Fix error when using SkyReels I2V Hunyuan Model

The number of out channels on the SkyReels Image-to-Video Hunyuan model is 32, compared to the normal 16. This change is the same fix applied to ComfyUI directly. See: https://github.com/comfyanonymous/ComfyUI/commit/acc152b674fd1c983acc6efd8aedbeb380660c0c#diff-828ff060ac292e5b8eff646d924ade3720f1500a17b42ebdc3034c193ed4b597
2025-02-19 06:20:46 -05:00
parent 61636b6503
commit 3597bb87aa
1 changed files with 1 additions and 1 deletions
@@ -296,7 +296,7 @@ def teacache_hunyuanvideo_forward(
            shape[i] = shape[i] // self.patch_size[i]
        img = img.reshape([img.shape[0]] + shape + [self.out_channels] + self.patch_size)
        img = img.permute(0, 4, 1, 5, 2, 6, 3, 7)
-        img = img.reshape(initial_shape)
+        img = img.reshape(initial_shape[0], self.out_channels, initial_shape[2], initial_shape[3], initial_shape[4])
        return img

 def teacache_ltxvmodel_forward(