diff --git a/tests/e2e/online_serving/test_qwen_image_layered_expansion.py b/tests/e2e/online_serving/test_qwen_image_layered_expansion.py
index c26e21039..315fba6ef 100644
--- a/tests/e2e/online_serving/test_qwen_image_layered_expansion.py
+++ b/tests/e2e/online_serving/test_qwen_image_layered_expansion.py
@@ -7,7 +7,7 @@ and are supported by Qwen-Image-Layered model.
 Kept cases (maximum feature coverage, no cpu-offload):
   sp_001              : cache_dit + Ulysses-SP 2          (2×H100)
   cfg_parallel_002    : cache_dit + CFG-Parallel 2        (2×H100)
-  layers_guard_001    : layerwise offload + layers=3      (1×H100, issue #1969 guard)
+  layers_guard_001    : layerwise offload + layers=2      (1×H100, issue #1969 guard)
 
 Total distinct features covered: cache_dit, Ulysses-SP, CFG-Parallel, layerwise-offload.
 """
@@ -116,8 +116,8 @@ LAYERS_GUARD_CASES = [
             model=MODEL,
             server_args=["--enable-layerwise-offload"],
         ),
-        3,
-        id="layers_guard_001_layers3",
+        2,
+        id="layers_guard_001_layers2",
         marks=SINGLE_CARD_FEATURE_MARKS,
     ),
 ]
diff --git a/tests/entrypoints/openai_api/test_image_server.py b/tests/entrypoints/openai_api/test_image_server.py
index 31a82102a..5a7ef7bf0 100644
--- a/tests/entrypoints/openai_api/test_image_server.py
+++ b/tests/entrypoints/openai_api/test_image_server.py
@@ -1244,7 +1244,7 @@ def test_parameter_validation():
 
     # Invalid layers for layered models (must stay within the backend-supported range)
     with pytest.raises(ValueError):
-        ImageGenerationRequest(prompt="test", layers=2)
+        ImageGenerationRequest(prompt="test", layers=1)
 
     with pytest.raises(ValueError):
         ImageGenerationRequest(prompt="test", layers=11)
@@ -1663,13 +1663,13 @@ def test_image_edit_invalid_layers(async_omni_test_client):
         files=[("image", img_bytes)],
         data={
             "prompt": "test",
-            "layers": 2,
+            "layers": 1,
         },
     )
     assert response.status_code == 400
     detail = response.json()["detail"]
     assert "Invalid layers" in detail
-    assert "layers must be between 3 and 10 inclusive" in detail
+    assert "layers must be between 2 and 10 inclusive" in detail
 
     # Test layers above the supported range
     response = async_omni_test_client.post(
@@ -1683,7 +1683,7 @@ def test_image_edit_invalid_layers(async_omni_test_client):
     assert response.status_code == 400
     detail = response.json()["detail"]
     assert "Invalid layers" in detail
-    assert "layers must be between 3 and 10 inclusive" in detail
+    assert "layers must be between 2 and 10 inclusive" in detail
 
 
 def test_image_edit_resolution_and_size_conflict(async_omni_test_client):
diff --git a/vllm_omni/entrypoints/openai/image_api_utils.py b/vllm_omni/entrypoints/openai/image_api_utils.py
index b958d786a..5bd79e936 100644
--- a/vllm_omni/entrypoints/openai/image_api_utils.py
+++ b/vllm_omni/entrypoints/openai/image_api_utils.py
@@ -14,7 +14,7 @@ import io
 import PIL.Image
 
 SUPPORTED_LAYERED_RESOLUTIONS = (640, 1024)
-SUPPORTED_LAYERED_LAYERS_RANGE = range(3, 11)
+SUPPORTED_LAYERED_LAYERS_RANGE = range(2, 11)
 
 
 def parse_size(size_str: str) -> tuple[int, int]:
diff --git a/vllm_omni/entrypoints/openai/protocol/images.py b/vllm_omni/entrypoints/openai/protocol/images.py
index 78f63d387..b7247962c 100644
--- a/vllm_omni/entrypoints/openai/protocol/images.py
+++ b/vllm_omni/entrypoints/openai/protocol/images.py
@@ -60,7 +60,7 @@ class ImageGenerationRequest(BaseModel):
     user: str | None = Field(default=None, description="User identifier for tracking")
     layers: int | None = Field(
         default=None,
-        description="Number of output layers for layered image models. Supported range: 3-10.",
+        description="Number of output layers for layered image models. Supported range: 2-10.",
     )
 
     @field_validator("size")