{"id":105688,"date":"2025-08-31T22:40:10","date_gmt":"2025-08-31T22:40:10","guid":{"rendered":"https:\/\/www.newsbeep.com\/uk\/105688\/"},"modified":"2025-08-31T22:40:10","modified_gmt":"2025-08-31T22:40:10","slug":"ai-converts-ascii-game-to-real-time-ai-rendered-graphics-thunder-lizard-ascii-visuals-transformed-but-latency-and-consistency-need-improvement","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/uk\/105688\/","title":{"rendered":"AI converts ASCII game to real-time AI-rendered graphics \u2013 Thunder Lizard ASCII visuals transformed, but latency and consistency need improvement"},"content":{"rendered":"

Software engineer Jeff Schomay has been experimenting with techniques to transform game visuals using artificial intelligence-powered rendering. In a recent blog post,<\/a> he shared screens from his Thunder Lizard \u201cold-school ASCII RPG style game\u201d and you can see various AI models reconstructing the title\u2019s basic character-based visuals into far plusher full-motion graphics. However, there are quite a few compromises needed to achieve a \u2018playable\u2019 10fps and 1ms latency AI visual enhanced game.<\/p>\n

The current game<\/p>\n

You can play Thunder Lizard<\/a>, using the current ASCII<\/a> rogue-like engine visuals, right now, via that link. In brief, you use the cursor keys to navigate around the prehistoric landscape while attempting to catch and east smaller dinosaurs, while avoiding larger ones. You grow as you eat smaller prey, but you have to flourish enough to become the most powerful dinosaur before the volcano destroys the entire landscape.<\/p>\n

<\/p>\n

Wouldn\u2019t this game be more fun with snazzy pixel art visuals? Schomay must have thought so, too. And you can see various samples of AI-rendered alternatives to the ASCII throughout his blog post.<\/p>\n

You may like<\/p>\n

Cake and eat it \u2013 not possible<\/p>\n

As Schomay put it in his blog post, there is a \u201cneed for speed\u201d in gaming, that isn\u2019t yet met by many AI renderers. At least concerning what is available to indie devs.<\/p>\n

We get to see some fantastic looking prehistoric landscape renderers, which would really add something to Thunder Lizard. However, the software engineer couldn\u2019t coax better than \u201ca four-second latency, it was unplayable\u201d from the most handsome AI game graphics renderer.<\/p>\n

The compromise<\/p>\n

You can read much more about Schomay\u2019s efforts with various AI models in the linked blog, but for actual playability the choice was ultimately Fal.ai<\/a>. This model beat the other contenders for its \u201cvery fast generation times, source image adherence, and decent look and feel,\u201d according to the software engineer.<\/p>\n

AI rendered ASCII game in real time – YouTube
\n\"AI<\/p>\n

Watch On <\/a><\/p>\n

Though what you see is an (AI) engine capable of just 10fps and 1ms latency, it\u2019s the best option, according to Schomay\u2019s efforts, in this case.<\/p>\n

Get Tom’s Hardware’s best news and in-depth reviews, straight to your inbox.<\/p>\n

Pixel peepers might feel a little let down by the chosen AI visuals, which eventually won out. However, Schomay ends his blog on an upbeat note, stating that \u201cit is amazing to see AI image generation happen in real-time.\u201d He is also excited about the future, but hopes some strides can be made in frame to frame consistency.<\/p>\n

We’ve previously reported on the use of AI in developing and enhancing games and graphics. Nvidia shared a lot of RTX technology reliant AI-enhanced development tool<\/a> information earlier this year.<\/p>\n

Follow Tom’s Hardware on Google News<\/a>, or add us as a preferred source<\/a>, to get our up-to-date news, analysis, and reviews in your feeds. Make sure to click the Follow button!<\/p>\n","protected":false},"excerpt":{"rendered":"Software engineer Jeff Schomay has been experimenting with techniques to transform game visuals using artificial intelligence-powered rendering. In…\n","protected":false},"author":2,"featured_media":105689,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[554,733,4308,86,56,54,55],"class_list":["post-105688","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-technology","tag-uk","tag-united-kingdom","tag-unitedkingdom"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/105688","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=105688"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/105688\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/105689"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=105688"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=105688"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=105688"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}