):
return {"required": {"vae": ("VAE", ),
"width": ("INT", {"default": 1280, "min": 32, "max": nodes.MAX_RESOLUTION, "step": 32}),
"height": ("INT", {"default": 704, "min": 32, "max": nodes.MAX_RESOLUTION, "step": 32}),
"length": ("INT", {"default": 49, "min": 1, "max": nodes.MAX_RESOLUTION, "step": 4}),
"batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
},
"optional": {"start_image": ("IMAGE", ),
}}
RETURN_TYPES = ("LATENT",)
FUNCTION = "encode"
CATEGORY = "conditioning/inpaint"
def encode(self, vae, width, height, length, batch_size, start_image=None):
latent = torch.zeros([1, 48, ((length - 1) // 4) + 1, height // 16, width // 16], device=comfy.model_management.intermediate_device())
if start_image is None:
out_latent = {}
out_latent["samples"] = latent
return (out_latent,)
mask = torch.ones([latent.shape[0], 1, ((length - 1) // 4) + 1, latent.shape[-2], latent.shape[-1]], 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)
latent_temp = vae.encode(start_image)
latent[:, :, :latent_temp.shape[-3]] = latent_temp
mask[:, :, :latent_temp.shape[-3]] *= 0.0
out_latent = {}
latent_format = comfy.latent_formats.Wan22()
latent = latent_format.process_out(latent) * mask + latent * (1.0 - mask)
out_latent["samples"] = latent.repeat((batch_size, ) + (1,) * (latent.ndim - 1))
out_latent["noise_mask"] = mask.repeat((batch_size, ) + (1,) * (mask.ndim - 1))
return (out_latent,)
NODE_CLASS_MAPPINGS = {
"WanTrackToVideo": WanTrackToVideo,
"WanImageToVideo": WanImageToVideo,
@@ -695,4 +738,5 @@ NODE_CLASS_MAPPINGS = {
"TrimVideoLatent": TrimVideoLatent,
"WanCameraImageToVideo": WanCameraImageToVideo,
"WanPhantomSubjectToVideo": WanPhantomSubjectToVideo,
"Wan22ImageToVideoLatent": Wan22ImageToVideoLatent,
}