{
  "schema_version": 1,
  "origin": "rather",
  "generated_media": true,
  "run_id": "visual-pilot-20261013",
  "plan_sha256": "cc5e6b41e2d980e8b0a1690ff9ed5e9d50c32244379c4885785e98fa15c15ee7",
  "model": {
    "id": "wan22-ti2v-5b",
    "label": "Wan 2.2 TI2V 5B",
    "adapter": "wan",
    "repository": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
    "revision": "b8fff7315c768468a5333511427288870b2e9635",
    "modes": [
      "t2v",
      "i2v"
    ],
    "license_url": "https://github.com/Wan-Video/Wan2.2/blob/main/LICENSE.txt",
    "min_vram_gb": 48,
    "generation": {
      "width": 768,
      "height": 448,
      "frames": 121,
      "fps": 24,
      "steps": 40,
      "guidance_scale": 5.0,
      "negative_prompt": "",
      "cpu_offload": false
    }
  },
  "case": {
    "id": "worldmodelbench-robot-blocks",
    "benchmark_id": "worldmodelbench",
    "title": "Can it move just the requested block?",
    "category_id": "instruction-following",
    "mode": "t2v",
    "prompts": [
      "A fixed camera shows a robot arm above a white table. A red cube sits on the left and a blue cube sits on the right. The robot grasps the red cube and places it inside a shallow yellow tray in the middle. The blue cube remains motionless. Continuous shot, realistic motion."
    ],
    "initial_image": null,
    "reference_video": null,
    "source_url": "https://worldmodelbench-team.github.io/",
    "source_revision": "rather-authored-illustration-v1",
    "source_case_id": "rather-robot-blocks",
    "protocol_label": "Rather-authored illustration of instruction following and physical adherence",
    "scope": "illustration",
    "license_name": "Rather-authored prompt / CC BY 4.0",
    "license_url": "https://creativecommons.org/licenses/by/4.0/",
    "attribution": "Prompt and generation by Rather. Inspired by the capabilities studied in WorldModelBench.",
    "reuse_basis": "Rather wrote this prompt independently. No third-party input image or official dataset case is redistributed; the original prompt is provided under CC BY 4.0.",
    "observation": "Does the arm grasp the red cube, place it in the tray and leave the blue cube alone? Watch for sliding, disappearing objects and broken contact.",
    "deviations": [
      "768 x 448 visual preview; not a full benchmark evaluation.",
      "One preselected seed per model; no output selection or prompt optimization.",
      "This is an explanatory scenario, not an official WorldModelBench test case."
    ]
  },
  "result": {
    "status": "completed",
    "task_id": "wan22-ti2v-5b--worldmodelbench-robot-blocks--42",
    "model_id": "wan22-ti2v-5b",
    "case_id": "worldmodelbench-robot-blocks",
    "seed": 42,
    "attempt": "attempt-002",
    "started_at": 1791933165.3969865,
    "files": {
      "turns.json": "97ece1ce7be32a56a56960fb696bb66d7559e942236797bd8acae6907b94134a",
      "last-frame.png": "95096741e4cc1d5b9697bb948780fdec8da8d1c98d306ddfff336023face2cfc",
      "poster.webp": "76a5b78df5458f83c71a118b04db071d5b38fcda2b681368941ebaa5c43bc5f4",
      "output.mp4": "3d2dfab127dcd769c4bb67e0e1b1cd3c2c1c3ac6b1c57d07d276e78ed77c27c6",
      "turn-1.mp4": "3d2dfab127dcd769c4bb67e0e1b1cd3c2c1c3ac6b1c57d07d276e78ed77c27c6"
    },
    "metrics": [],
    "score_status": "not_scored",
    "runner_sources": {
      "__init__.py": "1177f346391bd9981530027988fbf51e1280fff0cf6ab4cfa88d95bd83441e0e",
      "adapters.py": "ed0453d62311d212ffd3686b031fe63e5c3b2e4aced4f75dd1db69c0a3155f73",
      "benchmarks.py": "df9a1d5ec109f29426c85e0c5cb35d28a70c607988edaf7e15dfec2008b02f37",
      "cli.py": "0f553514058b5a8df3ac5f33ed20d28292cc9be1b13e7a93dbbaa30b217daccd",
      "contracts.py": "3bb724b95276068ae488808b49e27eebd4c854d18ac099cb4201db210d5e4ecc",
      "io.py": "44492043f3b3e74a3a752793c94a8cd5c695ce2a586b48577981400fa2bff4a2",
      "publish.py": "4e9c3005db7b0965ee780b8f113fcf587fe2e47d9e92519aee62cfbbbbdf3d31",
      "runpod.py": "ab105a7835d72fd7fc78d92d8416e5d96572643df2b0694d1f44125f341eec3c",
      "worker.py": "ad3e7cea2f30ff6454d1a63f308cb78b98774109dbdc7b8491608f1616123d16"
    },
    "finished_at": 1791933270.0569742,
    "elapsed_seconds": 104.65998792648315,
    "width": 768,
    "height": 448,
    "fps": 24,
    "frame_count": 121,
    "duration_seconds": 5.041666666666667
  },
  "turns": [
    {
      "turn": 1,
      "prompt": "A fixed camera shows a robot arm above a white table. A red cube sits on the left and a blue cube sits on the right. The robot grasps the red cube and places it inside a shallow yellow tray in the middle. The blue cube remains motionless. Continuous shot, realistic motion.",
      "seed": 42,
      "start_seconds": 0.0,
      "video": "turn-1.mp4"
    }
  ],
  "environment": {
    "packages": {
      "torch": "2.8.0",
      "diffusers": "0.35.2",
      "transformers": "4.56.2",
      "accelerate": "1.10.1",
      "Pillow": "11.3.0",
      "numpy": "2.2.6"
    },
    "python": "3.11.11",
    "gpu": "NVIDIA A100 80GB PCIe",
    "cuda": "12.8",
    "worker_source_sha256": "ad3e7cea2f30ff6454d1a63f308cb78b98774109dbdc7b8491608f1616123d16"
  },
  "input_transform": "Resize the full conditioning frame to the recorded model dimensions; no crop.",
  "sampling": "All planned seeds retained. No best-of selection. A small visual sample is not a leaderboard evaluation.",
  "prior_attempts": [
    {
      "attempt": "attempt-001",
      "status": "failed"
    },
    {
      "attempt": "attempt-002",
      "status": "completed"
    }
  ]
}
