{"id":906,"date":"2025-07-06T05:28:51","date_gmt":"2025-07-06T05:28:51","guid":{"rendered":"https:\/\/janusai.pro\/?p=906"},"modified":"2025-07-06T05:28:52","modified_gmt":"2025-07-06T05:28:52","slug":"janus-4o-sharegpt-4o-image","status":"publish","type":"post","link":"https:\/\/janusai.pro\/ro\/janus-4o-sharegpt-4o-image\/","title":{"rendered":"Noua vedet\u0103 a gener\u0103rii de imagini multimodale: Janus-4o? Distribuie GPT-4o-Image stabile\u0219te un nou standard pentru seturile de date, aliniind generarea de imagini cu GPT-4o."},"content":{"rendered":"<div style=\"margin-top: 0px; margin-bottom: 0px;\" class=\"sharethis-inline-share-buttons\" ><\/div>\n<p><a href=\"https:\/\/sharegpt4o.github.io\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Distribui\u021bi imaginea GPT-4o<\/a> este un set de date de generare a imaginilor la scar\u0103 larg\u0103 \u0219i de \u00eenalt\u0103 calitate, \u00een care toate imaginile sunt generate folosind capacit\u0103\u021bile de generare a imaginilor ale GPT-4o.<\/p>\n\n\n\n<p>Acest set de date \u00ee\u0219i propune s\u0103 combine avantajele modelelor multimodale open-source cu punctele forte ale GPT-4o \u00een crearea de con\u021binut vizual. <\/p>\n\n\n\n<p>Include 45.000 de exemple de conversii text-imagine \u0219i 46.000 de conversii imagine-text, ceea ce \u00eel face o resurs\u0103 practic\u0103 pentru \u00eembun\u0103t\u0103\u021birea modelelor multimodale \u00een sarcinile de generare \u0219i editare a imaginilor.<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"998\" height=\"700\" src=\"https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/f48c8349-9310-48a1-9276-d7614aa958d9.png\" alt=\"\" class=\"wp-image-911\" srcset=\"https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/f48c8349-9310-48a1-9276-d7614aa958d9.png 998w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/f48c8349-9310-48a1-9276-d7614aa958d9-300x210.png 300w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/f48c8349-9310-48a1-9276-d7614aa958d9-768x539.png 768w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/f48c8349-9310-48a1-9276-d7614aa958d9-18x12.png 18w\" sizes=\"auto, (max-width: 998px) 100vw, 998px\" \/><\/figure>\n\n\n\n<p>Janus-4o este un LLM multimodal capabil de generare text-imagine \u0219i text+imagine-imagine. Se bazeaz\u0103 pe Janus-Pro \u0219i este optimizat folosind setul de date ShareGPT-4o-Image. Comparativ cu Janus-Pro, Janus-4o introduce capacit\u0103\u021bi de generare text+imagine-imagine \u0219i realizeaz\u0103 \u00eembun\u0103t\u0103\u021biri semnificative \u00een generarea text-imagine.<\/p>\n\n\n\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_82_2 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Tabla de con\u021binut<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Tabelul de con\u021binut\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewbox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewbox=\"0 0 24 24\" version=\"1.2\" baseprofile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/janusai.pro\/ro\/janus-4o-sharegpt-4o-image\/#Dataset_Overview\" >Prezentare general\u0103 a setului de date<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/janusai.pro\/ro\/janus-4o-sharegpt-4o-image\/#Related_Links\" >Linkuri conexe<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/janusai.pro\/ro\/janus-4o-sharegpt-4o-image\/#Paper_Introduction\" >Introducere la lucrare<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/janusai.pro\/ro\/janus-4o-sharegpt-4o-image\/#Method_Overview\" >Prezentare general\u0103 a metodei<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/janusai.pro\/ro\/janus-4o-sharegpt-4o-image\/#Experimental_Results\" >Rezultate experimentale<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/janusai.pro\/ro\/janus-4o-sharegpt-4o-image\/#Conclusions\" >Concluzii<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Dataset_Overview\"><\/span>Prezentare general\u0103 a setului de date<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Setul de date ShareGPT-4o-Image con\u021bine 91.000 de mostre de generare a imaginilor GPT-4o, clasificate dup\u0103 cum urmeaz\u0103:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Text-imagine: 45.717<\/li>\n\n\n\n<li>Text-plus-imagine-\u00een-imagine: 46.539<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Related_Links\"><\/span>Linkuri conexe<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Cod: <a href=\"https:\/\/github.com\/FreedomIntelligence\/ShareGPT-4o-Image\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">github click aici<\/a><\/p>\n\n\n\n<p>Model: <a href=\"https:\/\/huggingface.co\/FreedomIntelligence\/Janus-4o-7B\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">ob\u021bine\u021bi modelul ShareGPT-4o-Image<\/a><\/p>\n\n\n\n<p>H\u00e2rtie: <a href=\"https:\/\/arxiv.org\/pdf\/2506.18095\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">click aici<\/a><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Paper_Introduction\"><\/span>Introducere la lucrare<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Progresele recente \u00een modelele de generare multimodal\u0103 au permis o generare realist\u0103 de imagini, aliniat\u0103 la instruc\u021biuni. Cu toate acestea, sistemele de top precum GPT-4o-Image r\u0103m\u00e2n proprietare \u0219i inaccesibile.<\/p>\n\n\n\n<p>Pentru a face aceste capabilit\u0103\u021bi accesibile publicului, lucrarea introduce ShareGPT-4o-Image, primul set de date care con\u021bine 45.000 de exemple de text-imagine \u0219i 46.000 de exemple de text-plus-imagine-imagine, toate sintetizate folosind capacit\u0103\u021bile de generare de imagini ale GPT-4o pentru a-i rafina capacit\u0103\u021bile avansate de generare de imagini. Folosind acest set de date, lucrarea a dezvoltat Janus-4o, un model de limbaj multimodal de dimensiuni mari capabil de generare text-imagine \u0219i text-plus-imagine-imagine.<\/p>\n\n\n\n<p>Janus-4o nu numai c\u0103 \u00eembun\u0103t\u0103\u021be\u0219te semnificativ capacit\u0103\u021bile de generare text-imagine fa\u021b\u0103 de predecesorul s\u0103u Janus-Pro, dar introduce \u0219i capacit\u0103\u021bi de generare text-plus-imagine-imagine. \u00cen special, ob\u021bine performan\u021be impresionante \u00een generarea de imagini din text \u0219i imagini de la zero folosind doar 91K e\u0219antioane sintetice \u0219i antrenat timp de 6 ore pe o ma\u0219in\u0103 GPU 8\u00d7A800.<\/p>\n\n\n\n<p>Sper\u0103m c\u0103 lansarea ShareGPT-4o-Image \u0219i Janus-4o va promova cercetarea deschis\u0103 \u00een generarea de imagini fotorealiste, aliniate la instruc\u021biuni.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Method_Overview\"><\/span>Prezentare general\u0103 a metodei<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"1028\" height=\"718\" src=\"https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/74bd55e5-5cc6-49e8-be21-cf5c4a66042d.png\" alt=\"\" class=\"wp-image-908\" srcset=\"https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/74bd55e5-5cc6-49e8-be21-cf5c4a66042d.png 1028w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/74bd55e5-5cc6-49e8-be21-cf5c4a66042d-300x210.png 300w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/74bd55e5-5cc6-49e8-be21-cf5c4a66042d-1024x715.png 1024w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/74bd55e5-5cc6-49e8-be21-cf5c4a66042d-768x536.png 768w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/74bd55e5-5cc6-49e8-be21-cf5c4a66042d-18x12.png 18w\" sizes=\"auto, (max-width: 1028px) 100vw, 1028px\" \/><\/figure>\n\n\n\n<p><strong>ShareGPT-4o-Image \u00eembun\u0103t\u0103\u021be\u0219te performan\u021ba gener\u0103rii de imagini.<\/strong> Prin ajustarea fin\u0103 a Janus-Pro cu ShareGPT-4o-Image, am generat Janus-4o, care demonstreaz\u0103 o performan\u021b\u0103 de generare a imaginilor semnificativ \u00eembun\u0103t\u0103\u021bit\u0103. Janus-4o accept\u0103, de asemenea, generarea text-imagine \u0219i imagine-imagine, dep\u0103\u0219ind alte teste de performan\u021b\u0103 cu doar 91.000 de e\u0219antioane de antrenament.<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"370\" src=\"https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/fc3b163f-d1d2-42f5-81bc-884eb677ea52.png\" alt=\"\" class=\"wp-image-910\" srcset=\"https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/fc3b163f-d1d2-42f5-81bc-884eb677ea52.png 1024w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/fc3b163f-d1d2-42f5-81bc-884eb677ea52-300x108.png 300w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/fc3b163f-d1d2-42f5-81bc-884eb677ea52-768x278.png 768w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/fc3b163f-d1d2-42f5-81bc-884eb677ea52-18x7.png 18w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p><strong>Prezentare general\u0103 a modelului Janus-4o.<\/strong> Modelul se bazeaz\u0103 pe Janus-Pro \u0219i a fost construit prin reglarea fin\u0103 a acestuia pe ShareGPT-4o-Image. Acesta \u00eencorporeaz\u0103 \u00eembun\u0103t\u0103\u021biri pentru a sprijini generarea de text-imagine \u0219i imagine-imagine. At\u00e2t sarcinile text-imagine, c\u00e2t \u0219i cele text-imagine sunt antrenate \u00een comun.<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"1058\" height=\"304\" src=\"https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/2b81408d-3c8b-45a8-ac73-ee0a48164c05.png\" alt=\"\" class=\"wp-image-909\" srcset=\"https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/2b81408d-3c8b-45a8-ac73-ee0a48164c05.png 1058w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/2b81408d-3c8b-45a8-ac73-ee0a48164c05-300x86.png 300w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/2b81408d-3c8b-45a8-ac73-ee0a48164c05-1024x294.png 1024w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/2b81408d-3c8b-45a8-ac73-ee0a48164c05-768x221.png 768w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/2b81408d-3c8b-45a8-ac73-ee0a48164c05-18x5.png 18w\" sizes=\"auto, (max-width: 1058px) 100vw, 1058px\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Experimental_Results\"><\/span>Rezultate experimentale<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"1072\" height=\"1140\" src=\"https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/72720ada-7418-4979-a8fd-4ce09050d696.png\" alt=\"\" class=\"wp-image-907\" srcset=\"https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/72720ada-7418-4979-a8fd-4ce09050d696.png 1072w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/72720ada-7418-4979-a8fd-4ce09050d696-282x300.png 282w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/72720ada-7418-4979-a8fd-4ce09050d696-963x1024.png 963w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/72720ada-7418-4979-a8fd-4ce09050d696-768x817.png 768w, https:\/\/janusai.pro\/wp-content\/uploads\/2025\/07\/72720ada-7418-4979-a8fd-4ce09050d696-11x12.png 11w\" sizes=\"auto, (max-width: 1072px) 100vw, 1072px\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Conclusions\"><\/span>Concluzii<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>ShareGPT-4o-Image este primul set de date la scar\u0103 larg\u0103 capabil s\u0103 surprind\u0103 capacit\u0103\u021bile avansate de generare de imagini ale GPT-4o \u00een generarea text-imagine \u0219i text-imagine. Pe baza acestui set de date, lucrarea a dezvoltat Janus-4o, un model de \u00eenv\u0103\u021bare automat\u0103 (MLLM) capabil s\u0103 genereze imagini de \u00eenalt\u0103 calitate din text pur sau combina\u021bii imagine-text.<\/p>\n\n\n\n<p>Janus-4o realizeaz\u0103 \u00eembun\u0103t\u0103\u021biri semnificative \u00een generarea text-imagine \u0219i ob\u021bine rezultate extrem de competitive \u00een sarcinile text-imagine, demonstr\u00e2nd calitatea \u00eenalt\u0103 \u0219i caracterul practic al ShareGPT-4o-Image.<\/p>\n\n\n\n<p>Datorit\u0103 eficien\u021bei gener\u0103rii de imagini autoregresive bazate pe MLLM, Janus-4o poate fi antrenat \u00een doar 6 ore pe o ma\u0219in\u0103 GPU 8\u00d7A800 \u0219i ob\u021bine \u00eembun\u0103t\u0103\u021biri semnificative ale performan\u021bei cu cerin\u021be de calcul extrem de reduse.<\/p>","protected":false},"excerpt":{"rendered":"<p>ShareGPT-4o-Image este un set de date de generare de imagini la scar\u0103 larg\u0103 \u0219i de \u00eenalt\u0103 calitate, \u00een care toate imaginile sunt generate folosind capacit\u0103\u021bile de generare de imagini ale GPT-4o. Acest set de date \u00ee\u0219i propune s\u0103 combine avantajele modelelor multimodale open-source cu punctele forte ale GPT-4o \u00een crearea de con\u021binut vizual. Include 45.000 de mostre text-imagine \u0219i 46.000 de mostre imagine-text, ceea ce \u00eel face o resurs\u0103 practic\u0103 pentru \u00eembun\u0103t\u0103\u021birea modelelor multimodale \u00een domeniul imaginilor...<\/p>","protected":false},"author":2,"featured_media":859,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_kadence_starter_templates_imported_post":false,"_kad_post_transparent":"","_kad_post_title":"","_kad_post_layout":"","_kad_post_sidebar_id":"","_kad_post_content_style":"","_kad_post_vertical_padding":"","_kad_post_feature":"","_kad_post_feature_position":"","_kad_post_header":false,"_kad_post_footer":false,"footnotes":""},"categories":[1],"tags":[],"class_list":["post-906","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/janusai.pro\/ro\/wp-json\/wp\/v2\/posts\/906","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/janusai.pro\/ro\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/janusai.pro\/ro\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/janusai.pro\/ro\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/janusai.pro\/ro\/wp-json\/wp\/v2\/comments?post=906"}],"version-history":[{"count":1,"href":"https:\/\/janusai.pro\/ro\/wp-json\/wp\/v2\/posts\/906\/revisions"}],"predecessor-version":[{"id":912,"href":"https:\/\/janusai.pro\/ro\/wp-json\/wp\/v2\/posts\/906\/revisions\/912"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/janusai.pro\/ro\/wp-json\/wp\/v2\/media\/859"}],"wp:attachment":[{"href":"https:\/\/janusai.pro\/ro\/wp-json\/wp\/v2\/media?parent=906"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/janusai.pro\/ro\/wp-json\/wp\/v2\/categories?post=906"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/janusai.pro\/ro\/wp-json\/wp\/v2\/tags?post=906"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}