{
  "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": 31,
  "pageCount": 114,
  "prevPage": 30,
  "nextPage": 32,
  "slideType": "industry_trends",
  "function": "illustrate_case",
  "density": "dense",
  "nDataPoints": 0,
  "notes": "The slide uses visual examples to demonstrate the capabilities of different AI models.",
  "elementsJson": [
    "headline_text",
    "paragraph",
    "photo",
    "bullet_list",
    "logo_grid"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc/31",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc#slide-31",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Instead of using a diffusion model, Parti treats text-to-image generation as a simple sequence-to-sequence task, where the sequence to be predicted is a representation of the pixels of the image.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c4-7719-a216-fa24e52154e1",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.28,
        "x": 0.05,
        "y": 0.38
      },
      "kind": "image",
      "text": "DALL-E 2 examples",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "271074c2-c818-4a75-b4df-923f2f40f37b",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.28,
        "x": 0.36,
        "y": 0.38
      },
      "kind": "image",
      "text": "Imagen examples",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "989858e2-7f21-4719-8d6e-b3f9a9e1bc2a",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.28,
        "x": 0.67,
        "y": 0.38
      },
      "kind": "image",
      "text": "Parti examples",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "e9dbb766-c80a-4172-a838-7b73a27f35ae",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.95,
        "x": 0.03,
        "y": 0.66
      },
      "kind": "list",
      "text": "Instead of using a diffusion model, Parti treats text-to-image generation as a simple sequence-to-sequence task, where the sequence to be predicted is a representation of the pixels of the image. Notably, as the number of parameters and training data in Parti are scaled, the model acquires new abilities like spelling.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "281be600-3144-495c-a59f-0f6822ef5549",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.08,
        "w": 0.95,
        "x": 0.03,
        "y": 0.82
      },
      "kind": "list",
      "text": "Other impressive text-to-image models include GLIDE (OpenAI) and Make-a-Scene (Meta — can use both text and sketches), which predate DALL-E 2, and CogView2 (Tsinghua, BAAI — both English and Chinese).",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "7ec3e090-c011-43b9-9b9a-9e27869ae1ca",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.12,
        "w": 0.95,
        "x": 0.03,
        "y": 0.21
      },
      "kind": "paragraph",
      "text": "The second iteration of OpenAI's DALL-E, released in April 2022, came with a significant jump in the quality of generated images. Soon after, another at least equally impressive diffusion-based model came from Google (Imagen). Meanwhile, Google's Parti took a different, autoregressive, route.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "16d2f333-5236-404f-bd50-97ede73733f1",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.7,
        "x": 0.03,
        "y": 0.14
      },
      "kind": "title",
      "text": "DALL-E 2, Imagen and Parti...the battle for text-to-image generation rages",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "abf66681-f9f5-4b54-a9d5-15314c91fec3",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "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
}