[Misc] Consolidate LingBot text-to-video runner

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

benchmarks/lingbot_video/dense_pipeline_parity.py

@@ -167,7 +167,7 @@ def main() -> None:
     ]
     native_cmd = [
         sys.executable,
-        "examples/offline_inference/text_to_video/text_to_video_lingbot.py",
+        "examples/offline_inference/text_to_video/text_to_video.py",
         "--model",
         args.model,
         "--prompt",

docs/user_guide/examples/offline_inference/text_to_video.md

@@ -12,6 +12,7 @@ For backend selection and SageAttention usage, see the [Diffusion Attention Back
 | Model | Default Resolution | Default Frames | Default Steps | Guidance | VRAM (BF16) |
 |---|---|---|---|---|---|
 | `Wan-AI/Wan2.2-T2V-A14B-Diffusers` | 720x1280 | 81 | 40 | 4.0 | ~60 GiB |
+| `robbyant/lingbot-video-dense-1.3b` / `robbyant/lingbot-video-moe-30b-a3b` | 192x320 | 9 | 2 | 3.0 | ~68 GiB (MoE smoke) |
 | `Lightricks/LTX-2` | 512x768 | 121 | 40 | video 3.0 / audio 7.0 | Model-dependent |
 | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v` | 480x832 | 121 | 50 | 6.0 | 1×A100 80GB |
 | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v` | 720x1280 | 121 | 50 | 6.0 | FP8 + VAE tiling required |
@@ -35,6 +36,25 @@ python text_to_video.py \
   --output t2v_out.mp4
 ```
 
+### LingBot-Video
+
+The shared runner recognizes both official LingBot checkpoint IDs and selects
+the native `LingBotVideoPipeline` automatically:
+
+```bash
+python text_to_video.py \
+  --model robbyant/lingbot-video-dense-1.3b \
+  --prompt "a robotic arm picks up a red block" \
+  --height 192 --width 320 --num-frames 9 --num-inference-steps 2 \
+  --guidance-scale 3.0 --flow-shift 3.0 --fps 24 \
+  --output lingbot_t2v.mp4
+```
+
+Use `robbyant/lingbot-video-moe-30b-a3b` for the MoE checkpoint. For local
+paths without `lingbot` in the directory name, add
+`--model-class-name LingBotVideoPipeline`. Model-only options use
+`--extra-body`, for example `'{"batch_cfg": true, "output_type": "np"}'`.
+
 ### LTX-2
 
 ```bash

examples/offline_inference/text_to_video/text_to_video.md

@@ -8,6 +8,7 @@ A unified script for text-to-video generation. Supports multiple models with mod
 |---|---|---|---|---|---|
 | `Wan-AI/Wan2.1-VACE-1.3B-diffusers` | 480x832 | 81 | 30 | 5.0 | ~20 GiB (RTX 5090, VAE tiling) |
 | `Wan-AI/Wan2.2-T2V-A14B-Diffusers` | 720x1280 | 81 | 40 | 4.0 | ~60 GiB |
+| `robbyant/lingbot-video-dense-1.3b` / `robbyant/lingbot-video-moe-30b-a3b` | 192x320 | 9 | 2 | 3.0 | ~68 GiB (MoE smoke) |
 | `Lightricks/LTX-2` | 512x768 | 121 | 40 | video 3.0 / audio 7.0 | Model-dependent |
 | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v` | 480x832 | 121 | 50 | 6.0 | 1×A100 80GB |
 | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v` | 720x1280 | 121 | 50 | 6.0 | FP8 + VAE tiling required |
@@ -57,18 +58,31 @@ python text_to_video.py \
 
 ### LingBot-Video
 
-The dedicated LingBot example explicitly selects the video output modality:
+The shared runner recognizes the official dense and MoE checkpoint IDs, selects
+`LingBotVideoPipeline`, and builds the canonical video request envelope:
 
 ```bash
-python examples/offline_inference/text_to_video/text_to_video_lingbot.py \
+python text_to_video.py \
   --model robbyant/lingbot-video-dense-1.3b \
+  --prompt "a robotic arm picks up a red block" \
   --height 192 --width 320 --num-frames 9 --num-inference-steps 2 \
+  --guidance-scale 3.0 --flow-shift 3.0 --fps 24 \
   --output lingbot_t2v.mp4
 ```
 
 Use the same command with `robbyant/lingbot-video-moe-30b-a3b` for the MoE
 checkpoint. Requested frame counts are rounded upward to the causal
-VAE's `4n+1` grid.
+VAE's `4n+1` grid. For a local checkpoint path whose name does not contain
+`lingbot`, pass `--model-class-name LingBotVideoPipeline`.
+
+LingBot-only options such as `batch_cfg` and `output_type` use the shared
+model-extra channel, for example:
+
+```bash
+python text_to_video.py \
+  --model robbyant/lingbot-video-dense-1.3b \
+  --extra-body '{"batch_cfg": true, "output_type": "np"}'
+```
 
 ### LTX-2
 

examples/offline_inference/text_to_video/text_to_video.py

@@ -80,6 +80,17 @@ _MODEL_PRESETS = {
         "fps": 16,
         "output": "helios_output.mp4",
     },
+    "lingbot": {
+        "model_class_name": "LingBotVideoPipeline",
+        "height": 192,
+        "width": 320,
+        "num_frames": 9,
+        "num_inference_steps": 2,
+        "guidance_scale": 3.0,
+        "fps": 24,
+        "flow_shift": 3.0,
+        "output": "lingbot_video_output.mp4",
+    },
     "ltx2": {
         "height": 512,
         "width": 768,
@@ -110,27 +121,49 @@ _MODEL_PRESETS = {
 def _detect_preset(model: str, model_class_name: str | None = None) -> dict:
     model_lower = model.lower()
     class_lower = (model_class_name or "").lower()
-    if "distilled" in class_lower or "distilled" in model_lower:
-        return _MODEL_PRESETS["ltx2_distilled"]
-    if "ltx23" in class_lower or "ltx-2.3" in model_lower or "ltx_2.3" in model_lower:
-        return _MODEL_PRESETS["ltx23"]
-    if "ltx2" in class_lower or "ltx-2" in model_lower or "ltx_2" in model_lower:
+    if "lingbot" in model_lower or "lingbotvideo" in class_lower:
+        return _MODEL_PRESETS["lingbot"]
+    if "ltx" in class_lower or "ltx" in model_lower:
+        if "distilled" in class_lower or "distilled" in model_lower:
+            return _MODEL_PRESETS["ltx2_distilled"]
+        if "ltx23" in class_lower or "ltx-2.3" in model_lower or "ltx_2.3" in model_lower:
+            return _MODEL_PRESETS["ltx23"]
         return _MODEL_PRESETS["ltx2"]
-    if "vace" in model_lower:
+    if "vace" in model_lower or "vace" in class_lower:
         return _MODEL_PRESETS["vace"]
     # Edge must be matched before the generic cosmos branch (its "cosmos" substring would
     # otherwise pick up the Nano/Super 720p / gs 6.0 / flow_shift 10.0 preset).
     if ("cosmos" in model_lower or "cosmos" in class_lower) and ("edge" in model_lower or "edge" in class_lower):
         return _MODEL_PRESETS["cosmos3_edge"]
-    if "cosmos" in model_lower:
+    if "cosmos" in model_lower or "cosmos" in class_lower:
         return _MODEL_PRESETS["cosmos"]
-    if "hunyuan" in model_lower:
+    if "hunyuan" in model_lower or "hunyuan" in class_lower:
         return _MODEL_PRESETS["hunyuan"]
-    if "helios" in model_lower:
+    if "helios" in model_lower or "helios" in class_lower:
         return _MODEL_PRESETS["helios"]
     return _MODEL_PRESETS["wan"]
 
 
+def build_text_to_video_prompt(prompt: str, negative_prompt: str | None) -> dict[str, Any]:
+    """Build the canonical request envelope for the shared T2V example."""
+    result: dict[str, Any] = {
+        "prompt": prompt,
+        "modalities": ["video"],
+    }
+    if negative_prompt is not None:
+        result["negative_prompt"] = negative_prompt
+    return result
+
+
+def _normalize_float_tensor(tensor: torch.Tensor) -> torch.Tensor:
+    """Normalize decoded frames without remapping tensors already in [0, 1]."""
+    if not tensor.is_floating_point():
+        return tensor
+    if float(tensor.min()) < 0.0:
+        return tensor.clamp(-1, 1) * 0.5 + 0.5
+    return tensor.clamp(0, 1)
+
+
 def parse_profiler_config(value: str) -> dict[str, Any]:
     try:
         config = json.loads(value)
@@ -160,7 +193,7 @@ def parse_extra_body(value: str) -> dict[str, Any]:
 def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(
         description="Generate a video from a text prompt. "
-        "Supports Wan2.2, HunyuanVideo-1.5, Helios, and other text-to-video models."
+        "Supports Wan2.2, HunyuanVideo-1.5, Helios, LingBot-Video, and other text-to-video models."
     )
     parser.add_argument(
         "--model",
@@ -408,6 +441,7 @@ def main():
     for key, default_val in preset.items():
         if getattr(args, key.replace("-", "_"), None) is None:
             setattr(args, key.replace("-", "_"), default_val)
+    model_class_name = args.model_class_name
 
     generator = torch.Generator(device=current_omni_platform.device_type).manual_seed(args.seed)
     # Cache-dit config (Wan2.2 only)
@@ -513,12 +547,11 @@ def main():
             lora_path=lora_path,
         )
 
-    prompt_dict = {"prompt": args.prompt}
-    if args.negative_prompt is not None:
-        prompt_dict["negative_prompt"] = args.negative_prompt
-    elif preset not in (_MODEL_PRESETS["ltx2"], _MODEL_PRESETS["ltx23"]):
+    negative_prompt = args.negative_prompt
+    if negative_prompt is None and all(preset is not _MODEL_PRESETS[name] for name in ("lingbot", "ltx2", "ltx23")):
         # Preserve the historical empty-prompt behavior for non-LTX examples.
-        prompt_dict["negative_prompt"] = ""
+        negative_prompt = ""
+    prompt_dict = build_text_to_video_prompt(args.prompt, negative_prompt)
 
     extra_args = {}
     if lora_request:
@@ -630,8 +663,7 @@ def main():
                 frame_tensor = frame_tensor[0]
             if frame_tensor.dim() == 3 and frame_tensor.shape[0] in (3, 4):
                 frame_tensor = frame_tensor.permute(1, 2, 0)
-            if frame_tensor.is_floating_point():
-                frame_tensor = frame_tensor.clamp(-1, 1) * 0.5 + 0.5
+            frame_tensor = _normalize_float_tensor(frame_tensor)
             return frame_tensor.float().numpy()
         if isinstance(frame, np.ndarray):
             frame_array = frame
@@ -683,8 +715,7 @@ def main():
                 video_tensor = video_tensor[0]
         elif video_tensor.dim() == 4 and video_tensor.shape[0] in (3, 4):
             video_tensor = video_tensor.permute(1, 2, 3, 0)
-        if video_tensor.is_floating_point():
-            video_tensor = video_tensor.clamp(-1, 1) * 0.5 + 0.5
+        video_tensor = _normalize_float_tensor(video_tensor)
         video_array = video_tensor.float().numpy()
     elif isinstance(frames, np.ndarray):
         video_array = frames

examples/offline_inference/text_to_video/text_to_video_lingbot.py

@@ -1,131 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-
-from __future__ import annotations
-
-import argparse
-import time
-from pathlib import Path
-from typing import Any
-
-import numpy as np
-import torch
-
-from vllm_omni.diffusion.data import DiffusionParallelConfig
-from vllm_omni.entrypoints.omni import Omni
-from vllm_omni.inputs.data import OmniDiffusionSamplingParams
-from vllm_omni.outputs import OmniRequestOutput
-from vllm_omni.platforms import current_omni_platform
-
-
-def parse_args() -> argparse.Namespace:
-    parser = argparse.ArgumentParser(description="Generate text-to-video with a LingBot-Video checkpoint.")
-    parser.add_argument("--model", default="robbyant/lingbot-video-dense-1.3b")
-    parser.add_argument("--prompt", default="a robotic arm picks up a red block")
-    parser.add_argument("--negative-prompt", default=None)
-    parser.add_argument("--output", default="lingbot_video_output.mp4")
-    parser.add_argument("--height", type=int, default=192)
-    parser.add_argument("--width", type=int, default=320)
-    parser.add_argument("--num-frames", type=int, default=9)
-    parser.add_argument("--num-inference-steps", type=int, default=2)
-    parser.add_argument("--guidance-scale", type=float, default=3.0)
-    parser.add_argument("--flow-shift", type=float, default=3.0)
-    parser.add_argument("--seed", type=int, default=42)
-    parser.add_argument("--fps", type=int, default=24)
-    parser.add_argument("--output-type", choices=["pt", "np"], default="pt")
-    parser.add_argument("--batch-cfg", action="store_true")
-    return parser.parse_args()
-
-
-def _peak_memory_mb(output: Any) -> float:
-    result = output[0] if isinstance(output, list) and output else output
-    return float(getattr(result, "peak_memory_mb", 0.0) or 0.0)
-
-
-def _extract_video(output: Any) -> Any:
-    if isinstance(output, list):
-        output = output[0] if output else None
-    if isinstance(output, OmniRequestOutput):
-        if output.final_output_type != "image":
-            raise ValueError(f"Unexpected output type {output.final_output_type!r}.")
-        if not output.images:
-            raise ValueError("No video frames found in OmniRequestOutput.")
-        return output.images[0] if len(output.images) == 1 else output.images
-    return output
-
-
-def _to_frame_array(video: Any) -> np.ndarray:
-    if isinstance(video, torch.Tensor):
-        tensor = video.detach().cpu()
-        if tensor.dim() == 5:
-            tensor = tensor[0]
-        if tensor.dim() == 4 and tensor.shape[-1] not in (3, 4):
-            if tensor.shape[0] in (3, 4):
-                tensor = tensor.permute(1, 2, 3, 0)
-            elif tensor.shape[1] in (3, 4):
-                tensor = tensor.permute(0, 2, 3, 1)
-        if tensor.is_floating_point():
-            if float(tensor.min()) < 0.0:
-                tensor = tensor.clamp(-1, 1) * 0.5 + 0.5
-            else:
-                tensor = tensor.clamp(0, 1)
-        return tensor.float().numpy()
-    if isinstance(video, np.ndarray):
-        array = video[0] if video.ndim == 5 else video
-        if np.issubdtype(array.dtype, np.integer):
-            return array.astype(np.float32) / 255.0
-        return array.astype(np.float32, copy=False)
-    if isinstance(video, list):
-        return np.stack([_to_frame_array(frame) for frame in video], axis=0)
-    return np.asarray(video, dtype=np.float32)
-
-
-def main() -> None:
-    args = parse_args()
-    generator = torch.Generator(device=current_omni_platform.device_type).manual_seed(args.seed)
-    omni = Omni(
-        model=args.model,
-        model_class_name="LingBotVideoPipeline",
-        flow_shift=args.flow_shift,
-        parallel_config=DiffusionParallelConfig(),
-    )
-
-    prompt: dict[str, Any] = {
-        "prompt": args.prompt,
-        "modalities": ["video"],
-        "num_frames": args.num_frames,
-    }
-    if args.negative_prompt is not None:
-        prompt["negative_prompt"] = args.negative_prompt
-
-    sampling_params = OmniDiffusionSamplingParams(
-        height=args.height,
-        width=args.width,
-        num_frames=args.num_frames,
-        num_inference_steps=args.num_inference_steps,
-        guidance_scale=args.guidance_scale,
-        generator=generator,
-        output_type=args.output_type,
-        extra_args={"batch_cfg": args.batch_cfg, "shift": args.flow_shift},
-    )
-
-    start = time.perf_counter()
-    output = omni.generate(prompt, sampling_params)
-    elapsed = time.perf_counter() - start
-    print(f"Total generation time: {elapsed:.4f} seconds ({elapsed * 1000:.2f} ms)")
-    peak_mb = _peak_memory_mb(output)
-    if peak_mb:
-        print(f"Worker peak GPU memory (reserved): {peak_mb:.2f} MiB ({peak_mb / 1024:.2f} GiB)")
-
-    video = _to_frame_array(_extract_video(output))
-    output_path = Path(args.output)
-    output_path.parent.mkdir(parents=True, exist_ok=True)
-    from diffusers.utils import export_to_video
-
-    export_to_video(list(video), str(output_path), fps=args.fps)
-    print(f"Saved generated video to {output_path}")
-    omni.close()
-
-
-if __name__ == "__main__":
-    main()

recipes/Robbyant/LingBot-Video.md

@@ -27,7 +27,7 @@ parallel, cache, quantized, or expert-kernel backends.
 - Dense checkpoint: <https://huggingface.co/robbyant/lingbot-video-dense-1.3b>
 - MoE checkpoint: <https://huggingface.co/robbyant/lingbot-video-moe-30b-a3b>
 - Upstream project: <https://github.com/Robbyant/lingbot-video>
-- Related offline example: [`examples/offline_inference/text_to_video/text_to_video_lingbot.py`](../../examples/offline_inference/text_to_video/text_to_video_lingbot.py)
+- Related offline example: [`examples/offline_inference/text_to_video/text_to_video.py`](../../examples/offline_inference/text_to_video/text_to_video.py)
 - Related online video API docs: [`docs/serving/videos_api.md`](../../docs/serving/videos_api.md)
 
 ## Hardware Support
@@ -52,7 +52,7 @@ The MoE path is validated with BF16 expert weights.
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 \
-python examples/offline_inference/text_to_video/text_to_video_lingbot.py \
+python examples/offline_inference/text_to_video/text_to_video.py \
   --model robbyant/lingbot-video-dense-1.3b \
   --prompt "a robotic arm picks up a red block" \
   --output lingbot_t2v.mp4 \
@@ -70,7 +70,7 @@ python examples/offline_inference/text_to_video/text_to_video_lingbot.py \
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 \
-python examples/offline_inference/text_to_video/text_to_video_lingbot.py \
+python examples/offline_inference/text_to_video/text_to_video.py \
   --model robbyant/lingbot-video-moe-30b-a3b \
   --prompt "a robotic arm picks up a red block" \
   --output lingbot_moe_t2v.mp4 \

tests/examples/offline_inference/test_text_to_video_prompts.py

@@ -0,0 +1,79 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from __future__ import annotations
+
+import pytest
+import torch
+
+from examples.offline_inference.text_to_video.text_to_video import (
+    _MODEL_PRESETS,
+    _detect_preset,
+    _normalize_float_tensor,
+    build_text_to_video_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_video_builds_canonical_prompt(
+    negative_prompt: str | None,
+    expected_negative_prompt: str | None,
+) -> None:
+    result = build_text_to_video_prompt("a robot waves", negative_prompt)
+
+    assert result["prompt"] == "a robot waves"
+    assert result["modalities"] == ["video"]
+    if expected_negative_prompt is None:
+        assert "negative_prompt" not in result
+    else:
+        assert result["negative_prompt"] == expected_negative_prompt
+
+
+@pytest.mark.parametrize(
+    ("model", "model_class_name", "preset_name"),
+    [
+        ("robbyant/lingbot-video-dense-1.3b", None, "lingbot"),
+        ("/models/custom-checkpoint", "LingBotVideoPipeline", "lingbot"),
+        ("Lightricks/LTX-2", "LTX2DistilledPipeline", "ltx2_distilled"),
+        ("BestWishYsh/Helios-Distilled", None, "helios"),
+        ("/models/cosmos-edge", "Cosmos3EdgeVFMTransformer", "cosmos3_edge"),
+        ("/models/vace", "WanVACEPipeline", "vace"),
+    ],
+)
+def test_detect_preset_is_scoped_to_model_family(
+    model: str,
+    model_class_name: str | None,
+    preset_name: str,
+) -> None:
+    assert _detect_preset(model, model_class_name) is _MODEL_PRESETS[preset_name]
+
+
+def test_lingbot_preset_matches_lingbot_defaults() -> None:
+    assert _MODEL_PRESETS["lingbot"] == {
+        "model_class_name": "LingBotVideoPipeline",
+        "height": 192,
+        "width": 320,
+        "num_frames": 9,
+        "num_inference_steps": 2,
+        "guidance_scale": 3.0,
+        "fps": 24,
+        "flow_shift": 3.0,
+        "output": "lingbot_video_output.mp4",
+    }
+
+
+def test_normalize_float_tensor_preserves_zero_to_one_frames() -> None:
+    frames = torch.tensor([0.0, 0.25, 1.0, 1.5])
+
+    assert torch.equal(_normalize_float_tensor(frames), torch.tensor([0.0, 0.25, 1.0, 1.0]))
+
+
+def test_normalize_float_tensor_maps_negative_one_to_one_frames() -> None:
+    frames = torch.tensor([-1.5, -1.0, 0.0, 1.0, 1.5])
+
+    assert torch.equal(_normalize_float_tensor(frames), torch.tensor([0.0, 0.0, 0.5, 1.0, 1.0]))