349 lines
16 KiB
JSON
349 lines
16 KiB
JSON
{
|
|
"name": "t2va-dialogue-864x480-141f-base12-sdpa-seed440420",
|
|
"measured_at": "2026-08-20",
|
|
"measurement": "Warm resident direct-runtime request including conditioning, sampling, video/audio decode, encoding, and mux",
|
|
"hardware": "NVIDIA GB10",
|
|
"runtime_image": "sha256:d842225c9c5036647ee5cab1fae2e093357cc8041bd8617e33a82c81d0bcc874",
|
|
"torch": "2.9.1+cu130",
|
|
"model": "minimax_h3_fl2va_pruned_nvfp4.safetensors",
|
|
"task": "t2va",
|
|
"resolution": [864, 480],
|
|
"frames": 141,
|
|
"fps": 24,
|
|
"duration_seconds": 5.875,
|
|
"steps": 12,
|
|
"scheduler": "beta",
|
|
"sampler": "res_multistep",
|
|
"seed": 440420,
|
|
"attention": "sdpa",
|
|
"turbo": null,
|
|
"upscale": null,
|
|
"mux_audio": true,
|
|
"keep_intermediates": false,
|
|
"vae_dtype": "float16",
|
|
"vae_tile_size": 256,
|
|
"mlp_chunks": 1,
|
|
"prompt": "integrated_multimodal_description: [Shot 1] Live-action, cinematic, a static medium two-shot frames exactly two adults seated across from each other at a small table in a quiet, otherwise empty meeting room. A composed adult man sits on the left and a composed adult woman sits on the right. Both maintain neutral, attentive expressions. The man with a low, clear baritone voice and measured speaking pace (S1) looks toward the woman and says in a calm, matter-of-fact delivery: <d>[English] The north entrance closes at six.</d> During S1's line, only his lips and jaw move; the woman's lips remain completely closed. Immediately after his final word, his lips meet and his jaw ceases speaking motion. After a brief silent pause, the woman with a clear alto voice and measured speaking pace (S2) looks toward the man and replies in a calm, matter-of-fact delivery: <d>[English] Then we should leave by five thirty.</d> During S2's line, only her lips and jaw move; the man's lips remain completely closed. Immediately after her final word, her lips meet and her jaw ceases speaking motion. Both remain silent with neutral, closed-mouth expressions through the final frame. There is no overlapping speech. The camera remains completely static with no cuts.\n\noverall_soundscape: Quiet, dry indoor room tone with a faint ventilation hum. Only S1 and S2 are audible, one at a time. No laughter, chuckling, giggling, smiling vocalization, sighing, gasping, audible breathing, filler sounds, audience reaction, narration, or other voices.\n\nnon_diegetic_music: N/A",
|
|
"timings_seconds": {
|
|
"latents_initialized": 0.018280818010680377,
|
|
"text_conditioned": 3.531974215002265,
|
|
"sampled": 125.30079188900709,
|
|
"vae_decoded": 23.84665890400356,
|
|
"pixels_cpu": 0.06607734999852255,
|
|
"raw_write": 2.75871228199685,
|
|
"video_encode": 0.39305945999512915,
|
|
"audio_decoded": 0.3400787889986532,
|
|
"audio_raw_write": 0.0008342489891219884,
|
|
"audio_encode": 0.034553833000245504,
|
|
"mux": 0.19705491400964092,
|
|
"request": 156.48807670301176,
|
|
"wall": 156.56338787100685
|
|
},
|
|
"throughput": {
|
|
"sampling_frames_per_second": 1.1252921699401506,
|
|
"wall_frames_per_second": 0.9005936950992043,
|
|
"sampling_realtime_factor": 21.327794364086314,
|
|
"wall_realtime_factor": 26.649087297192655
|
|
},
|
|
"cache": {
|
|
"mode": null,
|
|
"threshold": 0.0,
|
|
"skipped_steps": 0,
|
|
"rates": []
|
|
},
|
|
"output": {
|
|
"linux_path": "/home/daniel/StoryStudioAssets/H3-output/h3-baselines/dialogue-two-character-864x480-141f-base12-sdpa-seed440420.mp4",
|
|
"unc_path": "\\\\192.168.1.162\\StoryStudioAssets\\H3-output\\h3-baselines\\dialogue-two-character-864x480-141f-base12-sdpa-seed440420.mp4",
|
|
"sha256": "2eb61334978b42bcec00ec68449f3f39139d9e24ef5ba70ef2240dc8bf7116e0",
|
|
"size_bytes": 429062,
|
|
"container_bit_rate": 584254,
|
|
"duration_seconds": 5.875,
|
|
"video": {
|
|
"codec": "h264",
|
|
"profile": "High",
|
|
"pixel_format": "yuv420p",
|
|
"width": 864,
|
|
"height": 480,
|
|
"fps": 24,
|
|
"frames": 141,
|
|
"bit_rate": 439001
|
|
},
|
|
"audio": {
|
|
"codec": "aac",
|
|
"profile": "LC",
|
|
"sample_rate": 32000,
|
|
"channels": 2,
|
|
"channel_layout": "stereo",
|
|
"bit_rate": 136335,
|
|
"mean_volume_db": -25.8,
|
|
"max_volume_db": -4.3,
|
|
"integrated_loudness_lufs": -21.18,
|
|
"true_peak_dbtp": -4.34,
|
|
"loudness_range_lu": 4.10,
|
|
"loudness_threshold_lufs": -33.94
|
|
}
|
|
},
|
|
"attention_backend_matrix": {
|
|
"reference_backend": "sdpa",
|
|
"comparison_note": "PSNR measures encoded output drift from SDPA, not subjective quality. Audio is effectively identical across all backends at greater than 170 dB decoded-PCM PSNR.",
|
|
"runs": {
|
|
"sdpa": {
|
|
"sampled_seconds": 125.30079188900709,
|
|
"request_seconds": 156.48807670301176,
|
|
"wall_seconds": 156.56338787100685,
|
|
"sampling_speedup_percent_vs_sdpa": 0.0,
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-sdpa-seed440420.mp4",
|
|
"sha256": "2eb61334978b42bcec00ec68449f3f39139d9e24ef5ba70ef2240dc8bf7116e0",
|
|
"size_bytes": 429062
|
|
},
|
|
"sage2": {
|
|
"sampled_seconds": 101.26120180900034,
|
|
"request_seconds": 132.59474182801205,
|
|
"wall_seconds": 132.66185540499282,
|
|
"sampling_speedup_percent_vs_sdpa": 19.185505,
|
|
"video_psnr_average_db_vs_sdpa": 22.4225,
|
|
"audio_psnr_db_vs_sdpa": [170.933, 170.934],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-sage2-seed440420.mp4",
|
|
"sha256": "c3e0691586c4101987f240c35a79637965af75088731108037cd084be945ba9d",
|
|
"size_bytes": 433450
|
|
},
|
|
"cudnn_sdpa": {
|
|
"sampled_seconds": 125.72722270998929,
|
|
"request_seconds": 157.14237468996726,
|
|
"wall_seconds": 157.2081264879962,
|
|
"sampling_speedup_percent_vs_sdpa": -0.340326,
|
|
"video_psnr_average_db_vs_sdpa": 22.093143,
|
|
"audio_psnr_db_vs_sdpa": [171.038, 171.01],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-cudnn_sdpa-seed440420.mp4",
|
|
"sha256": "cd17833c12a99cd71d1c0a9137a1dd9feba03943980d6eb8fff296cd9f9529a6",
|
|
"size_bytes": 429636
|
|
},
|
|
"ck_int8": {
|
|
"sampled_seconds": 104.05008868798905,
|
|
"request_seconds": 135.57199566195777,
|
|
"wall_seconds": 135.62453711099806,
|
|
"sampling_speedup_percent_vs_sdpa": 16.959752,
|
|
"video_psnr_average_db_vs_sdpa": 22.989999,
|
|
"audio_psnr_db_vs_sdpa": [170.981, 170.956],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-ck_int8-seed440420.mp4",
|
|
"sha256": "a54f9f3f2ba351d31b0b807646aea2740aae7c13c03d4eb7d44182aab3cf5618",
|
|
"size_bytes": 423190
|
|
},
|
|
"sage3": {
|
|
"sampled_seconds": 109.8837421490025,
|
|
"request_seconds": 142.34848491402227,
|
|
"wall_seconds": 142.41395058500348,
|
|
"sampling_speedup_percent_vs_sdpa": 12.304032,
|
|
"video_psnr_average_db_vs_sdpa": 19.63725,
|
|
"audio_psnr_db_vs_sdpa": [172.214, 172.06],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-sage3-seed440420.mp4",
|
|
"sha256": "3763ca4b79399037d997d5a37c795fdaf233aca88fdb90e122bf25450c75dddd",
|
|
"size_bytes": 596651
|
|
},
|
|
"sage3_mean": {
|
|
"sampled_seconds": 109.88214365398744,
|
|
"request_seconds": 141.45796999098093,
|
|
"wall_seconds": 141.51303354099218,
|
|
"sampling_speedup_percent_vs_sdpa": 12.305308,
|
|
"video_psnr_average_db_vs_sdpa": 19.63725,
|
|
"audio_psnr_db_vs_sdpa": [172.214, 172.06],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-sage3_mean-seed440420.mp4",
|
|
"sha256": "3763ca4b79399037d997d5a37c795fdaf233aca88fdb90e122bf25450c75dddd",
|
|
"size_bytes": 596651,
|
|
"identical_output_to": "sage3"
|
|
},
|
|
"kj_sage_cuda": {
|
|
"sampled_seconds": 113.68463072601298,
|
|
"request_seconds": 145.39383504101716,
|
|
"wall_seconds": 145.45757150900317,
|
|
"sampling_speedup_percent_vs_sdpa": 9.270621,
|
|
"video_psnr_average_db_vs_sdpa": 22.83642,
|
|
"audio_psnr_db_vs_sdpa": [171.042, 171.025],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-kj_sage_cuda-seed440420.mp4",
|
|
"sha256": "d85aaca677d2c678604b0aa2aba9bbf4921934bfc2970c20d0498b1762373ab5",
|
|
"size_bytes": 427568
|
|
},
|
|
"kj_sage_triton": {
|
|
"sampled_seconds": 118.28390433100867,
|
|
"request_seconds": 150.37281119299587,
|
|
"wall_seconds": 150.43365036998875,
|
|
"sampling_speedup_percent_vs_sdpa": 5.600034,
|
|
"video_psnr_average_db_vs_sdpa": 22.086796,
|
|
"audio_psnr_db_vs_sdpa": [170.149, 170.084],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-kj_sage_triton-seed440420.mp4",
|
|
"sha256": "9fe63aafa51aae8ecc0940ba75fbc13a978a50091fd8f0c336c2bb04e3658a54",
|
|
"size_bytes": 430038
|
|
},
|
|
"kj_sage_fp8": {
|
|
"sampled_seconds": 102.6086639950081,
|
|
"request_seconds": 134.1615118059999,
|
|
"wall_seconds": 134.2236167689989,
|
|
"sampling_speedup_percent_vs_sdpa": 18.110123,
|
|
"video_psnr_average_db_vs_sdpa": 22.814833,
|
|
"audio_psnr_db_vs_sdpa": [170.719, 170.692],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-kj_sage_fp8-seed440420.mp4",
|
|
"sha256": "8c5bc2a8bf7e496c2108194479fe60e67883dea0ab50e95f3ab4bac916274816",
|
|
"size_bytes": 420189
|
|
},
|
|
"kj_sage_fp8pp": {
|
|
"sampled_seconds": 103.24360375599645,
|
|
"request_seconds": 134.77945204998832,
|
|
"wall_seconds": 134.84802630099875,
|
|
"sampling_speedup_percent_vs_sdpa": 17.603391,
|
|
"video_psnr_average_db_vs_sdpa": 22.296461,
|
|
"audio_psnr_db_vs_sdpa": [170.615, 170.559],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-kj_sage_fp8pp-seed440420.mp4",
|
|
"sha256": "71643c7163e5dc16d64ac0c5d567bdd846f7944471eb0a97fd54f9a1990c24e9",
|
|
"size_bytes": 433672
|
|
},
|
|
"kj_head_sliced": {
|
|
"sampled_seconds": 103.97128305501246,
|
|
"request_seconds": 135.67128342803335,
|
|
"wall_seconds": 135.71258915099315,
|
|
"sampling_speedup_percent_vs_sdpa": 17.022645,
|
|
"video_psnr_average_db_vs_sdpa": 21.679726,
|
|
"audio_psnr_db_vs_sdpa": [171.235, 171.237],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-kj_head_sliced-seed440420.mp4",
|
|
"sha256": "48ee4da6c0a91f18714973ca23e26f1844b302024c8111946772cbc9a4a4dd83",
|
|
"size_bytes": 421728
|
|
},
|
|
"sol_attn": {
|
|
"sampled_seconds": 96.45773334198748,
|
|
"request_seconds": 128.10418028896675,
|
|
"wall_seconds": 128.17140150099294,
|
|
"sampling_speedup_percent_vs_sdpa": 23.019055,
|
|
"video_psnr_average_db_vs_sdpa": 16.653003,
|
|
"audio_psnr_db_vs_sdpa": [171.239, 171.268],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-sol_attn-seed440420.mp4",
|
|
"sha256": "8b999630210692301549d11d20d9319a6af5873a60d4cd735035e2ed79c469d6",
|
|
"size_bytes": 570667,
|
|
"note": "Experimental sparse Triton dispatch; eligible calls use sol_attn and shorter calls fall back."
|
|
},
|
|
"flash4": {
|
|
"sampled_seconds": 128.5334454880067,
|
|
"request_seconds": 160.91555801399227,
|
|
"wall_seconds": 160.96679471699463,
|
|
"sampling_speedup_percent_vs_sdpa": -2.579915,
|
|
"video_psnr_average_db_vs_sdpa": 21.238297,
|
|
"audio_psnr_db_vs_sdpa": [170.768, 170.628],
|
|
"output_file": "dialogue-two-character-864x480-141f-base12-flash4-seed440420.mp4",
|
|
"sha256": "cfb8a046cb79f8448988e7392ca748c0a08a2a034a43f6ab55a9058faa1a72ef",
|
|
"size_bytes": 449687
|
|
}
|
|
}
|
|
},
|
|
"turbo_sage2_matrix": {
|
|
"reference": "Base 12-step Sage2 from attention_backend_matrix",
|
|
"runs": {
|
|
"4step": {
|
|
"adapter": "Official FL2VA Turbo 4-step v1.1 768p",
|
|
"steps": 4,
|
|
"attention": "sage2",
|
|
"sampled_seconds": 51.661242722009774,
|
|
"request_seconds": 83.01122188399313,
|
|
"wall_seconds": 83.06598260099418,
|
|
"sampling_speedup_percent_vs_base_sage2": 48.982195,
|
|
"wall_speedup_percent_vs_base_sage2": 37.38518,
|
|
"output_file": "dialogue-two-character-864x480-141f-turbo4step-sage2-seed440420.mp4",
|
|
"sha256": "b02c29a8732d88c7dcf8e85462afcbe3aa83328541ce1647995e7d0d4188744a",
|
|
"size_bytes": 455325,
|
|
"container_bit_rate": 620017,
|
|
"audio": {
|
|
"integrated_loudness_lufs": -31.78,
|
|
"true_peak_dbtp": -14.55,
|
|
"first_0_25_seconds_peak_dbfs": -39.394894,
|
|
"first_0_25_seconds_rms_dbfs": -57.733654,
|
|
"first_sample_dbfs": [-54.110104, -50.553467]
|
|
}
|
|
},
|
|
"8step": {
|
|
"adapter": "Official FL2VA Turbo 8-step v1.0",
|
|
"steps": 8,
|
|
"attention": "sage2",
|
|
"sampled_seconds": 102.70967868898879,
|
|
"request_seconds": 134.31820170898573,
|
|
"wall_seconds": 134.36813215899747,
|
|
"sampling_speedup_percent_vs_base_sage2": -1.430436,
|
|
"wall_speedup_percent_vs_base_sage2": -1.286185,
|
|
"output_file": "dialogue-two-character-864x480-141f-turbo8step-sage2-seed440420.mp4",
|
|
"sha256": "21f450848c2ded8c02054cc241c8080d55a17979022eadfd892f3ce5205833e6",
|
|
"size_bytes": 585250,
|
|
"container_bit_rate": 796936,
|
|
"audio": {
|
|
"integrated_loudness_lufs": -24.39,
|
|
"true_peak_dbtp": -7.18,
|
|
"first_0_25_seconds_peak_dbfs": -21.305752,
|
|
"first_0_25_seconds_rms_dbfs": -41.479687,
|
|
"first_sample_dbfs": [-35.859436, -39.793118]
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"comfy_sdpa_comparison": {
|
|
"comfyui_version": "0.31.0",
|
|
"attention": "PyTorch attention without --use-sage-attention",
|
|
"prompt_id": "29c45a77-efdf-4cc8-8ae9-9b8a40823b41",
|
|
"execution_seconds": 152.767,
|
|
"wall_seconds": 153.03360149999207,
|
|
"wall_difference_from_direct_percent": -2.25454138353405,
|
|
"output": {
|
|
"linux_path": "/home/daniel/StoryStudioAssets/H3-output/h3-baselines/comfy-sdpa-dialogue-two-character-864x480-141f-base12-seed440420_00001_.mp4",
|
|
"unc_path": "\\\\192.168.1.162\\StoryStudioAssets\\H3-output\\h3-baselines\\comfy-sdpa-dialogue-two-character-864x480-141f-base12-seed440420_00001_.mp4",
|
|
"sha256": "f4510d6b8ac06b8f2cb22172454c6977a214e061dcc5539ace68e1cb70abc2ee",
|
|
"size_bytes": 443723,
|
|
"container_bit_rate": 604218,
|
|
"duration_seconds": 5.875,
|
|
"video": {
|
|
"codec": "h264",
|
|
"profile": "High",
|
|
"pixel_format": "yuv420p",
|
|
"width": 864,
|
|
"height": 480,
|
|
"fps": 24,
|
|
"frames": 141,
|
|
"bit_rate": 457452
|
|
},
|
|
"audio": {
|
|
"codec": "aac",
|
|
"profile": "LC",
|
|
"sample_rate": 32000,
|
|
"channels": 2,
|
|
"channel_layout": "stereo",
|
|
"bit_rate": 133407,
|
|
"mean_volume_db": -25.7,
|
|
"max_volume_db": -4.3,
|
|
"integrated_loudness_lufs": -21.12,
|
|
"true_peak_dbtp": -4.25,
|
|
"loudness_range_lu": 4.10,
|
|
"loudness_threshold_lufs": -33.88
|
|
}
|
|
},
|
|
"first_0_25_seconds": {
|
|
"direct": {
|
|
"peak_level_db": -19.429245,
|
|
"rms_level_db": -33.601728,
|
|
"max_sample_difference": 0.022571,
|
|
"peak_count": 2,
|
|
"nan_count": 0,
|
|
"inf_count": 0
|
|
},
|
|
"comfy": {
|
|
"peak_level_db": -19.261140,
|
|
"rms_level_db": -33.545443,
|
|
"max_sample_difference": 0.023026,
|
|
"peak_count": 2,
|
|
"nan_count": 0,
|
|
"inf_count": 0
|
|
},
|
|
"decoded_pcm_psnr_db": {
|
|
"channel_1": 162.496,
|
|
"channel_2": 162.783
|
|
},
|
|
"conclusion": "No amplitude clipping; direct and Comfy decoded waveforms are effectively identical. Any shared audible startup artifact originates before runtime-specific audio decode and mux."
|
|
},
|
|
"full_decoded_pcm_psnr_db": {
|
|
"channel_1": 166.581,
|
|
"channel_2": 165.385
|
|
}
|
|
}
|
|
}
|