{
  "docId": "019dd923-5e88-73ef-bd5d-0d0f98caffe1",
  "docSlug": "5df6bd1b0447b5f6",
  "documentTitle": "2025 Air Street Capital The State of AI Report 2025",
  "authorId": "AirStreetCapital",
  "authorName": "Air Street Capital",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 51,
  "pageCount": 313,
  "prevPage": 50,
  "nextPage": 52,
  "slideType": "industry_trends",
  "function": "summarize",
  "density": "dense",
  "nDataPoints": 4,
  "notes": "Includes a radar chart comparing model performance across various attributes.",
  "elementsJson": [
    "headline_text",
    "action_title",
    "paragraph",
    "bullet_list",
    "radar_chart"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-0d0f98caffe1/51",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-0d0f98caffe1",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-0d0f98caffe1.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-0d0f98caffe1#slide-51",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "From late-2024, Chinese labs split between open-weight foundations and closed-source products.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-41ac-7180-a81f-116a6cdf2a27",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.28,
        "x": 0.68,
        "y": 0.42
      },
      "kind": "chart",
      "text": "Radar chart comparing HunyuanVideo, CogVideoX-1.5, Sora-480p, and Kling 1.6 across performance metrics.",
      "attrs": null,
      "subkind": "radar",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "6ef03af7-7c66-492a-9b87-420e3adba2ff",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.65,
        "x": 0.02,
        "y": 0.38
      },
      "kind": "list",
      "text": "Tencent's HunyuanVideo (13B) open-sourced a transformer-based diffusion model with a 3D-VAE with evaluations reporting that it outperforming Runway Gen-3 and Luma 1.6. Code/weights released.\nOpen-Sora 2.0 achieved commercial-level quality from a ~$200k training run, reporting parity with HunyuanVideo and Runway Gen-3 Alpha on human/VBench tests and narrowing the gap to OpenAI's Sora.\nKling 2.1 added 720p/1080p tiers and editor-oriented controls, while Vidu 2.0 cut price (~¥0.04/s) and latency (~10 s to render 4 s@512p).",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "22b86cd1-0393-44d0-8de0-85ec746f61f9",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Model performance",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-41ac-7180-a81f-16c0496ff164",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.95,
        "x": 0.02,
        "y": 0.21
      },
      "kind": "paragraph",
      "text": "From late-2024, Chinese labs split between open-weight foundations and closed-source products. Tencent seeded an open ecosystem with HunyuanVideo, while Kuaishou's Kling 2.1 and Shengshu's Vidu 2.0 productize on speed, realism and cost. Models tend to use Diffusion Transformers (DiT), which replace convolutional U-Nets with transformer blocks for better scaling and to model joint dependencies across frames, pixels, and tokens.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "16e6572f-ca11-43f5-a83e-54ce77011f4e",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.55,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "China's video generation matures: a strategic divergence",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "b63a7936-014d-4d91-bcb1-36e29d6cbbf7",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 189,
      "from": 12,
      "beatId": "019dd95a-0682-776c-8e35-9f380673831f",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Sections 1-2 lay out research findings and industry data with charts and case studies.",
      "position": 1,
      "confidence": 70,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 89,
      "from": 12,
      "beatId": "019dd95a-0682-776c-8e35-ac68557d958b",
      "arcName": "The Onion",
      "arcSlug": "onion",
      "beatName": "First Layer",
      "beatSlug": "onion-first-layer",
      "evidence": "Research section unpacks technical layer beneath the headlines.",
      "position": 2,
      "confidence": 45,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}