[Bugfix] Limit Qwen-Image-Edit-2511 input image count (#2840)

Signed-off-by: david6666666 <530634352@qq.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>

vllm_omni/entrypoints/openai/api_server.py

@@ -1473,12 +1473,24 @@ async def edit_images(
             input_images_list.extend(urls)
         if not input_images_list:
             raise HTTPException(status_code=422, detail="Field 'image' or 'url' is required")
-        pil_images = await _load_input_images(input_images_list)
-        if len(pil_images) > 1 and not _supports_multimodal_image_inputs(raw_request, engine_client):
+        # Reject oversized multi-image edit requests before fetching or decoding
+        # any inputs. This keeps over-limit URL requests from burning network,
+        # CPU, and memory on work that will be rejected anyway.
+        max_input_images = _get_max_edit_input_images(raw_request, engine_client)
+        if max_input_images is not None and len(input_images_list) > max_input_images:
+            detail = (
+                "Received multiple input images. Only a single image is supported by this model."
+                if max_input_images == 1
+                else (
+                    f"Received {len(input_images_list)} input images. "
+                    f"At most {max_input_images} images are supported by this model."
+                )
+            )
             raise HTTPException(
                 status_code=HTTPStatus.BAD_REQUEST.value,
-                detail="Received multiple input images. Only a single image is supported by this model.",
+                detail=detail,
             )
+        pil_images = await _load_input_images(input_images_list)
         prompt["multi_modal_data"] = {}
         prompt["multi_modal_data"]["image"] = pil_images
 
@@ -1651,18 +1663,25 @@ def _get_engine_and_model(raw_request: Request):
     return engine_client, model_name, normalized_stage_configs
 
 
-def _supports_multimodal_image_inputs(raw_request: Request, engine_client: Any) -> bool:
+def _get_diffusion_od_config(raw_request: Request, engine_client: Any) -> Any:
     diffusion_engine = getattr(raw_request.app.state, "diffusion_engine", None) or engine_client
     get_diffusion_od_config = getattr(diffusion_engine, "get_diffusion_od_config", None)
-    od_config = (
+    return (
         get_diffusion_od_config() if callable(get_diffusion_od_config) else getattr(diffusion_engine, "od_config", None)
     )
 
+
+def _get_max_edit_input_images(raw_request: Request, engine_client: Any) -> int | None:
+    od_config = _get_diffusion_od_config(raw_request, engine_client)
     if od_config is None:
         # Preserve the existing compatibility behavior when the diffusion
         # config is not exposed on the serving surface.
-        return True
-    return bool(getattr(od_config, "supports_multimodal_inputs", False))
+        return None
+
+    if not bool(getattr(od_config, "supports_multimodal_inputs", False)):
+        return 1
+
+    return getattr(od_config, "max_multimodal_image_inputs", None)
 
 
 def _get_lora_from_json_str(lora_body):