[REFACT]Refactor diffusion outputs to payload metadata (#4922)

Signed-off-by: bjf-frz <frz123db@gmail.com>

examples/offline_inference/lance/end2end.py

@@ -293,16 +293,19 @@ def main():
 
     if args.modality in ("img2text", "video2text"):
         for i, req_output in enumerate(outputs):
-            text = getattr(req_output, "output", None) or getattr(req_output, "text", None)
-            if text is None and hasattr(req_output, "custom_output"):
-                text = (req_output.custom_output or {}).get("text_output")
+            multimodal_output = getattr(req_output, "multimodal_output", {}) or {}
+            metadata = multimodal_output.get("metadata", {}) if isinstance(multimodal_output, dict) else {}
+            text_metadata = metadata.get("text", {}) if isinstance(metadata, dict) else {}
+            text = (multimodal_output.get("text") if isinstance(multimodal_output, dict) else None) or (
+                text_metadata.get("text_output") if isinstance(text_metadata, dict) else None
+            )
+            text = text or getattr(req_output, "output", None) or getattr(req_output, "text", None)
             print(f"[Output {i}] {text}")
         return
 
     if args.modality in ("text2video", "video2video", "image2video"):
         for i, req_output in enumerate(outputs):
-            custom = getattr(req_output, "custom_output", None) or {}
-            frames = custom.get("video_frames")
+            frames = getattr(req_output, "images", None)
             if not frames:
                 print(f"[Output {i}] no video frames returned")
                 continue

examples/offline_inference/lance/gradio_demo.py

@@ -835,12 +835,15 @@ def run_task(
     print(f"[unified] task={task} {width}x{height} frames={num_frames} cfg={cfg} steps={steps} seed={seed}", flush=True)
 
     outputs = list(omni.generate(prompts=formatted, sampling_params_list=params))
-    custom = getattr(outputs[0], "custom_output", None) or {}
-    # Lance/Bagel return text at outputs[0].output (string) or
-    # custom_output["text_output"].
+    multimodal_output = getattr(outputs[0], "multimodal_output", {}) or {}
+    metadata = multimodal_output.get("metadata", {}) if isinstance(multimodal_output, dict) else {}
+    text_metadata = metadata.get("text", {}) if isinstance(metadata, dict) else {}
     text_out = None
     if task in {"x2t_image", "x2t_video"}:
-        text_out = custom.get("text_output") or getattr(outputs[0], "output", None)
+        text_out = (multimodal_output.get("text") if isinstance(multimodal_output, dict) else None) or (
+            text_metadata.get("text_output") if isinstance(text_metadata, dict) else None
+        )
+        text_out = text_out or getattr(outputs[0], "output", None)
         if not isinstance(text_out, str):
             text_out = None
 
@@ -856,13 +859,11 @@ def run_task(
             gr.update(value=str(text_out or "(empty)"), visible=True),
         )
     if task in {"t2v", "i2v", "video_edit"}:
-        frames = custom.get("video_frames")
+        frames = getattr(outputs[0], "images", None)
         if frames is None:
             raise gr.Error("No video frames in output.")
         return (gr.update(visible=False), gr.update(value=_save_video(frames), visible=True), gr.update(visible=False))
-    # image tasks — orchestrator strips ``outputs[0].output`` across the
-    # IPC boundary but preserves ``custom_output``, so prefer the latter.
-    img_out = custom.get("image") or getattr(outputs[0], "output", None)
+    img_out = (getattr(outputs[0], "images", None) or [None])[0] or getattr(outputs[0], "output", None)
     if img_out is None:
         raise gr.Error("No image in output.")
     return (gr.update(value=_save_image(img_out), visible=True), gr.update(visible=False), gr.update(visible=False))

examples/offline_inference/sensenova_u1/end2end.py

@@ -278,12 +278,17 @@ def main():
     )
 
     for req_output in outputs:
-        custom = getattr(req_output, "_custom_output", {}) or {}
-        if args.print_think and custom.get("think_text"):
-            print(f"[Think]\n{custom['think_text']}\n")
+        multimodal_output = getattr(req_output, "multimodal_output", {}) or {}
+        metadata = multimodal_output.get("metadata", {}) if isinstance(multimodal_output, dict) else {}
+        text_metadata = metadata.get("text", {}) if isinstance(metadata, dict) else {}
+        think_text = text_metadata.get("think_text") if isinstance(text_metadata, dict) else None
+        if args.print_think and think_text:
+            print(f"[Think]\n{think_text}\n")
 
         if is_text_output:
-            text = custom.get("text_output", "")
+            text = multimodal_output.get("text", "") if isinstance(multimodal_output, dict) else ""
+            if not text:
+                text = text_metadata.get("text_output", "") if isinstance(text_metadata, dict) else ""
             if not text:
                 text = getattr(req_output, "text", "") or ""
             print(f"[Response]\n{text}")