Skip to main content
BaiduPatent grant

Baidu was granted a patent for text-guided image style transfer.

Source: Autobound Signal API · 87 signals tracked for Baidu · updated

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

AskWhat changed at Baidu this week? Use Autobound signals for baidu.com.

What happened

In October 2026 Baidu patented a diffusion-based technique for creating or editing images from written descriptions and reference pictures, useful in graphics and digital content production.

Source

patents.google.comOct 27, 2026

US patent US12776122

Image style transfer

Abstract

A method is provided that includes: obtaining a reference image and a description text; extracting a text feature of the description text; and performing the following operations based on a pre-trained diffusion model to generate a target image: in each time step of the diffusion model: calculating a first cross-attention feature of a first image feature and the text feature; obtaining a second cross-attention feature of a second image feature of the reference image and the text feature; editing the first cross-attention feature based on the second cross-attention feature to obtain a third cross-attention feature; and generating a result image feature of the time step based on the third cross-attention feature and the text feature; and decoding a result image feature of a last time step to generate the target image.

patents.google.com/patent/US12776122Read 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
Oct 27, 2026
Inventors
4
Tech area
image processing / graphics
Patent number
US12776122

The full record

From the Signal API record

People

  • Haoran WangInventor
  • Zeke XieInventor
  • Yunfeng CaiInventor
  • Mingming SunInventor

Details

Primary CPC class
G06T 11/60 (Image data processing or generation, in general)
USPTO assignee
BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.
What the invention does
A method that repeatedly compares text instructions with both a reference image and a developing image so it can generate a new picture in the requested style.

Topics and mentions

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Enhanced Content
  • Design & Graphics

Technologies named

  • image generation
  • diffusion models
  • cross-attention
  • style transfer

Extraction

Detected
Oct 30, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Baidu 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 Baidu 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/17ec646f-e129-5e76-86e6-bc4f1a832450 returns this record as JSON. POST /v1/companies/enrich returns every signal for baidu.com.

{
  "signal_id": "17ec646f-e129-5e76-86e6-bc4f1a832450",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-10-30T00:40:20+00:00",
  "company": {
    "name": "Baidu",
    "domain": "baidu.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06T 11/60",
        "label": "Image data processing or generation, in general"
      },
      {
        "code": "G06T 9/00",
        "label": "Image data processing or generation, in general"
      },
      {
        "code": "G06V 10/44",
        "label": "Image or video recognition or understanding"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Enhanced Content",
      "Design & Graphics"
    ],
    "detail": "In October 2026 Baidu patented a diffusion-based technique for creating or editing images from written descriptions and reference pictures, useful in graphics and digital content production.",
    "summary": "Baidu was granted a patent for text-guided image style transfer.",
    "event_at": "2026-10-27",
    "inventors": [
      {
        "name": "Haoran Wang",
        "status": "unresolved",
        "is_primary": true
      },
      {
        "name": "Zeke Xie",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Yunfeng Cai",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Mingming Sun",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/mingming-sun-83957025"
      }
    ],
    "tech_area": "image processing / graphics",
    "event_kind": "grant_date",
    "grant_date": "2026-10-27",
    "source_url": "https://patents.google.com/patent/US12776122",
    "cpc_primary": {
      "code": "G06T 11/60",
      "label": "Image data processing or generation, in general"
    },
    "patent_title": "Image style transfer",
    "patent_number": "US12776122",
    "uspto_assignee": "BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.",
    "patent_abstract": "A method is provided that includes: obtaining a reference image and a description text; extracting a text feature of the description text; and performing the following operations based on a pre-trained diffusion model to generate a target image: in each time step of the diffusion model: calculating a first cross-attention feature of a first image feature and the text feature; obtaining a second cross-attention feature of a second image feature of the reference image and the text feature; editing the first cross-attention feature based on the second cross-attention feature to obtain a third cross-attention feature; and generating a result image feature of the time step based on the third cross-attention feature and the text feature; and decoding a result image feature of a last time step to generate the target image.",
    "precision_class": "structural",
    "invention_explanation": "A method that repeatedly compares text instructions with both a reference image and a developing image so it can generate a new picture in the requested style.",
    "technologies_mentioned": [
      "image generation",
      "diffusion models",
      "cross-attention",
      "style transfer"
    ]
  }
}

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.