[Misc] Build canonical image task prompts (#6049)

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>

tests/examples/offline_inference/test_image_task_prompts.py

@@ -0,0 +1,47 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from __future__ import annotations
+
+import pytest
+from PIL import Image
+
+from examples.offline_inference.image_to_video.image_to_video import build_image_to_video_prompt
+from examples.offline_inference.text_to_image.text_to_image import build_text_to_image_prompt
+
+pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
+
+
+@pytest.mark.parametrize(
+    ("negative_prompt", "expected_negative_prompt"),
+    [(None, None), ("", ""), ("blurry", "blurry")],
+)
+def test_text_to_image_builds_canonical_prompt(
+    negative_prompt: str | None,
+    expected_negative_prompt: str | None,
+) -> None:
+    result = build_text_to_image_prompt("a red fox", negative_prompt)
+
+    assert result["prompt"] == "a red fox"
+    assert result["modalities"] == ["image"]
+    if expected_negative_prompt is None:
+        assert "negative_prompt" not in result
+    else:
+        assert result["negative_prompt"] == expected_negative_prompt
+
+
+def test_image_to_video_builds_canonical_prompt() -> None:
+    image = Image.new("RGB", (32, 16), "red")
+
+    result = build_image_to_video_prompt(
+        prompt="the fox turns toward the camera",
+        negative_prompt="flicker",
+        media_inputs={"image": image},
+    )
+
+    assert result == {
+        "prompt": "the fox turns toward the camera",
+        "modalities": ["video"],
+        "multi_modal_data": {"image": image},
+        "negative_prompt": "flicker",
+    }

tests/model_extras/test_model_extras.py

@@ -3,6 +3,8 @@
 
 from __future__ import annotations
 
+from typing import Any
+
 import pytest
 from PIL import Image
 
@@ -135,67 +137,6 @@ def test_lingbot_extra_registry_declares_request_params() -> None:
     assert should_init_extra_args_for_non_diffusion_stages("LingBotVideoPipeline") is False
 
 
-@pytest.mark.core_model
-@pytest.mark.cpu
-def test_lingbot_text_to_image_prompt_builder_preserves_empty_negative_prompt() -> None:
-    assert build_text_to_image_prompt(
-        "LingBotVideoPipeline",
-        prompt="a red fox in fresh snow",
-        negative_prompt="",
-        height=192,
-        width=320,
-    ) == {
-        "prompt": "a red fox in fresh snow",
-        "modalities": ["image"],
-        "negative_prompt": "",
-    }
-
-
-@pytest.mark.core_model
-@pytest.mark.cpu
-def test_lingbot_image_to_video_prompt_builder() -> None:
-    image = Image.new("RGB", (320, 192), "red")
-    result = build_image_to_video_prompt(
-        "LingBotVideoPipeline",
-        prompt="the fox looks toward the camera",
-        negative_prompt=None,
-        media_inputs={"image": image},
-        height=192,
-        width=320,
-        num_frames=9,
-    )
-    assert result == {
-        "prompt": "the fox looks toward the camera",
-        "modalities": ["video"],
-        "multi_modal_data": {"image": image},
-        "num_frames": 9,
-    }
-
-
-@pytest.mark.core_model
-@pytest.mark.cpu
-@pytest.mark.parametrize(
-    "media_inputs",
-    [
-        {},
-        {"image": "input.png"},
-        {"image": [Image.new("RGB", (16, 16))]},
-        {"image": Image.new("RGB", (16, 16)), "video": b"video"},
-    ],
-    ids=["missing", "path", "multiple", "extra-modality"],
-)
-def test_lingbot_image_to_video_prompt_builder_rejects_invalid_media(
-    media_inputs: dict[str, object],
-) -> None:
-    with pytest.raises(ValueError, match="exactly one PIL image"):
-        build_image_to_video_prompt(
-            "LingBotVideoPipeline",
-            prompt="move",
-            negative_prompt=None,
-            media_inputs=media_inputs,
-        )
-
-
 @pytest.mark.core_model
 @pytest.mark.cpu
 @pytest.mark.parametrize("pipeline_name", ["Cosmos3OmniDiffusersPipeline", "Cosmos3OmniPipeline"])
@@ -342,8 +283,11 @@ def test_ming_flash_omni_declared_extra_args_route_into_sampling_params() -> Non
 def test_ming_flash_omni_text_to_image_prompt_builder() -> None:
     assert build_text_to_image_prompt(
         "MingImagePipeline",
-        prompt="Please draw a cute cat.",
-        negative_prompt="ugly, blurry",
+        {
+            "prompt": "Please draw a cute cat.",
+            "modalities": ["image"],
+            "negative_prompt": "ugly, blurry",
+        },
         height=512,
         width=768,
     ) == {
@@ -360,8 +304,7 @@ def test_ming_flash_omni_text_to_image_prompt_builder() -> None:
     # pipeline's 1024x1024 default still applies.
     assert build_text_to_image_prompt(
         "MingImagePipeline",
-        prompt="Draw a poster.",
-        negative_prompt=None,
+        {"prompt": "Draw a poster.", "modalities": ["image"]},
     ) == {
         "prompt": "Draw a poster.",
         "modalities": ["image"],
@@ -391,28 +334,6 @@ def test_ming_flash_omni_image_to_image_prompt_builder() -> None:
     assert "negative_prompt" not in result
 
 
-@pytest.mark.core_model
-@pytest.mark.cpu
-@pytest.mark.parametrize("pipeline_name", ["Cosmos3OmniDiffusersPipeline", "Cosmos3OmniPipeline"])
-def test_cosmos3_text_to_image_prompt_builder_selects_image_modality(pipeline_name: str) -> None:
-    assert build_text_to_image_prompt(
-        pipeline_name,
-        prompt="a red sports car at golden hour",
-        negative_prompt="blurry, distorted",
-        height=1024,
-        width=1024,
-    ) == {
-        "prompt": "a red sports car at golden hour",
-        "modalities": ["image"],
-        "negative_prompt": "blurry, distorted",
-    }
-    assert build_text_to_image_prompt(
-        pipeline_name,
-        prompt="a red sports car",
-        negative_prompt=None,
-    ) == {"prompt": "a red sports car", "modalities": ["image"]}
-
-
 @pytest.mark.core_model
 @pytest.mark.cpu
 def test_audiox_extra_registry_declares_request_and_response_params() -> None:
@@ -505,8 +426,11 @@ def test_unknown_pipeline_has_empty_extra_registry() -> None:
 def test_bagel_text_to_image_prompt_builder() -> None:
     assert build_text_to_image_prompt(
         "BagelPipeline",
-        prompt="a cat",
-        negative_prompt="blurry",
+        {
+            "prompt": "a cat",
+            "modalities": ["image"],
+            "negative_prompt": "blurry",
+        },
         height=512,
         width=768,
     ) == {
@@ -543,14 +467,17 @@ def test_bagel_image_to_image_prompt_builder() -> None:
 
 @pytest.mark.core_model
 @pytest.mark.cpu
-def test_unknown_pipeline_uses_default_text_to_image_prompt() -> None:
-    assert build_text_to_image_prompt(
-        "UnknownPipeline",
-        prompt="a cat",
-        negative_prompt=None,
-        height=512,
-        width=512,
-    ) == {"prompt": "a cat"}
+def test_unknown_pipeline_preserves_canonical_text_to_image_prompt() -> None:
+    canonical_prompt = {"prompt": "a cat", "modalities": ["image"]}
+    assert (
+        build_text_to_image_prompt(
+            "UnknownPipeline",
+            canonical_prompt,
+            height=512,
+            width=512,
+        )
+        is canonical_prompt
+    )
 
 
 @pytest.mark.core_model
@@ -569,12 +496,14 @@ def test_unknown_pipeline_uses_default_image_to_image_prompt() -> None:
     }
 
 
-def _build_vace_prompt(media_inputs: dict[str, object], *, num_frames: int = 5) -> dict:
+def _build_vace_prompt(media_inputs: dict[str, Any], *, num_frames: int = 5) -> dict:
     return build_image_to_video_prompt(
         "WanVACEPipeline",
-        prompt="a bird flying",
-        negative_prompt=None,
-        media_inputs=media_inputs,
+        {
+            "prompt": "a bird flying",
+            "modalities": ["video"],
+            "multi_modal_data": media_inputs,
+        },
         height=16,
         width=320,
         num_frames=num_frames,
@@ -597,7 +526,7 @@ def _build_vace_prompt(media_inputs: dict[str, object], *, num_frames: int = 5)
     ],
     ids=["i2v", "v2lf", "flf2v", "inpaint", "r2v"],
 )
-def test_vace_image_to_video_prompt_builder(media_inputs: dict[str, object]) -> None:
+def test_vace_image_to_video_prompt_builder(media_inputs: dict[str, Any]) -> None:
     result = _build_vace_prompt(media_inputs)
     mmd = result["multi_modal_data"]
     if "reference_images" in mmd:
@@ -616,7 +545,7 @@ def test_vace_image_to_video_prompt_builder(media_inputs: dict[str, object]) ->
         ({"control_image": Image.new("RGB", (320, 16))}, "Unsupported VACE media input"),
     ],
 )
-def test_vace_rejects_invalid_media_combinations(media_inputs: dict[str, object], message: str) -> None:
+def test_vace_rejects_invalid_media_combinations(media_inputs: dict[str, Any], message: str) -> None:
     with pytest.raises(ValueError, match=message):
         _build_vace_prompt(media_inputs)
 
@@ -664,8 +593,7 @@ def test_mammothmoda2_extra_registry_declares_request_and_response_params() -> N
 
     wrapper_prompt = build_text_to_image_prompt(
         "MammothModa2ForConditionalGeneration",
-        prompt="a cat",
-        negative_prompt=None,
+        {"prompt": "a cat", "modalities": ["image"]},
         height=256,
         width=256,
     )
@@ -679,8 +607,11 @@ def test_mammothmoda2_text_to_image_prompt_builder() -> None:
     # prompt is ignored (MammothModa2 t2i uses CFG, not an explicit negative path).
     assert build_text_to_image_prompt(
         "MammothModa2DiTPipeline",
-        prompt="a cat",
-        negative_prompt="blurry",
+        {
+            "prompt": "a cat",
+            "modalities": ["image"],
+            "negative_prompt": "blurry",
+        },
         height=512,
         width=768,
     ) == {