[new-model] Open-H3-Regenerate-2K: 768P H3 draft to 2560x1440, served on the OpenAI video routes (#2035)

Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>

examples/inference/basic/basic_open_h3_regenerate_2k.py

@@ -0,0 +1,87 @@
+# SPDX-License-Identifier: Apache-2.0
+"""Regenerate a 768P MiniMax-H3 draft video at 2560x1440 with Open-H3-Regenerate-2K.
+
+The draft is VAE-encoded (the first 121 frames at 24 fps, 1344x768), its latent is upscaled, and three refine steps
+of the H3 transformer with the released LoRA run at 2560x1440. The output video is silent. See
+docs/inference/open_h3_regenerate_2k.md.
+
+    python examples/inference/basic/basic_open_h3_regenerate_2k.py --video draft.mp4 --prompt "..." --output out/
+"""
+
+from __future__ import annotations
+
+import argparse
+import time
+from pathlib import Path
+
+from fastvideo import VideoGenerator
+from fastvideo.api import (
+    ComponentConfig,
+    EngineConfig,
+    GenerationRequest,
+    GeneratorConfig,
+    InputConfig,
+    OffloadConfig,
+    OutputConfig,
+    PipelineSelection,
+    SamplingConfig,
+)
+
+DEFAULT_MODEL = "Efficient-Large-Model/Open-H3-Regenerate-2K"
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    parser.add_argument("--model-path", default=DEFAULT_MODEL, help="release repo id or a local copy of it")
+    parser.add_argument("--video", required=True, help="768P draft video (URL-free local path)")
+    parser.add_argument("--prompt", required=True, help="text the refine steps are conditioned on")
+    parser.add_argument("--output", type=Path, default=Path("outputs/open_h3_regenerate_2k"))
+    parser.add_argument("--steps", type=int, choices=(2, 3), default=3, help="refine steps (3 is the released setting)")
+    parser.add_argument("--seed", type=int, default=1766580932)
+    parser.add_argument("--attention-backend", default="TORCH_SDPA")
+    parser.add_argument("--draft-size", choices=("768p", "576p"), default="768p",
+                        help="size the draft is encoded at; 576p for drafts from other video models")
+    parser.add_argument("--runs", type=int, default=1, help="repeat the request to measure warm timings")
+    return parser.parse_args()
+
+
+def main() -> None:
+    args = parse_args()
+    args.output.mkdir(parents=True, exist_ok=True)
+    generator = VideoGenerator.from_config(
+        GeneratorConfig(
+            model_path=args.model_path,
+            engine=EngineConfig(num_gpus=1, offload=OffloadConfig(dit=False, dit_layerwise=False, text_encoder=True, vae=False)),
+            pipeline=PipelineSelection(
+                components=ComponentConfig(),
+                experimental={
+                    "attention_backend": args.attention_backend,
+                    "draft_size": args.draft_size,
+                },
+            ),
+        ))
+    try:
+        for run in range(args.runs):
+            started = time.perf_counter()
+            result = generator.generate(
+                GenerationRequest(
+                    prompt=args.prompt,
+                    inputs=InputConfig(video_path=args.video),
+                    sampling=SamplingConfig(height=1440,
+                                            width=2560,
+                                            num_frames=124,
+                                            fps=24,
+                                            num_inference_steps=args.steps,
+                                            guidance_scale=1.0,
+                                            seed=args.seed),
+                    output=OutputConfig(output_path=str(args.output / f"regen2k_{run}.mp4"),
+                                        save_video=True,
+                                        return_frames=False),
+                ))
+            print(f"run {run}: {time.perf_counter() - started:.1f}s -> {result.video_path}")
+    finally:
+        generator.shutdown()
+
+
+if __name__ == "__main__":
+    main()