Seni kecerdasan buatan: Perbedaan antara revisi

[[Berkas:1960's_art_of_cow_getting_abducted_by_UFO_in_midwestGothic Amethyst Restaurant Interior at Night (CLIP-Guided Diffusion).jpg|jmpl|Sebuah gambar yang dihasilkan oleh DALLCLIP-EGuided 2Diffusion berdasarkan perintah teks "seniLukisan dekadeyang 1960-anenigmatik tentangdan sapiindah yangdari diculiksebuah olehrestoran UFOgotik diyang midwestkompleks (Amerikadi Serikat)malam hari"]]

Sejumlah program menggunakan [[model teks-ke-gambar]] untuk membuat berbagai variasi gambar berdasarkan perintah teks yang beragam. Diantaranya [[EleutherAI]] VQGAN+CLIP yang dirilis pada tahun 2021,<ref name="adafruitVQGANCLIP">{{Cite web|last=Burgess|first=Phillip|title=Generating AI "Art" with VQGAN+CLIP|url=https://learn.adafruit.com/generating-ai-art-with-vqgan-clip|website=[[Adafruit]]|access-date=July 20, 2022}}</ref> [[OpenAI]] DALL-E yang merilis sebuah seri gambar pada Januari 2021, [[Google]] Brain Imagen dan Parti yang diumumkan pada Mei 2022, [[Microsoft]] NUWA-Infinity,<ref>{{Cite web|title=NUWA-Infinity|url=https://nuwa-infinity.microsoft.com/#/|website=nuwa-infinity.microsoft.com|access-date=2022-08-10}}</ref><ref>{{Cite news|last=Vincent|first=James|date=May 24, 2022|title=All these images were generated by Google's latest text-to-image AI|url=https://www.theverge.com/2022/5/24/23139297/google-imagen-text-to-image-ai-system-examples-paper|work=The Verge|publisher=Vox Media|access-date=May 28, 2022}}</ref> dan [[Stable Diffusion]] yang dirilis pada Agustus 2022.<ref name="technologyreview">{{Cite web|last=Heikkilä|first=Melissa|date=16 September 2022|title=This artist is dominating AI-generated art. And he's not happy about it.|url=https://www.technologyreview.com/2022/09/16/1059598/this-artist-is-dominating-ai-generated-art-and-hes-not-happy-about-it/|website=MIT Technology Review|access-date=2 October 2022}}</ref><ref>{{Cite web|date=15 September 2022|title=Stable Diffusion|url=https://github.com/CompVis/stable-diffusion|publisher=CompVis - Machine Vision and Learning LMU Munich|access-date=15 September 2022}}</ref> Stability.ai mempunyai sebuah antarmuka Stable Diffusion yang disebut DreamStudio.<ref name="venturebeatai">{{Cite news|date=18 October 2022|title=Stable Diffusion creator Stability AI accelerates open-source AI, raises $101M|url=https://venturebeat.com/ai/stable-diffusion-creator-stability-ai-raises-101m-funding-to-accelerate-open-source-ai/|work=VentureBeat|access-date=10 November 2022}}</ref> Stable Diffusion adalah perangkat lunak dengan sumber tersedia, yang mendukung pengembangan plugin untuk [[Krita]], [[Adobe Photoshop|Photoshop]], [[Blender (perangkat lunak)|Blender]], dan [[GIMP]],<ref name="Choudhary">{{Cite web|last=Choudhary|first=Lokesh|date=23 September 2022|title=These new innovations are being built on top of Stable Diffusion|url=https://analyticsindiamag.com/these-new-innovations-are-being-built-on-top-of-stable-diffusion/|website=Analytics India Magazine|access-date=9 November 2022}}</ref> juga antarmuka berbasis web [[sumber terbuka]] Automatic1111.<ref>{{Cite news|last=Dave James|date=27 October 2022|title=I thrashed the RTX 4090 for 8 hours straight training Stable Diffusion to paint like my uncle Hermann|url=https://www.pcgamer.com/nvidia-rtx-4090-stable-diffusion-training-aharon-kahana/|work=PC Gamer|language=en|access-date=9 November 2022}}</ref><ref>{{Cite web|last=Lewis|first=Nick|date=16 September 2022|title=How to Run Stable Diffusion Locally With a GUI on Windows|url=https://www.howtogeek.com/832491/how-to-run-stable-diffusion-locally-with-a-gui-on-windows/|website=How-To Geek|access-date=9 November 2022}}</ref><ref name="atsmooth">{{Cite news|last=Edwards|first=Benj|date=4 October 2022|title=Begone, polygons: 1993's Virtua Fighter gets smoothed out by AI|url=https://arstechnica.com/gaming/2022/10/begone-polygons-1993s-virtua-fighter-gets-smoothed-out-by-ai/|work=Ars Technica|language=en-us|access-date=9 November 2022}}</ref>