Image generation method, device and system and storage medium

The invention provides an image generation method, device and system and a storage medium, and belongs to the technical field of image generation, and the method comprises the steps: carrying out the mapping processing of a to-be-processed image, and obtaining an original potential representation ve...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CAI XIAODONG, HUANG YONGSEN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator CAI XIAODONG
HUANG YONGSEN
description The invention provides an image generation method, device and system and a storage medium, and belongs to the technical field of image generation, and the method comprises the steps: carrying out the mapping processing of a to-be-processed image, and obtaining an original potential representation vector; performing vectorization analysis on the original cue word text to obtain an original text vector group; training the training model through the original prompt word text, the original potential representation vector and the original text vector group to obtain an image generation model; and predicting the prompt word text to be generated through the image generation model to obtain an image generation result. According to the method, accurate capturing and accurate mapping of key attributes in text description are achieved, the attribute corresponding relation between the generated image and the text is improved, the accuracy of image generation is improved, and the method has important practical application
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118470374A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118470374A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118470374A3</originalsourceid><addsrcrecordid>eNrjZLD1zE1MT1VIT81LLUosyczPU8hNLcnIT9FRSEkty0xOVUjMS1EoriwuSc2FMEvyi0AaclNTMktzeRhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYjLQ3JJ4Zz9DQwsTcwNjcxNHY2LUAADzmy_X</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Image generation method, device and system and storage medium</title><source>esp@cenet</source><creator>CAI XIAODONG ; HUANG YONGSEN</creator><creatorcontrib>CAI XIAODONG ; HUANG YONGSEN</creatorcontrib><description>The invention provides an image generation method, device and system and a storage medium, and belongs to the technical field of image generation, and the method comprises the steps: carrying out the mapping processing of a to-be-processed image, and obtaining an original potential representation vector; performing vectorization analysis on the original cue word text to obtain an original text vector group; training the training model through the original prompt word text, the original potential representation vector and the original text vector group to obtain an image generation model; and predicting the prompt word text to be generated through the image generation model to obtain an image generation result. According to the method, accurate capturing and accurate mapping of key attributes in text description are achieved, the attribute corresponding relation between the generated image and the text is improved, the accuracy of image generation is improved, and the method has important practical application</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240809&amp;DB=EPODOC&amp;CC=CN&amp;NR=118470374A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,778,883,25551,76302</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240809&amp;DB=EPODOC&amp;CC=CN&amp;NR=118470374A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CAI XIAODONG</creatorcontrib><creatorcontrib>HUANG YONGSEN</creatorcontrib><title>Image generation method, device and system and storage medium</title><description>The invention provides an image generation method, device and system and a storage medium, and belongs to the technical field of image generation, and the method comprises the steps: carrying out the mapping processing of a to-be-processed image, and obtaining an original potential representation vector; performing vectorization analysis on the original cue word text to obtain an original text vector group; training the training model through the original prompt word text, the original potential representation vector and the original text vector group to obtain an image generation model; and predicting the prompt word text to be generated through the image generation model to obtain an image generation result. According to the method, accurate capturing and accurate mapping of key attributes in text description are achieved, the attribute corresponding relation between the generated image and the text is improved, the accuracy of image generation is improved, and the method has important practical application</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLD1zE1MT1VIT81LLUosyczPU8hNLcnIT9FRSEkty0xOVUjMS1EoriwuSc2FMEvyi0AaclNTMktzeRhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYjLQ3JJ4Zz9DQwsTcwNjcxNHY2LUAADzmy_X</recordid><startdate>20240809</startdate><enddate>20240809</enddate><creator>CAI XIAODONG</creator><creator>HUANG YONGSEN</creator><scope>EVB</scope></search><sort><creationdate>20240809</creationdate><title>Image generation method, device and system and storage medium</title><author>CAI XIAODONG ; HUANG YONGSEN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118470374A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CAI XIAODONG</creatorcontrib><creatorcontrib>HUANG YONGSEN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CAI XIAODONG</au><au>HUANG YONGSEN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Image generation method, device and system and storage medium</title><date>2024-08-09</date><risdate>2024</risdate><abstract>The invention provides an image generation method, device and system and a storage medium, and belongs to the technical field of image generation, and the method comprises the steps: carrying out the mapping processing of a to-be-processed image, and obtaining an original potential representation vector; performing vectorization analysis on the original cue word text to obtain an original text vector group; training the training model through the original prompt word text, the original potential representation vector and the original text vector group to obtain an image generation model; and predicting the prompt word text to be generated through the image generation model to obtain an image generation result. According to the method, accurate capturing and accurate mapping of key attributes in text description are achieved, the attribute corresponding relation between the generated image and the text is improved, the accuracy of image generation is improved, and the method has important practical application</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN118470374A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Image generation method, device and system and storage medium
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T13%3A43%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=CAI%20XIAODONG&rft.date=2024-08-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118470374A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true