support more wan models

Author: Artiprocher

diffsynth/configs/model_config.py

@@ -124,6 +124,7 @@
     (None, "6d6ccde6845b95ad9114ab993d917893", ["wan_video_dit"], [WanModel], "civitai"),
     (None, "6bfcfb3b342cb286ce886889d519a77e", ["wan_video_dit"], [WanModel], "civitai"),
     (None, "349723183fc063b2bfc10bb2835cf677", ["wan_video_dit"], [WanModel], "civitai"),
+    (None, "efa44cddf936c70abd0ea28b6cbe946c", ["wan_video_dit"], [WanModel], "civitai"),
     (None, "cb104773c6c2cb6df4f9529ad5c60d0b", ["wan_video_dit"], [WanModel], "diffusers"),
     (None, "9c8818c2cbea55eca56c7b447df170da", ["wan_video_text_encoder"], [WanTextEncoder], "civitai"),
     (None, "5941c53e207d62f20f9025686193c40b", ["wan_video_image_encoder"], [WanImageEncoder], "civitai"),

diffsynth/models/wan_video_dit.py

@@ -535,6 +535,20 @@ def from_civitai(self, state_dict):
                 "num_layers": 30,
                 "eps": 1e-6
             }
+        elif hash_state_dict_keys(state_dict) == "efa44cddf936c70abd0ea28b6cbe946c":
+            config = {
+                "has_image_input": True,
+                "patch_size": [1, 2, 2],
+                "in_dim": 48,
+                "dim": 5120,
+                "ffn_dim": 13824,
+                "freq_dim": 256,
+                "text_dim": 4096,
+                "out_dim": 16,
+                "num_heads": 40,
+                "num_layers": 40,
+                "eps": 1e-6
+            }
         else:
             config = {}
         return state_dict, config