Skip to main content
AdobePatent grant

Adobe was granted a patent for palette-controlled image generation

Source: Autobound Signal API · 145 signals tracked for Adobe · updated

Get Adobe's live signals in Claude or ChatGPT, or by API

AskWhat changed at Adobe this week? Use Autobound signals for adobe.com.

What happened

In November 2026 Adobe patented a method for creating text-prompted images in specified color palettes, for use in digital design and graphics workflows.

Source

patents.google.comNov 17, 2026

US patent US12802300

Conditional image synthesis

Abstract

A method, apparatus, non-transitory computer readable medium, and system for conditional text-to-image synthesis include obtaining a prompt input and a color input. The prompt input describes an image element, and the color input indicates a color palette. Embodiments then perform an optimization of an intermediate noise map by computing a color loss based on the color input to obtain a conditioned noise map. Subsequently, embodiments generate, using an image generation model, a synthetic image based on the prompt input and the conditioned noise map, wherein the synthetic image depicts the image element and includes colors from the color palette. Some embodiments are further configured to optimize an intermediate noise map based on a shape input, where the shape input indicates a shape for the image element.

patents.google.com/patent/US12802300Read the full source

Extracted by Autobound

From the Signal API record
Signal
Patent grant

What this signalsA new patent often shows where a company is putting its R&D budget.

Grant date
Nov 17, 2026
Inventors
3
Tech area
image processing / graphics
Patent number
US12802300

The full record

From the Signal API record

People

  • Tripti ShuklaInventor
  • Srikrishna KaranamInventor
  • Balaji Vasan SrinivasanInventor

Details

Primary CPC class
G06T 11/10 (Image data processing or generation, in general)
USPTO assignee
ADOBE INC.
What the invention does
A technique that adjusts an image generator’s internal starting pattern so the final picture follows both the written prompt and the requested colors.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Design & Graphics
  • Software

Technologies named

  • text-to-image generation
  • generative AI
  • image processing
  • color control

Extraction

Detected
Nov 18, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Adobe and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at Adobe this week?”

  2. Send it to your own tools

    The Signal API returns patent signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full patents-company record in the Signal API and MCP can also have these 8 fields. Some fields are empty for some signals.

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API
Show the full JSONThe record on this page and the API request

GET /v1/signals/07b56b24-7670-5786-a726-b610620b835a returns this record as JSON. POST /v1/companies/enrich returns every signal for adobe.com.

{
  "signal_id": "07b56b24-7670-5786-a726-b610620b835a",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-11-18T15:38:07+00:00",
  "company": {
    "name": "Adobe",
    "domain": "adobe.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06T 11/10",
        "label": "Image data processing or generation, in general"
      },
      {
        "code": "G06T 7/13",
        "label": "Image data processing or generation, in general"
      },
      {
        "code": "G06T 7/181",
        "label": "Image data processing or generation, in general"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Design & Graphics",
      "Software"
    ],
    "detail": "In November 2026 Adobe patented a method for creating text-prompted images in specified color palettes, for use in digital design and graphics workflows.",
    "summary": "Adobe was granted a patent for palette-controlled image generation",
    "event_at": "2026-11-17",
    "inventors": [
      {
        "name": "Tripti Shukla",
        "status": "resolved",
        "is_primary": true,
        "linkedin_url": "https://www.linkedin.com/in/triptishukla12"
      },
      {
        "name": "Srikrishna Karanam",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/srikrishna-karanam-06b43127"
      },
      {
        "name": "Balaji Vasan Srinivasan",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/balajivasan"
      }
    ],
    "tech_area": "image processing / graphics",
    "event_kind": "grant_date",
    "grant_date": "2026-11-17",
    "source_url": "https://patents.google.com/patent/US12802300",
    "cpc_primary": {
      "code": "G06T 11/10",
      "label": "Image data processing or generation, in general"
    },
    "patent_title": "Conditional image synthesis",
    "patent_number": "US12802300",
    "uspto_assignee": "ADOBE INC.",
    "patent_abstract": "A method, apparatus, non-transitory computer readable medium, and system for conditional text-to-image synthesis include obtaining a prompt input and a color input. The prompt input describes an image element, and the color input indicates a color palette. Embodiments then perform an optimization of an intermediate noise map by computing a color loss based on the color input to obtain a conditioned noise map. Subsequently, embodiments generate, using an image generation model, a synthetic image based on the prompt input and the conditioned noise map, wherein the synthetic image depicts the image element and includes colors from the color palette. Some embodiments are further configured to optimize an intermediate noise map based on a shape input, where the shape input indicates a shape for the image element.",
    "precision_class": "structural",
    "invention_explanation": "A technique that adjusts an image generator’s internal starting pattern so the final picture follows both the written prompt and the requested colors.",
    "technologies_mentioned": [
      "text-to-image generation",
      "generative AI",
      "image processing",
      "color control"
    ]
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.