{"id":37873,"date":"2023-04-20T09:45:35","date_gmt":"2023-04-20T06:45:35","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=37873"},"modified":"2025-08-29T22:52:02","modified_gmt":"2025-08-29T19:52:02","slug":"ai-image-generation-five-free-services","status":"publish","type":"post","link":"https:\/\/forklog.com\/en\/ai-image-generation-five-free-services\/","title":{"rendered":"AI image generation: five free services"},"content":{"rendered":"<div class=\"wp-block-text-wrappers-keypoints article_keypoints\">\n<h2 class=\"wp-block-heading\">Key points<\/h2>\n<ul class=\"wp-block-list\">\n<li>A neural network is a mathematical model that operates on principles similar to the human brain. It learns by initially processing a large dataset rather than relying on bespoke code for a specific task.<\/li>\n<li>In recent years neural networks have advanced rapidly, chiefly for tasks involving text, video, audio and other data.<\/li>\n<li>Models that can swiftly generate images from text prompts, combine graphical objects or recreate missing elements, including human faces, have become especially popular. They do not replace designers and artists, but they streamline routine work.<\/li>\n<\/ul>\n<\/div>\n<h2 class=\"wp-block-heading\">How neural networks generate images<\/h2>\n<p>Neural networks are a form of machine learning and underpin deep-learning algorithms. They consist of neurons that receive, process and return information. Neurons are connected by synapses.<\/p>\n<p>AI models rely on training data to identify patterns and solve tasks such as recognising or generating images.<\/p>\n<p>For example, when searching for similar pictures with Google Lens, the system also uses a neural network. It looks for similarities with other images in its database.<\/p>\n<p>By a similar principle, algorithms generate illustrations from text prompts. A user inputs a request in natural language and the network combines elements it has learned.<\/p>\n<p>Some models cannot create images from text, but can apply visual effects to existing pictures, stylise them after famous artists or alter selected objects.<\/p>\n<p>The potential of such systems seems vast, particularly in art. In 2022 image generators gained broad popularity.<\/p>\n<p>ForkLog has selected five free resources that let anyone test a neural network online and create unique images.<\/p>\n<h2 class=\"wp-block-heading\"><a href=\"https:\/\/www.bing.com\/create\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">Bing Image Creator<\/a><\/h2>\n<p>Microsoft\u2019s service is based on the DALL-E neural network. In March 2023 the tech giant launched a standalone site for the tool and integrated it into Bing Chat.<\/p>\n<p>In October 2022 the service was publicly released, allowing anyone to sign up and use it. The system now generates more than 2 million images a day. By contrast, creating a DALL-E 2 profile requires a phone number from a limited list of countries.<\/p>\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/Snimok-ekrana-2023-04-14-002109-817x1024.png\" alt=\"AI image generation: five free services\" class=\"wp-image-204863\" width=\"817\" height=\"1024\" srcset=\"https:\/\/forklog.com\/wp-content\/uploads\/Snimok-ekrana-2023-04-14-002109-817x1024.png 817w, https:\/\/forklog.com\/wp-content\/uploads\/Snimok-ekrana-2023-04-14-002109-239x300.png 239w, https:\/\/forklog.com\/wp-content\/uploads\/Snimok-ekrana-2023-04-14-002109-768x963.png 768w, https:\/\/forklog.com\/wp-content\/uploads\/Snimok-ekrana-2023-04-14-002109.png 1006w\" sizes=\"auto, (max-width: 817px) 100vw, 817px\" \/><figcaption>Images generated in Bing Chat mode. Data: Bing Image Creator.<\/figcaption><\/figure>\n<p>In April the AI generator appeared in the Edge browser. It is available from the sidebar to users worldwide.<\/p>\n<p>To use the service, open the corresponding browser pane, enter a prompt and wait for the result. Image Creator will produce four options, which can be downloaded.<\/p>\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\">\n<div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Image Creator in Microsoft Edge\" width=\"500\" height=\"281\" src=\"https:\/\/www.youtube.com\/embed\/yxEczioCqJk?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe>\n<\/div>\n<\/figure>\n<p>To prevent misuse for toxic content, Microsoft has implemented its own safeguards in addition to OpenAI\u2019s methods.<\/p>\n<p>The company also makes clear that images are AI-generated and marks results with watermarks.<\/p>\n<p>The tool gives users 25 boosts a week to speed up generation. One token is debited per request.<\/p>\n<p>After boosts are exhausted, the company offers to obtain more via Microsoft Rewards points or wait for a weekly refresh.<\/p>\n<h2 class=\"wp-block-heading\"><a href=\"https:\/\/dream.ai\/create\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">Dream by WOMBO<\/a><\/h2>\n<p>The web service lets you create images free and without registration, though there is a Premium tier. Mobile apps are available for <a href=\"https:\/\/play.google.com\/store\/apps\/details?id=com.womboai.wombodream&#038;utm_source=web-app&#038;utm_campaign=web-app&#038;pcampaignid=pcampaignidMKT-Other-global-all-co-prtnr-py-PartBadge-Mar2515-1\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">Android<\/a> and <a href=\"https:\/\/apps.apple.com\/us\/app\/wombo-dream\/id1586366816?itsct=apps_box_badge&#038;itscg=30200\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">iOS<\/a>.<\/p>\n<p>To generate an image, enter a text prompt up to 200 characters and select a visual style. After 10\u201320 seconds the network returns a result at 960\u00d71568 pixels.<\/p>\n<p>Finished images can be downloaded or published to the site\u2019s feed.<\/p>\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"627\" height=\"1024\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/dream_TradingCard-1-627x1024.jpg\" alt=\"AI image generation: five free services\" class=\"wp-image-204864\" srcset=\"https:\/\/forklog.com\/wp-content\/uploads\/dream_TradingCard-1-627x1024.jpg 627w, https:\/\/forklog.com\/wp-content\/uploads\/dream_TradingCard-1-184x300.jpg 184w, https:\/\/forklog.com\/wp-content\/uploads\/dream_TradingCard-1-768x1254.jpg 768w, https:\/\/forklog.com\/wp-content\/uploads\/dream_TradingCard-1-940x1536.jpg 940w, https:\/\/forklog.com\/wp-content\/uploads\/dream_TradingCard-1.jpg 960w\" sizes=\"auto, (max-width: 627px) 100vw, 627px\" \/><figcaption>An image generated in Dream by WOMBO for the prompt \u201cPink unicorn in modern Tokyo.\u201d Data: Dream by WOMBO.<\/figcaption><\/figure>\n<p>The \u201cEdit with text\u201d option lets you modify a generated image using a prompt. You can redraw an image, add or remove an element, restyle an object or invert the illustration.<\/p>\n<p>The feature is in beta and its accuracy is fairly low.<\/p>\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"627\" height=\"1024\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/Uploaded_Image_Edit_TradingCard-627x1024.jpg\" alt=\"AI image generation: five free services\" class=\"wp-image-204865\" srcset=\"https:\/\/forklog.com\/wp-content\/uploads\/Uploaded_Image_Edit_TradingCard-627x1024.jpg 627w, https:\/\/forklog.com\/wp-content\/uploads\/Uploaded_Image_Edit_TradingCard-184x300.jpg 184w, https:\/\/forklog.com\/wp-content\/uploads\/Uploaded_Image_Edit_TradingCard-768x1254.jpg 768w, https:\/\/forklog.com\/wp-content\/uploads\/Uploaded_Image_Edit_TradingCard-940x1536.jpg 940w, https:\/\/forklog.com\/wp-content\/uploads\/Uploaded_Image_Edit_TradingCard.jpg 960w\" sizes=\"auto, (max-width: 627px) 100vw, 627px\" \/><figcaption>On the image \u201cPink unicorn in modern Tokyo,\u201d Dream by WOMBO replaced asphalt with green grass. Data: Dream by WOMBO.<\/figcaption><\/figure>\n<p>In the free version you can edit an image only twice. After that you must reupload the image or modify the new one.<\/p>\n<p>The service also allows you to stylise your own image by request.<\/p>\n<p>Premium costs $9.99 a month or $89.99 a year. A one-off payment of $169.99 is also offered.<\/p>\n<h2 class=\"wp-block-heading\"><a href=\"https:\/\/huggingface.co\/spaces\/stabilityai\/stable-diffusion\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">Stable Diffusion<\/a><\/h2>\n<p>A text-to-image generator created by Stability AI. In September 2022 the service became available to the general public.<\/p>\n<p><script async=\"\" src=\"https:\/\/telegram.org\/js\/telegram-widget.js?19\" data-telegram-post=\"forklogAI\/2681\" data-width=\"100%\"><\/script><\/p>\n<p>The model was trained to create images from any text prompt, including pictures with public figures and nude people. However, in November 2022 the company updated the algorithm, weakening its ability to create <span data-descr=\"a tag used in correspondence to highlight hyperlinks containing materials with nudity, guro, pornography and obscene language\" class=\"old_tooltip\">NSFW<\/span> content and illustrations in the style of specific artists.<\/p>\n<p>The network draws for free.<\/p>\n<p>Users simply enter a text prompt of any length. The model then generates four illustrations at 512\u00d7512 pixels.<\/p>\n<figure class=\"wp-block-image size-full\"><img decoding=\"async\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/Bez-nazvaniya-4-1.webp\" alt=\"AI image generation: five free services\" class=\"wp-image-204866\"\/><figcaption>A \u201cThe Last of Us\u201d poster in anime style. Data: Stable Diffusion.<\/figcaption><\/figure>\n<h2 class=\"wp-block-heading\"><a href=\"https:\/\/lexica.art\/aperture\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">Lexica Aperture<\/a><\/h2>\n<p>In December 2022 Sharif Shameem, the founder of Lexica, a search engine for images and AI prompts, <a href=\"https:\/\/twitter.com\/sharifshameem\/status\/1602416016360759296?s=20\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">presented<\/a> the Lexica Aperture image generator. The algorithm can create photorealistic illustrations from text prompts.<\/p>\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"683\" height=\"1024\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/Polaroid-portrait-of-Joe-Biden-posing-in-the-White-1-683x1024.jpg\" alt=\"AI image generation: five free services\" class=\"wp-image-204867\" srcset=\"https:\/\/forklog.com\/wp-content\/uploads\/Polaroid-portrait-of-Joe-Biden-posing-in-the-White-1-683x1024.jpg 683w, https:\/\/forklog.com\/wp-content\/uploads\/Polaroid-portrait-of-Joe-Biden-posing-in-the-White-1-200x300.jpg 200w, https:\/\/forklog.com\/wp-content\/uploads\/Polaroid-portrait-of-Joe-Biden-posing-in-the-White-1-768x1152.jpg 768w, https:\/\/forklog.com\/wp-content\/uploads\/Polaroid-portrait-of-Joe-Biden-posing-in-the-White-1-1024x1536.jpg 1024w, https:\/\/forklog.com\/wp-content\/uploads\/Polaroid-portrait-of-Joe-Biden-posing-in-the-White-1-1365x2048.jpg 1365w, https:\/\/forklog.com\/wp-content\/uploads\/Polaroid-portrait-of-Joe-Biden-posing-in-the-White-1-scaled.jpg 1707w\" sizes=\"auto, (max-width: 683px) 100vw, 683px\" \/><figcaption>Image generated by Lexica Aperture for the prompt \u201cJoe Biden and Marilyn Monroe posing in the Oval Office of the White House.\u201d Data: Lexica Aperture.<\/figcaption><\/figure>\n<p>The network is available for free after signing in via a simple web interface. It creates images in portrait or landscape orientation at 768\u00d71152 pixels.<\/p>\n<p>Below the prompt field you can specify a negative prompt\u2014what should not appear in the picture. The service also lets you upload a reference image.<\/p>\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"683\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/Portrait-of-Daenerys-Targaryen-from-Game-of-Throne-4-1024x683.jpg\" alt=\"AI image generation: five free services\" class=\"wp-image-204868\" srcset=\"https:\/\/forklog.com\/wp-content\/uploads\/Portrait-of-Daenerys-Targaryen-from-Game-of-Throne-4-1024x683.jpg 1024w, https:\/\/forklog.com\/wp-content\/uploads\/Portrait-of-Daenerys-Targaryen-from-Game-of-Throne-4-300x200.jpg 300w, https:\/\/forklog.com\/wp-content\/uploads\/Portrait-of-Daenerys-Targaryen-from-Game-of-Throne-4-768x512.jpg 768w, https:\/\/forklog.com\/wp-content\/uploads\/Portrait-of-Daenerys-Targaryen-from-Game-of-Throne-4.jpg 1152w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption>Image generated by Lexica Aperture for the prompt \u201cDaenerys Targaryen with a dragon in a castle.\u201d Data: Lexica Aperture.<\/figcaption><\/figure>\n<p>The finished image can be expanded or used to create variations.<\/p>\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"683\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/Fotoram.io_-1024x683.png\" alt=\"AI image generation: five free services\" class=\"wp-image-204869\" srcset=\"https:\/\/forklog.com\/wp-content\/uploads\/Fotoram.io_-1024x683.png 1024w, https:\/\/forklog.com\/wp-content\/uploads\/Fotoram.io_-300x200.png 300w, https:\/\/forklog.com\/wp-content\/uploads\/Fotoram.io_-768x512.png 768w, https:\/\/forklog.com\/wp-content\/uploads\/Fotoram.io_-1536x1024.png 1536w, https:\/\/forklog.com\/wp-content\/uploads\/Fotoram.io_-2048x1365.png 2048w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption>Four variants of an image generated by Lexica Aperture for the prompt \u201cDaenerys Targaryen with a dragon in a castle.\u201d Data: Lexica Aperture.<\/figcaption><\/figure>\n<h2 class=\"wp-block-heading\"><a href=\"https:\/\/deepdreamgenerator.com\/generator\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">Deep Dream Generator<\/a><\/h2>\n<p>A platform for creating and editing images. The service requires account registration and has limits on free use.<\/p>\n<p>The project\u2019s site offers three modes.<\/p>\n<h3 class=\"wp-block-heading\">Text 2 Dream<\/h3>\n<p>Creates images from a text description. The user should craft a prompt or click \u201crandom prompt.\u201d<\/p>\n<p>The generator is relatively fast, but sometimes falls short of DALL-E 2 or Stable Diffusion in its interpretation of words and the resulting images.<\/p>\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/kgap3j_8f30ef7125f2bfb37ad4167a2b82c2216c9439ed.webp\" alt=\"AI image generation: five free services\" class=\"wp-image-204870\" width=\"840\" height=\"660\"\/><figcaption>Image generated by Deep Dream Generator for the prompt \u201cNFT unicorn riding a Space X rocket in space.\u201d Data: Deep Dream Generator.<\/figcaption><\/figure>\n<h3 class=\"wp-block-heading\">Deep Dream<\/h3>\n<p>This mode performs deep processing of a source image using AI algorithms. Upload a picture and set parameters: initial depth, AI enhancement and neural-network layer.<\/p>\n<figure class=\"wp-block-image size-full\"><img decoding=\"async\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/sedfj3_92c4a02e42761cc47c42d47a24904064cfe5853a.webp\" alt=\"AI image generation: five free services\" class=\"wp-image-204871\"\/><figcaption>An image generated with Deep Dream Generator and processed in Deep Dream mode. Data: Deep Dream Generator.<\/figcaption><\/figure>\n<h3 class=\"wp-block-heading\">Deep Style<\/h3>\n<p>In this mode the user can stylise an existing image. They upload a picture or photo and select a reference illustration from the list.<\/p>\n<figure class=\"wp-block-image size-full\"><img decoding=\"async\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/dmezj1_2a6cc265dd31b701c4506f4d4f8431c930bf3215.webp\" alt=\"AI image generation: five free services\" class=\"wp-image-204872\"\/><figcaption>An image generated with Deep Dream Generator and stylised in Deep Style mode. Data: Deep Dream Generator.<\/figcaption><\/figure>\n<p>As for free-tier limits, upon registration the user receives 30 units of energy. They are consumed when using the tools: five points per request in Deep Style or Text 2 Dream, and two points per request in Deep Dream.<\/p>\n<p>Energy can be purchased. The cheapest plan costs $19 per month.<\/p>\n<h2 class=\"wp-block-heading\"><a href=\"https:\/\/labs.openai.com\/\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">DALL-E 2<\/a><\/h2>\n<p>In January 2021 OpenAI sparked a revolution in AI by <a href=\"https:\/\/openai.com\/research\/dall-e\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">presenting<\/a> DALL-E, a text-to-image generator.<\/p>\n<p>It is a <a href=\"https:\/\/forklog.com\/en\/news\/what-are-transformers-machine-learning\">transformer<\/a> built on the large language model GPT-3 with 12 billion parameters and trained on text\u2013image pairs.<\/p>\n<p>The network generates images at 256\u00d7256 pixels. It offers a wide range of capabilities, including creating anthropomorphic animals and objects, realistically combining unrelated concepts, rendering text and applying transformations to existing illustrations.<\/p>\n<figure class=\"wp-block-image size-full\"><img decoding=\"async\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/Snimok-ekrana-2023-04-12-210828.webp\" alt=\"AI image generation: five free services\" class=\"wp-image-204873\"\/><figcaption>Images created with DALL-E for the prompt \u201cAn armchair in the shape of an avocado.\u201d Data: OpenAI.<\/figcaption><\/figure>\n<p>In April 2022 the company released the second version, which generates more realistic images with lower latency at 1024\u00d71024 pixels.<\/p>\n<p>DALL-E 2 lets you select and edit specific areas of existing images, add or remove elements along with shadows, create collages and produce variations.<\/p>\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"1010\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/Snimok-ekrana-2023-04-12-214517-1024x1010.png\" alt=\"AI image generation: five free services\" class=\"wp-image-204874\" srcset=\"https:\/\/forklog.com\/wp-content\/uploads\/Snimok-ekrana-2023-04-12-214517-1024x1010.png 1024w, https:\/\/forklog.com\/wp-content\/uploads\/Snimok-ekrana-2023-04-12-214517-300x296.png 300w, https:\/\/forklog.com\/wp-content\/uploads\/Snimok-ekrana-2023-04-12-214517-768x758.png 768w, https:\/\/forklog.com\/wp-content\/uploads\/Snimok-ekrana-2023-04-12-214517.png 1284w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption>Portrait of <a href=\"https:\/\/forklog.com\/en\/news\/who-is-satoshi-nakamoto\">Satoshi Nakamoto<\/a>, generated by DALL-E 2. Data: DALL-E 2.<\/figcaption><\/figure>\n<p>The new version also offers <a href=\"https:\/\/openai.com\/blog\/dall-e-introducing-outpainting\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">Outpanting<\/a>. It lets you expand an image using text prompts. When adding new objects, the system accounts for existing visual elements such as shadows, reflections and textures.<\/p>\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"326\" src=\"https:\/\/forklog.com\/wp-content\/uploads\/11-56-1024x326.png\" alt=\"AI image generation: five free services\" class=\"wp-image-204875\" srcset=\"https:\/\/forklog.com\/wp-content\/uploads\/11-56-1024x326.png 1024w, https:\/\/forklog.com\/wp-content\/uploads\/11-56-300x95.png 300w, https:\/\/forklog.com\/wp-content\/uploads\/11-56-768x244.png 768w, https:\/\/forklog.com\/wp-content\/uploads\/11-56-1536x488.png 1536w, https:\/\/forklog.com\/wp-content\/uploads\/11-56.png 2000w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption>Johannes Vermeer\u2019s \u201cGirl with a Pearl Earring\u201d and its expanded version created with DALL-E 2. Data: OpenAI.<\/figcaption><\/figure>\n<p>In October 2022 OpenAI closed the waitlist for the beta version of the image generator.<\/p>\n<p>The network is available in all countries except Afghanistan, Belarus, Venezuela, Iran, China and Russia.<\/p>\n<p>In February 2023 it became known that Ukraine was removed from the list of countries where the company\u2019s services are blocked. However, OpenAI\u2019s algorithms do not work in territories temporarily occupied by Russia.<\/p>\n<p>Users in regions where the technology is unavailable can interact with DALL-E 2 only if they have a VPN service and an active phone number from a country open to OpenAI products.<\/p>\n<p>Registration in DALL-E 2 is free. Image generation requires credits, with one deducted for each text prompt.<\/p>\n<p>Previously, new users were given free attempts to create images. Recently this <a href=\"https:\/\/help.openai.com\/en\/articles\/6399305-how-dall-e-credits-work\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">changed<\/a>.<\/p>\n<p>The network became paid for accounts registered after April 6, 2023. 115 attempts cost $15.<\/p>\n<p>Users who created an account before that date can still use the network for free. They receive 50 credits, which after a month decrease to 15. The number of attempts renews every 30 days.<\/p>\n<p>Various companies and well-known brands use DALL-E 2. <a href=\"https:\/\/www.cosmopolitan.com\/lifestyle\/a40314356\/dall-e-2-artificial-intelligence-cover\/\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">Cosmopolitan<\/a> and <a href=\"https:\/\/www.economist.com\/news\/2022\/06\/11\/how-a-computer-designed-this-weeks-cover\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">The Economist<\/a> used the network to generate covers. Microsoft launched its own application, <a href=\"https:\/\/designer.microsoft.com\/\" target=\"_blank\" rel=\"noopener nofollow\" title=\"\">Designer<\/a>, based on the service, which can create content such as text, ad banners, greeting cards and logos.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Which sites let you create images with neural networks, how the services differ and what their terms of use are\u2014read in this Cryptorium selection.<\/p>\n","protected":false},"author":1,"featured_media":37874,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"1","news_style_id":"5","cryptorium_level":"2","_short_excerpt_text":"","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[2113],"tags":[2130,438],"class_list":["post-37873","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-cryptorium","tag-101-artificial-intelligence","tag-artificial-intelligence"],"aioseo_notices":[],"amp_enabled":true,"views":"177","promo_type":"1","layout_type":"5","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/37873","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/comments?post=37873"}],"version-history":[{"count":1,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/37873\/revisions"}],"predecessor-version":[{"id":37875,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/37873\/revisions\/37875"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media\/37874"}],"wp:attachment":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media?parent=37873"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/categories?post=37873"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/tags?post=37873"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}