{
  "docId": "019dd923-5e88-73ef-bd5d-01cf0d8a8fbc",
  "docSlug": "cc8183ec02431b7a",
  "documentTitle": "2022 Air Street Capital The State of AI Report 2022",
  "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": 33,
  "pageCount": 114,
  "prevPage": 32,
  "nextPage": 34,
  "slideType": "industry_trends",
  "function": "establish_context",
  "density": "dense",
  "nDataPoints": 0,
  "notes": "Slide from State of AI 2022 report.",
  "elementsJson": [
    "headline_text",
    "paragraph",
    "screenshot",
    "bullet_list",
    "logo_grid"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc/33",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc#slide-33",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Research on diffusion-based text-to-video generation was kicked-off around April 2022, with work from Google and the University of British Columbia.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c4-7719-a216-4a29719103e5",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.32,
        "x": 0.36,
        "y": 0.45
      },
      "kind": "image",
      "text": "Imagen Video examples",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "32c54287-6a53-4461-b7d0-3f632be81454",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.32,
        "x": 0.03,
        "y": 0.45
      },
      "kind": "image",
      "text": "Make-a-Video examples",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "40ad6290-464d-41bd-ab3f-fdd6ec737579",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.28,
        "x": 0.69,
        "y": 0.45
      },
      "kind": "image",
      "text": "Phenaki examples",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "f3e465a2-e01f-47c6-8efb-684d1ce2ab0f",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.12,
        "w": 0.95,
        "x": 0.03,
        "y": 0.82
      },
      "kind": "list",
      "text": "In an eerily similar fashion to text-to-image generation, Google then published (less than a week later) almost simultaneously two models: one diffusion-model based, Imagen, and another non diffusion-model based, Phenaki. The latter can dynamically adapt the video via additional prompts.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "7a33675c-6d86-4bef-9abc-b41b2da02e17",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.08,
        "w": 0.95,
        "x": 0.03,
        "y": 0.73
      },
      "kind": "list",
      "text": "Meta made the first splash from Big Tech in text-to-video generation by releasing Make-a-Video, a diffusion model for video generation.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "a3242600-25a8-4f9d-a0be-ccc8bc35323a",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.12,
        "w": 0.95,
        "x": 0.03,
        "y": 0.2
      },
      "kind": "paragraph",
      "text": "Research on diffusion-based text-to-video generation was kicked-off around April 2022, with work from Google and the University of British Columbia. But in late September, new research from Meta and Google came with a jump in quality, announcing a sooner-than-expected DALL-E moment for text-to-video generation.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "466fe924-de4e-4283-8a0f-f8ecb27d22c4",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.45,
        "x": 0.03,
        "y": 0.13
      },
      "kind": "title",
      "text": "The text-to-video generation race has started",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "c5951e77-f953-4e6b-b0fe-790b161b16d3",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "AIDA Model",
      "slug": "aida-model",
      "agent": "Storyteller",
      "layer": "slide",
      "matchId": "4d65c208-c012-4fdb-befc-aa8a790d82ef",
      "evidence": "The slide starts with a title and a callout, grabbing the audience's attention (A), and then provides more information (I) about the text-to-video generation race.",
      "confidence": 0.7
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 80,
      "from": 5,
      "beatId": "019dd95a-0682-776c-8e35-2557e3799e96",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Definitions, exec summary, Research and Industry sections inventory the state of AI.",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 93,
      "from": 11,
      "beatId": "019dd95a-0682-776c-8e35-35abf646aa8b",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Research, Industry, Politics sections accumulate signals.",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 33,
      "from": 30,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3d-a4c263216829",
      "evidence": "Diffusion takeover, DALL-E 2/Imagen/Parti race, Stability/Midjourney emergence, text-to-video kickoff.",
      "position": 4,
      "objective": "Document the diffusion / text-to-image explosion across labs",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 82,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}