From f157bec8f42ff7218282050183c4d7e10a8d4b10 Mon Sep 17 00:00:00 2001 From: "lzw478614@alibaba-inc.com" Date: Thu, 12 Jun 2025 16:34:59 +0800 Subject: [PATCH] add fun-v1.1-1.3B-control-camera --- diffsynth/models/wan_video_dit.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/diffsynth/models/wan_video_dit.py b/diffsynth/models/wan_video_dit.py index 9bdbda3..50c06bf 100644 --- a/diffsynth/models/wan_video_dit.py +++ b/diffsynth/models/wan_video_dit.py @@ -316,8 +316,12 @@ class WanModel(torch.nn.Module): else: self.control_adapter = None - def patchify(self, x: torch.Tensor): + def patchify(self, x: torch.Tensor,control_camera_latents_input: torch.Tensor = None): x = self.patch_embedding(x) + if self.control_adapter is not None and control_camera_latents_input is not None: + y_camera = self.control_adapter(control_camera_latents_input) + x = [u + v for u, v in zip(x, y_camera)] + x = x[0].unsqueeze(0) grid_size = x.shape[2:] x = rearrange(x, 'b c f h w -> b (f h w) c').contiguous() return x, grid_size # x, grid_size: (f, h, w)