{
  "source": "VAR-Q Tables 2–4",
  "datasets": [
    {
      "id": "var20",
      "label": "VAR-d20 · Next-scale image",
      "table": "2a",
      "page": 7,
      "setting": "600M · ImageNet 256×256 · batch 128",
      "metrics": ["FID ↓", "IS ↑", "Precision ↑", "Recall ↑", "PSNR ↑", "SSIM ↑", "LPIPS ↓"],
      "rows": [
        {
          "method": "BF16",
          "precision": "BF16",
          "values": ["4.11", "357.32", "0.8650", "0.5160", "—", "—", "—"],
          "kv": "16.60",
          "saving": null
        },
        {
          "method": "FlexGen",
          "precision": "INT4",
          "values": ["4.03", "325.39", "0.8326", "0.5230", "11.84", "0.264", "0.553"],
          "kv": "4.29",
          "saving": "74.14"
        },
        {
          "method": "KIVI",
          "precision": "INT4",
          "values": ["3.55", "341.52", "0.8458", "0.5363", "11.81", "0.256", "0.552"],
          "kv": "4.65",
          "saving": "71.97"
        },
        {
          "method": "VAR-Q",
          "precision": "INT4",
          "values": ["3.44", "342.77", "0.8502", "0.5281", "13.22", "0.308", "0.462"],
          "kv": "4.64",
          "saving": "72.06"
        },
        {
          "method": "FlexGen",
          "precision": "INT3",
          "values": ["15.33", "139.59", "0.5944", "0.6308", "10.35", "0.212", "0.650"],
          "kv": "3.46",
          "saving": "79.14"
        },
        {
          "method": "KIVI",
          "precision": "INT3",
          "values": ["6.36", "233.84", "0.7260", "0.5748", "9.88", "0.187", "0.662"],
          "kv": "3.82",
          "saving": "76.97"
        },
        {
          "method": "VAR-Q",
          "precision": "INT3",
          "values": ["3.77", "262.24", "0.7706", "0.5767", "12.24", "0.266", "0.538"],
          "kv": "3.81",
          "saving": "77.06"
        }
      ],
      "defaultMetric": 0,
      "defaultPrecision": "INT3",
      "metricGroups": [
        ["Distribution quality", 4],
        ["Fidelity to BF16", 3]
      ],
      "tableLabels": ["FID ↓", "IS ↑", "Precision ↑", "Recall ↑", "PSNR ↑", "SSIM ↑", "LPIPS ↓"]
    },
    {
      "id": "var24",
      "label": "VAR-d24 · Next-scale image",
      "table": "2a",
      "page": 7,
      "setting": "1.0B · ImageNet 256×256 · batch 128",
      "metrics": ["FID ↓", "IS ↑", "Precision ↑", "Recall ↑", "PSNR ↑", "SSIM ↑", "LPIPS ↓"],
      "rows": [
        {
          "method": "BF16",
          "precision": "BF16",
          "values": ["2.97", "357.24", "0.8444", "0.5605", "—", "—", "—"],
          "kv": "23.91",
          "saving": null
        },
        {
          "method": "FlexGen",
          "precision": "INT4",
          "values": ["2.74", "325.69", "0.8175", "0.5816", "11.78", "0.256", "0.560"],
          "kv": "6.18",
          "saving": "74.14"
        },
        {
          "method": "KIVI",
          "precision": "INT4",
          "values": ["2.56", "340.55", "0.8295", "0.5786", "11.92", "0.268", "0.545"],
          "kv": "6.70",
          "saving": "71.97"
        },
        {
          "method": "VAR-Q",
          "precision": "INT4",
          "values": ["2.52", "341.60", "0.8321", "0.5718", "13.03", "0.296", "0.479"],
          "kv": "6.68",
          "saving": "72.06"
        },
        {
          "method": "FlexGen",
          "precision": "INT3",
          "values": ["14.91", "144.09", "0.6066", "0.6424", "10.63", "0.201", "0.643"],
          "kv": "4.99",
          "saving": "79.14"
        },
        {
          "method": "KIVI",
          "precision": "INT3",
          "values": ["4.29", "239.40", "0.7271", "0.6340", "10.88", "0.226", "0.631"],
          "kv": "5.51",
          "saving": "76.97"
        },
        {
          "method": "VAR-Q",
          "precision": "INT3",
          "values": ["3.60", "258.33", "0.7477", "0.6130", "11.90", "0.252", "0.558"],
          "kv": "5.48",
          "saving": "77.06"
        }
      ],
      "defaultMetric": 0,
      "defaultPrecision": "INT3",
      "metricGroups": [
        ["Distribution quality", 4],
        ["Fidelity to BF16", 3]
      ],
      "tableLabels": ["FID ↓", "IS ↑", "Precision ↑", "Recall ↑", "PSNR ↑", "SSIM ↑", "LPIPS ↓"]
    },
    {
      "id": "var30",
      "label": "VAR-d30 · Next-scale image",
      "table": "2a",
      "page": 7,
      "setting": "2.0B · ImageNet 256×256 · batch 128",
      "metrics": ["FID ↓", "IS ↑", "Precision ↑", "Recall ↑", "PSNR ↑", "SSIM ↑", "LPIPS ↓"],
      "rows": [
        {
          "method": "BF16",
          "precision": "BF16",
          "values": ["2.07", "335.10", "0.8260", "0.5812", "—", "—", "—"],
          "kv": "37.35",
          "saving": null
        },
        {
          "method": "FlexGen",
          "precision": "INT4",
          "values": ["2.00", "307.92", "0.8061", "0.6006", "12.47", "0.277", "0.510"],
          "kv": "9.66",
          "saving": "74.14"
        },
        {
          "method": "KIVI",
          "precision": "INT4",
          "values": ["1.99", "321.46", "0.8162", "0.5974", "12.86", "0.290", "0.484"],
          "kv": "10.47",
          "saving": "71.97"
        },
        {
          "method": "VAR-Q",
          "precision": "INT4",
          "values": ["1.97", "323.67", "0.8156", "0.5961", "13.54", "0.312", "0.437"],
          "kv": "10.44",
          "saving": "72.06"
        },
        {
          "method": "FlexGen",
          "precision": "INT3",
          "values": ["9.52", "180.57", "0.6738", "0.6417", "11.33", "0.232", "0.597"],
          "kv": "7.79",
          "saving": "79.14"
        },
        {
          "method": "KIVI",
          "precision": "INT3",
          "values": ["3.26", "264.93", "0.7536", "0.6189", "11.69", "0.249", "0.573"],
          "kv": "8.60",
          "saving": "76.97"
        },
        {
          "method": "VAR-Q",
          "precision": "INT3",
          "values": ["3.05", "268.16", "0.7612", "0.6307", "12.41", "0.270", "0.517"],
          "kv": "8.57",
          "saving": "77.06"
        }
      ],
      "defaultMetric": 0,
      "defaultPrecision": "INT3",
      "metricGroups": [
        ["Distribution quality", 4],
        ["Fidelity to BF16", 3]
      ],
      "tableLabels": ["FID ↓", "IS ↑", "Precision ↑", "Recall ↑", "PSNR ↑", "SSIM ↑", "LPIPS ↓"]
    },
    {
      "id": "infinity2",
      "label": "Infinity-2B · Next-scale image",
      "table": "2b",
      "page": 7,
      "setting": "Text-to-image · batch 8",
      "metrics": [
        "GenEval Two-Object ↑",
        "GenEval Position ↑",
        "GenEval Color ↑",
        "GenEval Overall ↑",
        "DPG Entity ↑",
        "DPG Relation ↑",
        "DPG Attribute ↑",
        "DPG Global ↑",
        "DPG Other ↑",
        "DPG Overall ↑"
      ],
      "rows": [
        {
          "method": "BF16",
          "precision": "BF16",
          "values": ["80.61", "25.51", "88.03", "69.61", "86.55", "89.51", "86.62", "83.24", "90.14", "81.97"],
          "kv": "41.10",
          "saving": null
        },
        {
          "method": "VAR-Q",
          "precision": "INT8",
          "values": ["79.34", "26.26", "87.23", "69.06", "87.69", "89.39", "88.70", "86.40", "85.85", "82.21"],
          "kv": "20.65",
          "saving": "49.75"
        },
        {
          "method": "FlexGen",
          "precision": "INT4",
          "values": ["78.57", "24.75", "54.50", "67.75", "87.39", "91.56", "85.38", "82.24", "82.04", "81.01"],
          "kv": "10.60",
          "saving": "74.22"
        },
        {
          "method": "KIVI",
          "precision": "INT4",
          "values": ["80.61", "24.49", "87.23", "67.48", "88.18", "91.13", "86.51", "83.18", "80.81", "80.04"],
          "kv": "10.78",
          "saving": "73.76"
        },
        {
          "method": "VAR-Q",
          "precision": "INT4",
          "values": ["79.34", "26.01", "86.97", "69.35", "87.24", "89.60", "87.43", "86.75", "90.13", "82.02"],
          "kv": "10.38",
          "saving": "74.75"
        },
        {
          "method": "KIVI",
          "precision": "INT3",
          "values": ["77.30", "26.26", "86.70", "67.56", "87.12", "92.39", "85.66", "82.94", "79.31", "80.76"],
          "kv": "8.73",
          "saving": "78.76"
        },
        {
          "method": "VAR-Q",
          "precision": "INT3",
          "values": ["78.32", "24.24", "88.03", "68.04", "87.74", "89.92", "87.01", "85.13", "87.01", "81.18"],
          "kv": "8.32",
          "saving": "79.75"
        }
      ],
      "defaultMetric": 3,
      "defaultPrecision": "INT4",
      "metricGroups": [
        ["GenEval ↑", 4],
        ["DPG ↑", 6]
      ],
      "tableLabels": [
        "Two-Object ↑",
        "Position ↑",
        "Color ↑",
        "Overall ↑",
        "Entity ↑",
        "Relation ↑",
        "Attribute ↑",
        "Global ↑",
        "Other ↑",
        "Overall ↑"
      ]
    },
    {
      "id": "infinity8",
      "label": "Infinity-8B · Next-scale image",
      "table": "2b",
      "page": 7,
      "setting": "Text-to-image · batch 6",
      "metrics": [
        "GenEval Two-Object ↑",
        "GenEval Position ↑",
        "GenEval Color ↑",
        "GenEval Overall ↑",
        "DPG Entity ↑",
        "DPG Relation ↑",
        "DPG Attribute ↑",
        "DPG Global ↑",
        "DPG Other ↑",
        "DPG Overall ↑"
      ],
      "rows": [
        {
          "method": "BF16",
          "precision": "BF16",
          "values": ["95.41", "62.12", "90.43", "83.54", "88.27", "89.30", "91.57", "92.83", "88.61", "85.72"],
          "kv": "67.43",
          "saving": null
        },
        {
          "method": "VAR-Q",
          "precision": "INT8",
          "values": ["96.43", "62.88", "89.89", "84.00", "90.57", "92.57", "89.23", "87.12", "92.68", "85.97"],
          "kv": "33.88",
          "saving": "49.75"
        },
        {
          "method": "FlexGen",
          "precision": "INT4",
          "values": ["95.41", "60.89", "89.02", "82.45", "90.75", "92.33", "89.15", "85.04", "84.49", "84.58"],
          "kv": "17.38",
          "saving": "74.22"
        },
        {
          "method": "KIVI",
          "precision": "INT4",
          "values": ["95.66", "65.40", "91.22", "83.26", "91.13", "94.10", "88.93", "85.67", "82.04", "85.74"],
          "kv": "17.69",
          "saving": "73.76"
        },
        {
          "method": "VAR-Q",
          "precision": "INT4",
          "values": ["95.92", "63.64", "91.49", "83.67", "90.70", "91.99", "91.07", "87.47", "89.23", "85.90"],
          "kv": "17.03",
          "saving": "74.75"
        },
        {
          "method": "KIVI",
          "precision": "INT3",
          "values": ["95.66", "63.38", "91.49", "82.75", "87.74", "94.33", "88.97", "84.05", "85.71", "84.89"],
          "kv": "14.32",
          "saving": "78.76"
        },
        {
          "method": "VAR-Q",
          "precision": "INT3",
          "values": ["95.41", "63.13", "90.69", "83.28", "89.65", "88.84", "90.82", "89.16", "91.80", "85.89"],
          "kv": "13.65",
          "saving": "79.75"
        },
        {
          "method": "VAR-Q",
          "precision": "INT2",
          "values": ["85.97", "56.57", "86.70", "74.38", "87.80", "90.09", "89.31", "91.22", "88.12", "83.83"],
          "kv": "8.60",
          "saving": "87.25"
        }
      ],
      "defaultMetric": 3,
      "defaultPrecision": "INT4",
      "metricGroups": [
        ["GenEval ↑", 4],
        ["DPG ↑", 6]
      ],
      "tableLabels": [
        "Two-Object ↑",
        "Position ↑",
        "Color ↑",
        "Overall ↑",
        "Entity ↑",
        "Relation ↑",
        "Attribute ↑",
        "Global ↑",
        "Other ↑",
        "Overall ↑"
      ]
    },
    {
      "id": "star720",
      "label": "InfinityStar · Next-scale video · 720p",
      "table": "3",
      "page": 8,
      "setting": "8B · 720p · batch 3",
      "metrics": [
        "Subject Consistency ↑",
        "Background Consistency ↑",
        "Temporal Flickering ↑",
        "Motion Smoothness ↑",
        "Dynamic Degree ↑",
        "Aesthetic Quality ↑",
        "Imaging Quality ↑",
        "Total Quality ↑"
      ],
      "rows": [
        {
          "method": "BF16",
          "precision": "BF16",
          "values": ["93.69", "94.62", "97.71", "98.86", "67.50", "58.49", "66.79", "82.33"],
          "kv": "62.72",
          "saving": null
        },
        {
          "method": "FlexGen",
          "precision": "INT4",
          "values": ["93.83", "94.76", "97.83", "98.91", "63.00", "55.50", "64.80", "80.11"],
          "kv": "16.48",
          "saving": "73.72"
        },
        {
          "method": "KIVI",
          "precision": "INT4",
          "values": ["92.01", "94.61", "97.27", "98.70", "68.00", "56.12", "63.60", "81.24"],
          "kv": "16.73",
          "saving": "73.33"
        },
        {
          "method": "VAR-Q",
          "precision": "INT4",
          "values": ["92.65", "94.09", "97.37", "98.59", "74.50", "56.87", "64.35", "81.66"],
          "kv": "16.00",
          "saving": "74.49"
        },
        {
          "method": "FlexGen",
          "precision": "INT3",
          "values": ["90.12", "92.68", "97.84", "96.91", "62.00", "56.01", "60.48", "79.95"],
          "kv": "13.56",
          "saving": "78.37"
        },
        {
          "method": "KIVI",
          "precision": "INT3",
          "values": ["90.45", "90.42", "97.65", "96.79", "74.00", "50.97", "61.92", "75.46"],
          "kv": "13.81",
          "saving": "77.99"
        },
        {
          "method": "VAR-Q",
          "precision": "INT3",
          "values": ["91.41", "93.56", "97.25", "98.37", "75.00", "55.55", "61.75", "80.59"],
          "kv": "13.08",
          "saving": "79.15"
        }
      ],
      "defaultMetric": 7,
      "defaultPrecision": "INT3",
      "metricGroups": [["VBench ↑", 8]],
      "tableLabels": [
        "Subject Consistency ↑",
        "Background Consistency ↑",
        "Temporal Flickering ↑",
        "Motion Smoothness ↑",
        "Dynamic Degree ↑",
        "Aesthetic Quality ↑",
        "Imaging Quality ↑",
        "Total Quality ↑"
      ]
    },
    {
      "id": "star480",
      "label": "InfinityStar · Next-scale video · 480p",
      "table": "3",
      "page": 8,
      "setting": "8B · 480p · batch 6",
      "metrics": [
        "Subject Consistency ↑",
        "Background Consistency ↑",
        "Temporal Flickering ↑",
        "Motion Smoothness ↑",
        "Dynamic Degree ↑",
        "Aesthetic Quality ↑",
        "Imaging Quality ↑",
        "Total Quality ↑"
      ],
      "rows": [
        {
          "method": "BF16",
          "precision": "BF16",
          "values": ["93.01", "94.53", "97.25", "98.68", "66.00", "58.13", "64.01", "81.30"],
          "kv": "55.87",
          "saving": null
        },
        {
          "method": "FlexGen",
          "precision": "INT4",
          "values": ["90.59", "94.39", "95.16", "98.64", "66.50", "56.48", "62.14", "78.94"],
          "kv": "15.03",
          "saving": "73.10"
        },
        {
          "method": "KIVI",
          "precision": "INT4",
          "values": ["92.44", "94.42", "96.65", "97.79", "64.00", "56.97", "62.92", "80.46"],
          "kv": "15.25",
          "saving": "72.71"
        },
        {
          "method": "VAR-Q",
          "precision": "INT4",
          "values": ["92.75", "94.51", "97.21", "98.67", "68.50", "57.84", "63.62", "81.32"],
          "kv": "14.60",
          "saving": "73.86"
        },
        {
          "method": "FlexGen",
          "precision": "INT3",
          "values": ["91.89", "93.91", "97.24", "98.62", "64.00", "57.54", "63.69", "80.64"],
          "kv": "12.45",
          "saving": "77.71"
        },
        {
          "method": "KIVI",
          "precision": "INT3",
          "values": ["93.01", "94.46", "97.33", "98.71", "64.00", "57.79", "63.56", "78.05"],
          "kv": "12.67",
          "saving": "77.33"
        },
        {
          "method": "VAR-Q",
          "precision": "INT3",
          "values": ["92.86", "94.30", "97.26", "98.64", "65.50", "57.52", "63.37", "80.98"],
          "kv": "12.03",
          "saving": "78.47"
        }
      ],
      "defaultMetric": 7,
      "defaultPrecision": "INT3",
      "metricGroups": [["VBench ↑", 8]],
      "tableLabels": [
        "Subject Consistency ↑",
        "Background Consistency ↑",
        "Temporal Flickering ↑",
        "Motion Smoothness ↑",
        "Dynamic Degree ↑",
        "Aesthetic Quality ↑",
        "Imaging Quality ↑",
        "Total Quality ↑"
      ]
    },
    {
      "id": "self",
      "label": "Self-Forcing · Next-frame video",
      "table": "4",
      "page": 8,
      "setting": "1.3B · 5-second clips · batch 12",
      "metrics": [
        "Subject Consistency ↑",
        "Background Consistency ↑",
        "Motion Smoothness ↑",
        "Dynamic Degree ↑",
        "Aesthetic Quality ↑",
        "Total Quality ↑",
        "Claude Opus 4.7 · Visual Quality ↑ (1–5)",
        "Claude Opus 4.7 · Dynamics ↑ (1–5)",
        "Claude Opus 4.7 · Text Alignment ↑ (1–5)"
      ],
      "rows": [
        {
          "method": "BF16",
          "precision": "BF16",
          "values": ["93.57", "94.07", "98.43", "75.00", "60.07", "82.94", "3.81", "3.10", "3.62"],
          "kv": "67.49",
          "saving": null
        },
        {
          "method": "FlexGen",
          "precision": "INT6",
          "values": ["93.52", "94.11", "98.44", "76.00", "60.02", "82.98", "3.79", "3.15", "3.73"],
          "kv": "27.95",
          "saving": "58.59"
        },
        {
          "method": "KIVI",
          "precision": "INT6",
          "values": ["93.58", "94.12", "98.49", "73.00", "60.07", "82.85", "3.82", "3.14", "3.63"],
          "kv": "28.22",
          "saving": "58.18"
        },
        {
          "method": "VAR-Q",
          "precision": "INT6",
          "values": ["93.96", "94.76", "98.49", "76.50", "61.25", "83.34", "3.89", "3.17", "3.62"],
          "kv": "27.50",
          "saving": "59.25"
        },
        {
          "method": "FlexGen",
          "precision": "INT4",
          "values": ["86.39", "85.84", "95.40", "73.00", "57.39", "75.91", "3.60", "3.40", "3.75"],
          "kv": "17.40",
          "saving": "74.22"
        },
        {
          "method": "KIVI",
          "precision": "INT4",
          "values": ["90.53", "91.86", "98.29", "74.50", "57.64", "80.33", "3.54", "3.44", "3.76"],
          "kv": "17.68",
          "saving": "73.81"
        },
        {
          "method": "VAR-Q",
          "precision": "INT4",
          "values": ["91.28", "92.55", "98.35", "75.50", "57.40", "80.99", "3.55", "3.50", "3.73"],
          "kv": "16.95",
          "saving": "74.88"
        }
      ],
      "defaultMetric": 5,
      "defaultPrecision": "INT6",
      "metricGroups": [
        ["VBench ↑", 6],
        ["Claude Opus 4.7 · VLM judge ↑ (1–5)", 3]
      ],
      "tableLabels": [
        "Subject Consistency ↑",
        "Background Consistency ↑",
        "Motion Smoothness ↑",
        "Dynamic Degree ↑",
        "Aesthetic Quality ↑",
        "Total Quality ↑",
        "Visual Quality ↑",
        "Dynamics ↑",
        "Text Alignment ↑"
      ]
    },
    {
      "id": "long",
      "label": "LongLive · Next-frame video",
      "table": "4",
      "page": 8,
      "setting": "1.3B · 30-second clips · batch 20",
      "metrics": [
        "Subject Consistency ↑",
        "Background Consistency ↑",
        "Motion Smoothness ↑",
        "Dynamic Degree ↑",
        "Aesthetic Quality ↑",
        "Total Quality ↑",
        "Claude Opus 4.7 · Visual Quality ↑ (1–5)",
        "Claude Opus 4.7 · Dynamics ↑ (1–5)",
        "Claude Opus 4.7 · Text Alignment ↑ (1–5)"
      ],
      "rows": [
        {
          "method": "BF16",
          "precision": "BF16",
          "values": ["91.44", "93.83", "98.94", "44.50", "60.74", "80.92", "3.75", "3.25", "3.69"],
          "kv": "64.28",
          "saving": null
        },
        {
          "method": "FlexGen",
          "precision": "INT6",
          "values": ["91.33", "93.49", "98.95", "46.50", "60.29", "80.60", "3.78", "3.33", "3.78"],
          "kv": "26.62",
          "saving": "58.59"
        },
        {
          "method": "KIVI",
          "precision": "INT6",
          "values": ["91.14", "93.45", "98.94", "43.50", "60.36", "80.65", "3.73", "3.27", "3.70"],
          "kv": "26.88",
          "saving": "58.18"
        },
        {
          "method": "VAR-Q",
          "precision": "INT6",
          "values": ["91.26", "93.57", "98.93", "47.50", "60.17", "80.94", "3.84", "3.31", "3.71"],
          "kv": "26.19",
          "saving": "59.25"
        },
        {
          "method": "FlexGen",
          "precision": "INT4",
          "values": ["86.72", "90.19", "95.83", "45.00", "55.16", "76.59", "3.48", "3.48", "3.77"],
          "kv": "16.57",
          "saving": "74.22"
        },
        {
          "method": "KIVI",
          "precision": "INT4",
          "values": ["85.83", "92.09", "97.80", "49.50", "56.59", "78.95", "3.48", "3.55", "3.79"],
          "kv": "16.84",
          "saving": "73.81"
        },
        {
          "method": "VAR-Q",
          "precision": "INT4",
          "values": ["88.39", "91.97", "98.80", "47.50", "57.11", "79.60", "3.54", "3.57", "3.80"],
          "kv": "16.15",
          "saving": "74.88"
        }
      ],
      "defaultMetric": 5,
      "defaultPrecision": "INT6",
      "metricGroups": [
        ["VBench ↑", 6],
        ["Claude Opus 4.7 · VLM judge ↑ (1–5)", 3]
      ],
      "tableLabels": [
        "Subject Consistency ↑",
        "Background Consistency ↑",
        "Motion Smoothness ↑",
        "Dynamic Degree ↑",
        "Aesthetic Quality ↑",
        "Total Quality ↑",
        "Visual Quality ↑",
        "Dynamics ↑",
        "Text Alignment ↑"
      ]
    }
  ]
}