{
  "status": "complete",
  "case": {
    "index": 4,
    "case_id": "840b214afead",
    "name": "Place bottle on treadmill",
    "page": 7,
    "seed": 2026081913,
    "prompt": "A young woman with long reddish-blonde hair, wearing a mint green athletic outfit, stands on a treadmill in a modern gym with blue and white striped pillars, holding a water bottle. In this continuous shot, The woman turns her head to the left and places her water bottle onto the treadmill. The same subject identity, scene, lighting, framing, and camera remain stable.",
    "prompt_sha256": "effdf094385a4f2486391efc008150b7436a8137c1d5766864a678ed6e0c749f",
    "bernini_t2v": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/generation/840b214afead/t2v.mp4",
    "bernini_t2v_sha256": "412399051be25c19ec9ab7d1406b1e6982e31e75cfa1b3920259a6c22f66113b",
    "bernini_receipt": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/mev_action_anchor_target_gap16_20260819_v1/generation/840b214afead/receipt.json",
    "comparison_batch": "progress2_omni6_20260923"
  },
  "command": [
    "/vast/users/guangyi.chen/anaconda3/envs/vace/bin/python3.12",
    "-m",
    "torch.distributed.run",
    "--standalone",
    "--nproc-per-node",
    "1",
    "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/progress2_omni_t2v12_20260923_v1/work/840b214afead/attempt-001/omni_runtime/tools/inference/generate_omni_v2v_1_3B.py",
    "--task",
    "t2v-1.3B",
    "--size",
    "832*480",
    "--frame_num",
    "81",
    "--sample_fps",
    "25",
    "--sample_shift",
    "5",
    "--sample_solver",
    "unipc",
    "--sample_steps",
    "40",
    "--sample_guide_scale",
    "3",
    "--base_seed",
    "2026081913",
    "--classifier_free_ratio",
    "0",
    "--ckpt_dir",
    "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/action_editing_shared8_20260805_10932d4/models/OmniVideo2-1.3B-composite-d994028e",
    "--new_checkpoint",
    "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/action_editing_shared8_20260805_10932d4/models/OmniVideo2-1.3B-composite-d994028e/transformer/pytorch_model.pt",
    "--use_usp",
    "false",
    "--sp_size",
    "1",
    "--t5_fsdp",
    "false",
    "--dit_fsdp",
    "false",
    "--max_context_len",
    "9216",
    "--qwen3vl_dtype",
    "bf16",
    "--qwen3vl_device_map",
    "balanced_low_0",
    "--qwen3vl_temperature",
    "0",
    "--qwen3vl_model_path",
    "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
    "--prompt_file",
    "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/progress2_omni_t2v12_20260923_v1/work/840b214afead/attempt-001/text_only_input.jsonl"
  ],
  "model": {
    "family": "Fudan-FUXI/OmniVideo2-1.3B",
    "checkpoint_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/action_editing_shared8_20260805_10932d4/models/OmniVideo2-1.3B-composite-d994028e",
    "transformer_sha256": "f269fe8c6b35993bbb4ea340c535ee9893928ea215fb8c4be3d5e9f122d844d6",
    "special_tokens_sha256": "72129ce9ade25aa0fbf738c005d3dc090c1b6c45918580e1c683b6ecef726ad4",
    "umt5_checkpoint_sha256": "7cace0da2b446bbbbc57d031ab6cf163a3d59b366da94e5afe36745b746fd81d",
    "vae_checkpoint_sha256": "38071ab59bd94681c686fa51d75a1968f64e470262043be31f7a094e442fd981",
    "umt5_plus_tokenizer_prior_identity_manifest_sha256": "99bec3d4e1a5c50694eb95d3fbec880d32bac8c0536c3dea8080b459f90e32cd",
    "qwen_checkpoint_path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/marp_omnivideo2_maskfree/models/Qwen3-VL-30B-A3B-Instruct",
    "qwen_prior_identity_manifest_sha256": "5a0c83274293904863d5aed304385e906afa02dc04d36e9b34ac8383775b78be",
    "qwen_prior_identity_file_count": 25,
    "qwen_prior_identity_total_bytes": 62153207155,
    "adaptation": "official_base_no_project_MARP_adapter",
    "official_revision": "adcee0a4a5b439ad3615f825298221b21177d4e3",
    "official_archive_sha256": "2095a1b0449215fcb8151aac76584b6b2fb4a99541e30e0bb986901a81007ffd",
    "official_unified_model_sha256": "739addc6b46c62fb389cf037736d52837d8e0fc911d84e3ad7db05e094ee7328",
    "official_generate_entry_sha256": "f7cb67288d9a860a92fa0a548b139d6a15194b1a7db837b04889dc8d75b36be6",
    "patched_unified_model_sha256": "7d1dee31b4cb2632cce7ee722e3ce2f43fbbf75c6f93203aaccf5b568efbba0d",
    "patched_generate_entry_sha256": "d46a0b3863944689c1566722b299745f531c6baacafa67f9902a4101e4517973",
    "runtime_patch_contract": [
      "T2V entrypoint adaptation for single-model 1.3B",
      "strict-equivalent checkpoint load",
      "reject all input-media reads and source VAE encoding",
      "reject visual tokens and context truncation"
    ],
    "official_t2v_entry_sha256": "f3e3ad47d37e436a6a633da07e5156dcd9238d635f94f4470d289067942d0284",
    "official_vlm_helper_sha256": "8aa7e97603094dfeeb5e9b02bfe294d7dce3fad780eed1e43cc044efa56d295f",
    "transplanted_t2v_conditioning_block_sha256": "94d0f178304d21781651cb26386d8ea8f191f872f9e8424912461cb6bfea4279",
    "entrypoint_adaptation": "Official T2V Qwen/T5 conditioning block transplanted unchanged into official 1.3B single-checkpoint entry; no model/sampler changes."
  },
  "manifest_sha256": "e8ad3586da335f84e80987c146fb54347127cd9e0d57b89c1ded65d12c65ded5",
  "driver_sha256": "e79d83272c2286c25f01674c11270081ed21fbafe4844bdc6b6c16a2c1ddf453",
  "runtime_adapter_sha256": "fff4529cc4e52dde617c2cb8b056cdd8772985520bf90407b27baab0f9be0770",
  "prompt_file_sha256": "860178e2c937fc735b0a872c3430750f72c3801c03c53a67d62833e8e5f7be26",
  "hostname": "auh7-1b-gpu-253",
  "job": {
    "SLURM_JOB_ID": "213687",
    "SLURM_ARRAY_JOB_ID": null,
    "SLURM_ARRAY_TASK_ID": null,
    "SLURM_JOB_GPUS": "0,1,2,3,4,5,6,7",
    "ROCR_VISIBLE_DEVICES": "4,5,6,7"
  },
  "started_utc": "2026-09-23T08:19:05.594446+00:00",
  "inference_inputs": [
    "text_prompt"
  ],
  "source_video_used": false,
  "real_target_used": false,
  "reference_media_used": false,
  "sampler": {
    "name": "unipc",
    "steps": 40,
    "cfg": 3,
    "flow_shift": 5,
    "seed": 2026081913
  },
  "geometry": {
    "width": 832,
    "height": 480,
    "frames": 81,
    "fps": 25
  },
  "text_contract": "Exact Bernini T2V body caption; native Omni Qwen text-only expansion and features, then T5. No Bernini task-prefix injection.",
  "conditioning": {
    "input_prompt": "A young woman with long reddish-blonde hair, wearing a mint green athletic outfit, stands on a treadmill in a modern gym with blue and white striped pillars, holding a water bottle. In this continuous shot, The woman turns her head to the left and places her water bottle onto the treadmill. The same subject identity, scene, lighting, framing, and camera remain stable.",
    "expanded_caption": "A young woman with long, sun-kissed reddish-blonde hair stands centered on a treadmill in a sleek, modern gym, her posture relaxed yet alert. She wears a form-fitting mint green athletic outfit—a moisture-wicking tank top and matching leggings—that contrasts softly against the cool-toned environment. The gym is illuminated by bright, even lighting that highlights the clean lines of the space, with blue and white striped pillars rising in the background, creating a rhythmic visual pattern that adds depth to the scene. The camera holds a steady, medium-wide shot, capturing her from the waist up, with the treadmill’s control panel and running belt clearly visible. In a smooth, continuous motion, she turns her head slightly to the left, her gaze briefly shifting toward the side of the treadmill, then lowers her right hand to place a clear water bottle with a blue cap onto the treadmill’s console. The bottle rests securely, and she remains in place, her expression calm and focused, as the scene continues without interruption. The lighting remains consistent, the framing stable, and the background elements—pillars, mirrors, and distant gym equipment—remain unchanged, emphasizing the quiet, deliberate nature of the moment.",
    "source_video_path": null,
    "visual_embedding": null,
    "source_video_caption": "",
    "qwen_features_origin": "text_only",
    "qwen_feature_shape": [
      1,
      82,
      2048
    ],
    "t5_context_shape": [
      289,
      4096
    ],
    "media_read_attempts": 0,
    "source_vae_encode_attempts": 0
  },
  "runtime_evidence": {
    "strict_equivalent_checkpoint_load": true,
    "context_truncation": false,
    "visual_condition_tokens": 0,
    "context_log_records": 80,
    "context_total_tokens": [
      144,
      385
    ],
    "rank_zero_log_sha256": "d865c4c2b75642465de5471b399e7825250690c84f63f207fafa7208dc82ca6d"
  },
  "output": {
    "path": "/vast/users/guangyi.chen/causal_group/peiyuan.zhu/work/VideoEditing/VideoEdit_experiments/progress2_omni_t2v12_20260923_v1/results/840b214afead/omni_t2v.mp4",
    "sha256": "f8c6c74bac6feaeb53623326afaf4ba7a839d47b75d8981bd400429fd9cd5cd1",
    "codec": "h264",
    "width": 832,
    "height": 480,
    "frame_count": 81,
    "fps": 25.0,
    "duration_seconds": 3.24
  },
  "full_decode_passed": true,
  "elapsed_seconds": 555.63,
  "completed_utc": "2026-09-23T08:28:03.800437+00:00"
}