{"id":12486,"date":"2024-05-21T18:26:24","date_gmt":"2024-05-21T18:26:24","guid":{"rendered":"https:\/\/dailyai.com\/?p=12486"},"modified":"2024-05-21T20:56:24","modified_gmt":"2024-05-21T20:56:24","slug":"researchers-train-model-to-create-images-without-seeing-copyrighted-work","status":"publish","type":"post","link":"https:\/\/dailyai.com\/pt\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/","title":{"rendered":"Os investigadores treinam um modelo para criar imagens sem \"ver\" obras protegidas por direitos de autor"},"content":{"rendered":"

Os investigadores da Universidade do Texas em Austin desenvolveram uma estrutura inovadora para treinar modelos de IA em imagens fortemente corrompidas.\u00a0<\/b><\/p>\n

Conhecido como Ambient Diffusion, este m\u00e9todo permite aos modelos de IA \"inspirarem-se\" nas imagens sem<\/em> copiando-os diretamente.<\/span><\/p>\n

Modelos convencionais de texto-imagem utilizados por DALL-E<\/span><\/span><\/span>Midjourney e Stable Diffusion correm o risco de violar direitos de autor porque s\u00e3o treinados em conjuntos de dados que incluem imagens protegidas por direitos de autor, levando-os por vezes a replicar inadvertidamente essas imagens.\u00a0<\/span><\/p>\n

O Ambient Diffusion inverte isso ao treinar modelos com dados deliberadamente corrompidos.<\/p>\n

No estudo<\/a>A equipa de investiga\u00e7\u00e3o, que inclui Alex Dimakis e Giannis Daras do departamento de Engenharia Eletrot\u00e9cnica e de Computadores da UT Austin e Constantinos Daskalakis da MIT<\/span><\/span><\/span><\/span><\/span>treinou um modelo Stable Diffusion XL num conjunto de dados de 3.000 imagens de celebridades.\u00a0<\/span><\/p>\n

Inicialmente, observou-se que os modelos treinados em dados limpos copiavam descaradamente os exemplos de treino.\u00a0<\/span><\/p>\n

No entanto, quando os dados de treino foram corrompidos - mascarando aleatoriamente at\u00e9 90% dos pix\u00e9is - o modelo continuou a produzir imagens \u00fanicas e de alta qualidade.<\/span><\/p>\n

Isto significa que a IA nunca \u00e9 exposta a vers\u00f5es reconhec\u00edveis das imagens originais, impedindo-a de as copiar.<\/span><\/p>\n

\"A nossa estrutura permite controlar o compromisso entre a memoriza\u00e7\u00e3o e o desempenho\". <\/span>explicou Giannis Daras<\/span><\/a>, um estudante licenciado em ci\u00eancias inform\u00e1ticas que liderou o trabalho.\u00a0<\/span><\/p>\n

\"\u00c0 medida que o n\u00edvel de corrup\u00e7\u00e3o encontrado durante o treino aumenta, a memoriza\u00e7\u00e3o do conjunto de treino diminui.\"<\/span><\/p>\n

Aplica\u00e7\u00f5es cient\u00edficas e m\u00e9dicas<\/h2>\n

As utiliza\u00e7\u00f5es da difus\u00e3o ambiente v\u00e3o para al\u00e9m da resolu\u00e7\u00e3o de quest\u00f5es de direitos de autor.\u00a0<\/span><\/p>\n

De acordo com o Professor Adam Klivans, um colaborador do projeto, \"o quadro poderia revelar-se \u00fatil tamb\u00e9m para aplica\u00e7\u00f5es cient\u00edficas e m\u00e9dicas. Isto aplicar-se-ia basicamente a qualquer investiga\u00e7\u00e3o em que seja dispendioso ou imposs\u00edvel dispor de um conjunto completo de dados n\u00e3o corrompidos, desde a imagiologia de buracos negros a certos tipos de exames de resson\u00e2ncia magn\u00e9tica\".<\/span><\/p>\n

Isto \u00e9 particularmente ben\u00e9fico em dom\u00ednios com acesso limitado a dados n\u00e3o corrompidos, tais como astronomia e f\u00edsica das part\u00edculas<\/a>.\u00a0<\/span><\/p>\n

Nestes e noutros dom\u00ednios, os dados podem ser extremamente ruidosos, de m\u00e1 qualidade ou escassos, o que significa que os dados significativos s\u00e3o em grande n\u00famero ultrapassados por dados in\u00fateis. Ensinar os modelos a utilizar dados sub-\u00f3ptimos de forma mais eficiente seria \u00fatil neste caso.<\/p>\n

Se a abordagem de difus\u00e3o ambiente fosse mais aperfei\u00e7oada, as empresas de IA poderiam criar modelos funcionais de texto para imagem, respeitando os direitos dos criadores de conte\u00fados originais e evitando problemas jur\u00eddicos.<\/p>\n

Embora isso n\u00e3o resolva os receios de que as ferramentas de imagem de IA reduzam o leque de trabalho dos verdadeiros artistas, pelo menos protegeria as suas obras de serem acidentalmente reproduzidas em resultados.<\/p>","protected":false},"excerpt":{"rendered":"

Os investigadores da Universidade do Texas em Austin desenvolveram uma estrutura inovadora para treinar modelos de IA em imagens fortemente corrompidas. Conhecido como Ambient Diffusion, este m\u00e9todo permite aos modelos de IA \"inspirarem-se\" nas imagens sem as copiarem diretamente. Os modelos convencionais de texto-imagem utilizados por DALL-E, Midjourney e Stable Diffusion correm o risco de violar os direitos de autor porque s\u00e3o treinados em conjuntos de dados que incluem imagens protegidas por direitos de autor, o que os leva, por vezes, a replicar inadvertidamente essas imagens. O Ambient Diffusion inverte esta situa\u00e7\u00e3o ao treinar modelos com dados deliberadamente corrompidos. No estudo, a equipa de investiga\u00e7\u00e3o, que inclui Alex Dimakis e Giannis Daras da Faculdade de Engenharia Eletrot\u00e9cnica e de Computadores da Universidade de Lisboa, estudou o seguinte<\/p>","protected":false},"author":2,"featured_media":12492,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[88],"tags":[165,105],"class_list":["post-12486","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ethics","tag-image-generation","tag-machine-learning"],"yoast_head":"\nResearchers train model to create images without 'seeing' copyrighted work | DailyAI<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/pt\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/\" \/>\n<meta property=\"og:locale\" content=\"pt_PT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Researchers train model to create images without 'seeing' copyrighted work | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers at The University of Texas at Austin have developed an innovative framework for training AI models on heavily corrupted images.\u00a0 Known as Ambient Diffusion, this method enables AI models to ‘draw inspiration’ from images without directly copying them. Conventional text-to-image models used by DALL-E, Midjourney, and Stable Diffusion risk copyright infringement because they’re trained on datasets that include copyrighted images, leading them to sometimes inadvertently replicate those images.\u00a0 Ambient Diffusion flips that on its head by training models with deliberately corrupted data. In the study, the research team, including Alex Dimakis and Giannis Daras from the Electrical and Computer\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/pt\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-05-21T18:26:24+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-05-21T20:56:24+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-21-19.21.33-A-high-tech-lab-with-researchers-working-on-a-diffusion-model-for-creating-images-without-seeing-copyrighted-work.-The-focal-point-is-a-large-comput.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1792\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Sam Jeans\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"Escrito por\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sam Jeans\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tempo estimado de leitura\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"Researchers train model to create images without ‘seeing’ copyrighted work\",\"datePublished\":\"2024-05-21T18:26:24+00:00\",\"dateModified\":\"2024-05-21T20:56:24+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/\"},\"wordCount\":404,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/DALL\u00b7E-2024-05-21-19.21.33-A-high-tech-lab-with-researchers-working-on-a-diffusion-model-for-creating-images-without-seeing-copyrighted-work.-The-focal-point-is-a-large-comput.webp\",\"keywords\":[\"image generation\",\"machine learning\"],\"articleSection\":[\"Ethics & Society\"],\"inLanguage\":\"pt-PT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/\",\"name\":\"Researchers train model to create images without 'seeing' copyrighted work | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/DALL\u00b7E-2024-05-21-19.21.33-A-high-tech-lab-with-researchers-working-on-a-diffusion-model-for-creating-images-without-seeing-copyrighted-work.-The-focal-point-is-a-large-comput.webp\",\"datePublished\":\"2024-05-21T18:26:24+00:00\",\"dateModified\":\"2024-05-21T20:56:24+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/#breadcrumb\"},\"inLanguage\":\"pt-PT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/DALL\u00b7E-2024-05-21-19.21.33-A-high-tech-lab-with-researchers-working-on-a-diffusion-model-for-creating-images-without-seeing-copyrighted-work.-The-focal-point-is-a-large-comput.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/DALL\u00b7E-2024-05-21-19.21.33-A-high-tech-lab-with-researchers-working-on-a-diffusion-model-for-creating-images-without-seeing-copyrighted-work.-The-focal-point-is-a-large-comput.webp\",\"width\":1792,\"height\":1024,\"caption\":\"Image generation\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/05\\\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Researchers train model to create images without ‘seeing’ copyrighted work\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"pt-PT\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\",\"name\":\"Sam Jeans\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"pt-PT\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"caption\":\"Sam Jeans\"},\"description\":\"Sam is a science and technology writer who has worked in various AI startups. When he\u2019s not writing, he can be found reading medical journals or digging through boxes of vinyl records.\",\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/sam-jeans-6746b9142\\\/\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/pt\\\/author\\\/samjeans\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Investigadores treinam modelo para criar imagens sem \"ver\" trabalhos protegidos por direitos de autor | DailyAI","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/pt\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/","og_locale":"pt_PT","og_type":"article","og_title":"Researchers train model to create images without 'seeing' copyrighted work | DailyAI","og_description":"Researchers at The University of Texas at Austin have developed an innovative framework for training AI models on heavily corrupted images.\u00a0 Known as Ambient Diffusion, this method enables AI models to ‘draw inspiration’ from images without directly copying them. Conventional text-to-image models used by DALL-E, Midjourney, and Stable Diffusion risk copyright infringement because they’re trained on datasets that include copyrighted images, leading them to sometimes inadvertently replicate those images.\u00a0 Ambient Diffusion flips that on its head by training models with deliberately corrupted data. In the study, the research team, including Alex Dimakis and Giannis Daras from the Electrical and Computer","og_url":"https:\/\/dailyai.com\/pt\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/","og_site_name":"DailyAI","article_published_time":"2024-05-21T18:26:24+00:00","article_modified_time":"2024-05-21T20:56:24+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-21-19.21.33-A-high-tech-lab-with-researchers-working-on-a-diffusion-model-for-creating-images-without-seeing-copyrighted-work.-The-focal-point-is-a-large-comput.webp","type":"image\/webp"}],"author":"Sam Jeans","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Escrito por":"Sam Jeans","Tempo estimado de leitura":"2 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"Researchers train model to create images without ‘seeing’ copyrighted work","datePublished":"2024-05-21T18:26:24+00:00","dateModified":"2024-05-21T20:56:24+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/"},"wordCount":404,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-21-19.21.33-A-high-tech-lab-with-researchers-working-on-a-diffusion-model-for-creating-images-without-seeing-copyrighted-work.-The-focal-point-is-a-large-comput.webp","keywords":["image generation","machine learning"],"articleSection":["Ethics & Society"],"inLanguage":"pt-PT"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/","url":"https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/","name":"Investigadores treinam modelo para criar imagens sem \"ver\" trabalhos protegidos por direitos de autor | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-21-19.21.33-A-high-tech-lab-with-researchers-working-on-a-diffusion-model-for-creating-images-without-seeing-copyrighted-work.-The-focal-point-is-a-large-comput.webp","datePublished":"2024-05-21T18:26:24+00:00","dateModified":"2024-05-21T20:56:24+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/#breadcrumb"},"inLanguage":"pt-PT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/"]}]},{"@type":"ImageObject","inLanguage":"pt-PT","@id":"https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-21-19.21.33-A-high-tech-lab-with-researchers-working-on-a-diffusion-model-for-creating-images-without-seeing-copyrighted-work.-The-focal-point-is-a-large-comput.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/05\/DALL\u00b7E-2024-05-21-19.21.33-A-high-tech-lab-with-researchers-working-on-a-diffusion-model-for-creating-images-without-seeing-copyrighted-work.-The-focal-point-is-a-large-comput.webp","width":1792,"height":1024,"caption":"Image generation"},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/05\/researchers-train-model-to-create-images-without-seeing-copyrighted-work\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Researchers train model to create images without ‘seeing’ copyrighted work"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"A sua dose di\u00e1ria de not\u00edcias sobre IA","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"pt-PT"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"pt-PT","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9","name":"Cal\u00e7as de ganga Sam","image":{"@type":"ImageObject","inLanguage":"pt-PT","@id":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","caption":"Sam Jeans"},"description":"Sam \u00e9 um escritor de ci\u00eancia e tecnologia que trabalhou em v\u00e1rias startups de IA. Quando n\u00e3o est\u00e1 a escrever, pode ser encontrado a ler revistas m\u00e9dicas ou a vasculhar caixas de discos de vinil.","sameAs":["https:\/\/www.linkedin.com\/in\/sam-jeans-6746b9142\/"],"url":"https:\/\/dailyai.com\/pt\/author\/samjeans\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/12486","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/comments?post=12486"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/12486\/revisions"}],"predecessor-version":[{"id":12498,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/posts\/12486\/revisions\/12498"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/media\/12492"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/media?parent=12486"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/categories?post=12486"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/pt\/wp-json\/wp\/v2\/tags?post=12486"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}