[diffusion] model: support mutli-image input and qwen-image-edit-2509 (#15005)

python/sglang/multimodal_gen/test/server/testcase_configs.py

@@ -226,6 +226,14 @@ TI2I_sampling_params = DiffusionSamplingParams(
     image_path="https://github.com/lm-sys/lm-sys.github.io/releases/download/test/TI2I_Qwen_Image_Edit_Input.jpg",
 )
 
+MULTI_IMAGE_TI2I_sampling_params = DiffusionSamplingParams(
+    prompt="The magician bear is on the left, the alchemist bear is on the right, facing each other in the central park square.",
+    image_path=[
+        "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/edit2509/edit2509_1.jpg",
+        "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/edit2509/edit2509_2.jpg",
+    ],
+)
+
 T2V_PROMPT = "A curious raccoon"
 
 TI2V_sampling_params = DiffusionSamplingParams(
@@ -288,6 +296,16 @@ ONE_GPU_CASES_A: list[DiffusionTestCase] = [
         ),
         TI2I_sampling_params,
     ),
+    DiffusionTestCase(
+        "qwen_image_edit_2509_ti2i",
+        DiffusionServerArgs(
+            model_path="Qwen/Qwen-Image-Edit-2509",
+            modality="image",
+            warmup_text=0,
+            warmup_edit=1,
+        ),
+        MULTI_IMAGE_TI2I_sampling_params,
+    ),
 ]
 
 ONE_GPU_CASES_B: list[DiffusionTestCase] = [