fix config

vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKLLTXVideo",
+  "_diffusers_version": "0.32.0.dev0",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "decoder_causal": false,
+  "encoder_causal": true,
+  "in_channels": 3,
+  "latent_channels": 128,
+  "layers_per_block": [
+    4,
+    3,
+    3,
+    3,
+    4
+  ],
+  "out_channels": 3,
+  "patch_size": 4,
+  "patch_size_t": 1,
+  "resnet_norm_eps": 1e-06,
+  "scaling_factor": 1.0,
+  "spatio_temporal_scaling": [
+    true,
+    true,
+    true,
+    false
+  ]
+}

vae/vae_config.json

@@ -1,32 +1 @@
-{
-  "_class_name": "AutoencoderKLLTXVideo",
-  "_diffusers_version": "0.32.0.dev0",
-  "block_out_channels": [
-    128,
-    256,
-    512,
-    512
-  ],
-  "decoder_causal": false,
-  "encoder_causal": true,
-  "in_channels": 3,
-  "latent_channels": 128,
-  "layers_per_block": [
-    4,
-    3,
-    3,
-    3,
-    4
-  ],
-  "out_channels": 3,
-  "patch_size": 4,
-  "patch_size_t": 1,
-  "resnet_norm_eps": 1e-06,
-  "scaling_factor": 1.0,
-  "spatio_temporal_scaling": [
-    true,
-    true,
-    true,
-    false
-  ]
-}
+{"_class_name": "CausalVideoAutoencoder", "dims": 3, "in_channels": 3, "out_channels": 3, "latent_channels": 128, "blocks": [["res_x", 4], ["compress_all", 1], ["res_x_y", 1], ["res_x", 3], ["compress_all", 1], ["res_x_y", 1], ["res_x", 3], ["compress_all", 1], ["res_x", 3], ["res_x", 4]], "scaling_factor": 1.0, "norm_layer": "pixel_norm", "patch_size": 4, "latent_log_var": "uniform", "use_quant_conv": false, "causal_decoder": false}