参数说明
必选参数
| 参数名 | 类型 | 默认值 | 范围 | 说明 |
|---|---|---|---|---|
| positive | CONDITIONING | - | - | 正面提示词条件 |
| negative | CONDITIONING | - | - | 负面提示词条件 |
| vae | VAE | - | - | 用于编码/解码的VAE模型 |
| width | INT | 832 | 16-MAX_RESOLUTION | 生成视频的宽度，步长为16 |
| height | INT | 480 | 16-MAX_RESOLUTION | 生成视频的高度，步长为16 |
| length | INT | 81 | 1-MAX_RESOLUTION | 生成视频的帧数，步长为4 |
| batch_size | INT | 1 | 1-4096 | 批处理大小 |
| strength | FLOAT | 1.0 | 0.0-1000.0 | 条件强度，步长为0.01 |
可选参数
| 参数名 | 类型 | 说明 |
|---|---|---|
| control_video | IMAGE | 控制视频，用于引导生成过程 |
| control_masks | MASK | 控制遮罩，定义视频中哪些区域应受到控制 |
| reference_image | IMAGE | 参考图像，作为视频生成的起点或参考（单张） |
输出参数
| 参数名 | 类型 | 说明 |
|---|---|---|
| positive | CONDITIONING | 处理后的正面提示词条件 |
| negative | CONDITIONING | 处理后的负面提示词条件 |
| latent | LATENT | 生成的视频潜在表示 |
| trim_latent | INT | 裁剪潜在表示的参数，默认值为0。当提供参考图像时，该值会被设置为参考图像在潜在空间中的形状尺寸。它指示下游节点需要从生成的潜在表示中裁剪掉多少来自参考图像的内容，确保最终视频输出中参考图像的影响被适当控制。 |
源码
[源码更新时间: 2025-05-15]class WanVaceToVideo:
@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}),
"strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1000.0, "step": 0.01}),
},
"optional": {"control_video": ("IMAGE", ),
"control_masks": ("MASK", ),
"reference_image": ("IMAGE", ),
}}
RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT", "INT")
RETURN_NAMES = ("positive", "negative", "latent", "trim_latent")
FUNCTION = "encode"
CATEGORY = "conditioning/video_models"
EXPERIMENTAL = True
def encode(self, positive, negative, vae, width, height, length, batch_size, strength, control_video=None, control_masks=None, reference_image=None):
latent_length = ((length - 1) // 4) + 1
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)
if control_video.shape[0] < length:
control_video = torch.nn.functional.pad(control_video, (0, 0, 0, 0, 0, 0, 0, length - control_video.shape[0]), value=0.5)
else:
control_video = torch.ones((length, height, width, 3)) * 0.5
if reference_image is not None:
reference_image = comfy.utils.common_upscale(reference_image[:1].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
reference_image = vae.encode(reference_image[:, :, :, :3])
reference_image = torch.cat([reference_image, comfy.latent_formats.Wan21().process_out(torch.zeros_like(reference_image))], dim=1)
if control_masks is None:
mask = torch.ones((length, height, width, 1))
else:
mask = control_masks
if mask.ndim == 3:
mask = mask.unsqueeze(1)
mask = comfy.utils.common_upscale(mask[:length], width, height, "bilinear", "center").movedim(1, -1)
if mask.shape[0] < length:
mask = torch.nn.functional.pad(mask, (0, 0, 0, 0, 0, 0, 0, length - mask.shape[0]), value=1.0)
control_video = control_video - 0.5
inactive = (control_video * (1 - mask)) + 0.5
reactive = (control_video * mask) + 0.5
inactive = vae.encode(inactive[:, :, :, :3])
reactive = vae.encode(reactive[:, :, :, :3])
control_video_latent = torch.cat((inactive, reactive), dim=1)
if reference_image is not None:
control_video_latent = torch.cat((reference_image, control_video_latent), dim=2)
vae_stride = 8
height_mask = height // vae_stride
width_mask = width // vae_stride
mask = mask.view(length, height_mask, vae_stride, width_mask, vae_stride)
mask = mask.permute(2, 4, 0, 1, 3)
mask = mask.reshape(vae_stride * vae_stride, length, height_mask, width_mask)
mask = torch.nn.functional.interpolate(mask.unsqueeze(0), size=(latent_length, height_mask, width_mask), mode='nearest-exact').squeeze(0)
trim_latent = 0
if reference_image is not None:
mask_pad = torch.zeros_like(mask[:, :reference_image.shape[2], :, :])
mask = torch.cat((mask_pad, mask), dim=1)
latent_length += reference_image.shape[2]
trim_latent = reference_image.shape[2]
mask = mask.unsqueeze(0)
positive = node_helpers.conditioning_set_values(positive, {"vace_frames": control_video_latent, "vace_mask": mask, "vace_strength": strength})
negative = node_helpers.conditioning_set_values(negative, {"vace_frames": control_video_latent, "vace_mask": mask, "vace_strength": strength})
latent = torch.zeros([batch_size, 16, latent_length, height // 8, width // 8], device=comfy.model_management.intermediate_device())
out_latent = {}
out_latent["samples"] = latent
return (positive, negative, out_latent, trim_latent)