xinyun/ComfyUI
1
0
Fork 0
mirror of https://git.datalinker.icu/comfyanonymous/ComfyUI synced 2025-12-08 21:44:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge cc337019ce5c4323b8d5b86fccc2a26c591be8c6 into fd271dedfde6e192a1f1a025521070876e89e04a

Browse Source
This commit is contained in:
Alex Butler 2025-12-08 10:37:09 +01:00 committed by GitHub
commit 390760da77
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 14 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
comfy_extras/nodes_wan.py
View File

@ -26,6 +26,7 @@ class WanImageToVideo(io.ComfyNode):
io.Int.Input("height", default=480, min=16, max=nodes.MAX_RESOLUTION, step=16),
io.Int.Input("length", default=81, min=1, max=nodes.MAX_RESOLUTION, step=4),
io.Int.Input("batch_size", default=1, min=1, max=4096),
io.Int.Input("vae_tile_size", default=0, min=0, optional=True, tooltip="VAE encode tile size, 0 means untiled (default)"),
io.ClipVisionOutput.Input("clip_vision_output", optional=True),
io.Image.Input("start_image", optional=True),
],
@ -37,14 +38,18 @@ class WanImageToVideo(io.ComfyNode):
)
@classmethod
def execute(cls, positive, negative, vae, width, height, length, batch_size, start_image=None, clip_vision_output=None) -> io.NodeOutput:
def execute(cls, positive, negative, vae, width, height, length, batch_size, vae_tile_size=0, start_image=None, clip_vision_output=None) -> io.NodeOutput:
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])
if vae_tile_size == 0:
concat_latent_image = vae.encode(image[:, :, :, :3])
else:
concat_latent_image = vae.encode_tiled(image[:, :, :, :3], tile_x=vae_tile_size, tile_y=vae_tile_size, overlap=32, tile_t=256, overlap_t=8)
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
@ -192,6 +197,7 @@ class WanFirstLastFrameToVideo(io.ComfyNode):
io.Int.Input("height", default=480, min=16, max=nodes.MAX_RESOLUTION, step=16),
io.Int.Input("length", default=81, min=1, max=nodes.MAX_RESOLUTION, step=4),
io.Int.Input("batch_size", default=1, min=1, max=4096),
io.Int.Input("vae_tile_size", default=0, min=0, optional=True, tooltip="VAE encode tile size, 0 means untiled (default)"),
io.ClipVisionOutput.Input("clip_vision_start_image", optional=True),
io.ClipVisionOutput.Input("clip_vision_end_image", optional=True),
io.Image.Input("start_image", optional=True),
@ -205,7 +211,7 @@ class WanFirstLastFrameToVideo(io.ComfyNode):
)
@classmethod
def execute(cls, positive, negative, vae, width, height, length, batch_size, start_image=None, end_image=None, clip_vision_start_image=None, clip_vision_end_image=None) -> io.NodeOutput:
def execute(cls, positive, negative, vae, width, height, length, batch_size, vae_tile_size=0, start_image=None, end_image=None, clip_vision_start_image=None, clip_vision_end_image=None) -> io.NodeOutput:
spacial_scale = vae.spacial_compression_encode()
latent = torch.zeros([batch_size, vae.latent_channels, ((length - 1) // 4) + 1, height // spacial_scale, width // spacial_scale], device=comfy.model_management.intermediate_device())
if start_image is not None:
@ -224,7 +230,11 @@ class WanFirstLastFrameToVideo(io.ComfyNode):
image[-end_image.shape[0]:] = end_image
mask[:, :, -end_image.shape[0]:] = 0.0
concat_latent_image = vae.encode(image[:, :, :, :3])
if vae_tile_size == 0:
concat_latent_image = vae.encode(image[:, :, :, :3])
else:
concat_latent_image = vae.encode_tiled(image[:, :, :, :3], tile_x=vae_tile_size, tile_y=vae_tile_size, overlap=32, tile_t=256, overlap_t=8)
mask = mask.view(1, mask.shape[2] // 4, 4, mask.shape[3], mask.shape[4]).transpose(1, 2)
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})