diff --git a/comfy/model_detection.py b/comfy/model_detection.py
index 58fe514c4..5a3f2e540 100644
--- a/comfy/model_detection.py
+++ b/comfy/model_detection.py
@@ -282,7 +282,7 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
 
         return dit_config
 
-    if '{}x_embedder.weight'.format(key_prefix) in state_dict_keys and '{}transformer_blocks.0.attn.to_q.weight'.format(key_prefix) in state_dict_keys and '{}single_transformer_blocks.0.attn.to_q.weight'.format(key_prefix) in state_dict_keys: #LongCat-Image (diffusers format, Flux variant)
+    if '{}x_embedder.weight'.format(key_prefix) in state_dict_keys and '{}transformer_blocks.0.attn.to_q.weight'.format(key_prefix) in state_dict_keys and '{}single_transformer_blocks.0.attn.to_q.weight'.format(key_prefix) in state_dict_keys and '{}context_embedder.weight'.format(key_prefix) in state_dict_keys and '{}time_embed.timestep_embedder.linear_1.weight'.format(key_prefix) in state_dict_keys: #LongCat-Image (diffusers format, Flux variant)
         dit_config = {}
         dit_config["image_model"] = "flux"
         dit_config["axes_dim"] = [16, 56, 56]
diff --git a/comfy/supported_models.py b/comfy/supported_models.py
index 8bc12d2fe..ca25ffdcf 100644
--- a/comfy/supported_models.py
+++ b/comfy/supported_models.py
@@ -1691,6 +1691,7 @@ class LongCatImage(supported_models_base.BASE):
         "x_embedder.weight": None,
         "context_embedder.weight": None,
         "single_transformer_blocks.10.attn.to_q.weight": None,
+        "time_embed.timestep_embedder.linear_1.weight": None,
     }
 
     sampling_settings = {