Model Training Method, Image Editing Method, Apparatus, Device, Medium, and Product
Summary
The USPTO published patent application US20260093978A1 by inventors Gu, Zhu, Chen, and Wen, disclosing methods for training image editing models using original images, editing descriptions, edited images, and multi-item evaluation information. The application covers processing these inputs to generate image editing results and updating the model based on differences between results and edited images.
What changed
This patent application discloses a model training method and image editing method. The process involves acquiring an original image, corresponding editing description text, an edited image, and evaluation information describing the edited image state across at least one evaluation item. The image editing model processes the original image, editing description text, and evaluation information to generate an editing result, which is then compared against the edited image to update the model. CPC classifications include G06N 3/08, G06N 3/04, and G06T 11/60.
This publication is informational and does not impose regulatory obligations. Technology companies developing AI image editing systems and researchers working on AI model training methods may wish to review the application for prior art considerations or potential licensing needs. Patent applications remain pending until formally examined and granted.
Archived snapshot
Apr 2, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
MODEL TRAINING METHOD, IMAGE EDITING METHOD, APPARATUS, DEVICE, MEDIUM, AND PRODUCT
Application US20260093978A1 Kind: A1 Apr 02, 2026
Inventors
Xin GU, Sijie ZHU, Fan CHEN, Longyin WEN
Abstract
The present application discloses a model training method, an image editing method, an apparatus, a device, a medium, and a product. The method includes: first acquiring an original image, an editing description text corresponding to the original image, an edited image corresponding to the original image with respect to the editing description text, and evaluation information of the edited image, enabling the evaluation information to describe the state of the edited image in at least one evaluation item. Then the original image, the editing description text and the evaluation information by using an image editing model are processed to obtain an image editing result corresponding to the original image. According to the difference between the image editing result and the edited image, the image editing model is updated.
CPC Classifications
G06N 3/08 G06N 3/04 G06T 11/60
Filing Date
2025-08-29
Application No.
19314144
Related changes
Get daily alerts for USPTO Patent Applications - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - AI & Computing (G06N) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.