Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Class WanVAE, def encode, feat_map is using self.decoder instead of self.encoder (#12682)

Reiner "Tiles" Prokein25ec3d96a323
diff --git a/comfy/ldm/wan/vae.py b/comfy/ldm/wan/vae.py
index 7903c7690..71f73c64e 100644
--- a/comfy/ldm/wan/vae.py
+++ b/comfy/ldm/wan/vae.py
@@ -485,7 +485,7 @@ class WanVAE(nn.Module):
iter_ = 1 + (t - 1) // 4
feat_map = None
if iter_ > 1:
- feat_map = [None] * count_conv3d(self.decoder)
+ feat_map = [None] * count_conv3d(self.encoder)
## 对encode输入的x,按时间拆分为1、4、4、4....
for i in range(iter_):
conv_idx = [0]