The Current State of AI Generated Art (Patreon)

The Current State of AI Generated Art

The current state of AI generated art as of mid 2022. #dalle2, #midjourney, #discodiffusion and many other text to image synthesis included. Special thanks - FlaminCat - Gandamu BYCLOUD AI Art Competition [Details] https://docs.google.com/document/d/1x1efjd9jSK9cF394VD2Wo0tdGM2ywJO9TvQYqypFLGA/edit?usp=sharing [Submission Link] https://forms.gle/vuzByaNwY46idq5Z9 To stay on top of the latest AI art Colabs: https://pharmapsychotic.com/tools.html All Projects/Research in order of Appearance: DeepDream: Inceptionism [Blog] https://ai.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html Style Transfer: Image Style Transfer Using Convolutional Neural Networks [GitHub] https://github.com/Kautenja/a-neural-algorithm-of-artistic-style GAN - Generative Adversarial Network [Paper] https://arxiv.org/abs/1406.2661 StyleGANs [StyleGAN GitHub] https://github.com/NVlabs/stylegan [StyleGAN 2 GitHub] https://github.com/NVlabs/stylegan2 [StyleGAN 3 GitHub] https://github.com/NVlabs/stylegan3 DALL-E: Creating Images from Text [Blog] https://openai.com/blog/dall-e/ CLIP: ConnectingText and Images [Blog] https://openai.com/blog/clip/ VQGAN+CLIP [Colab] https://colab.research.google.com/drive/1L8oL-vLJXVcRzCFbPwOoMkPKJ8-aYdPN#scrollTo=CppIQlPhhwhs [Paper] https://arxiv.org/abs/2204.08583 The Big Sleep [GitHub] https://github.com/lucidrains/big-sleep DeepDaze [GitHub] https://github.com/lucidrains/deep-daze Guided Diffusion (I showed the wrong paper on the video at 7:45) [Paper] https://arxiv.org/pdf/2110.02711.pdf CLIP Diffusion [256x256 Colab] https://colab.research.google.com/drive/12a_Wrfi2_gwwAuN3VvMTwVMz9TfqctNj [512x512 Colab] https://colab.research.google.com/drive/1V66mUeJbXrTuQITvJunvnWVn96FEbSI3 Disco Diffusion [v5.2 Colab] https://colab.research.google.com/github/alembics/disco-diffusion/blob/main/Disco_Diffusion.ipynb [Community Discord] https://discord.gg/msEZBy4HxA [User Guide] https://docs.google.com/document/d/1l8s7uS2dGqjztYSjPpzlmXLjl5PM3IGkRWI3IiCuK7g/edit Harmeet's Modifiers Research [Blog] https://weirdwonderfulai.art/resources/disco-diffusion-modifiers/ JAX Diffusion [Colab] https://colab.research.google.com/github/huemin-art/jax-guided-diffusion/blob/v2.7/Huemin_Jax_Diffusion_2_7.ipynb Latent Diffusion [Paper] https://arxiv.org/pdf/2112.10752.pdf Centipede Diffusion [v3.1 Colab] https://colab.research.google.com/github/Zalring/Centipede_Diffusion/blob/main/Centipede_Diffusion.ipynb DALL-E 2: Hierarchical Text-Conditional Image Generation with CLIP Latents [Blog] https://openai.com/dall-e-2/ [Early Access Waitlist] https://labs.openai.com/waitlist GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models [Paper] https://arxiv.org/pdf/2112.10741.pdf CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers [Paper] https://arxiv.org/abs/2204.14217 [GitHub] https://github.com/THUDM/CogView2 ru-DALLE [GitHub] https://github.com/ai-forever/ru-dalle MidJourney [Official Twitter] https://twitter.com/midjourney?s=20&t=Yv6-R-ybQJIRCoqKAH15GA [Beta Waitlist] bit.ly/3J2NNVs Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding [Blog] https://imagen.research.google/ Flamingo: Tackling multiple tasks with a single visual language model [Blog] https://www.deepmind.com/blog/tackling-multiple-tasks-with-a-single-visual-language-model This video is supported by the kind Patrons & YouTube Members: 🙏Andrew Lescelius, Panther Modern, 正毅 水野, Jake Disco, Demilson Quintao, Tony Jimenez, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Deagan, Mose Sakashita, Miguel, Bandera, Todd, Tono Cabanelas, Gennaro Schiano, 민 태, Chris LeDoux [Discord] https://discord.gg/NhJZGtH [Twitter] https://twitter.com/ytcloud_ [Patreon] https://www.patreon.com/bycloud [PayPal] https://paypal.me/cloudweather [Twitch] https://twitch.tv/bycloudai [Profile & Banner Art] https://twitter.com/pygm7 [Video Editor] https://twitter.com/MishnImpossible [Music 1] OneShot - 11th Hour (Kamex Remix) [Music 2] Astronauts - PowapowaP (Off vocal) [Music 3] OneShot - My Burden is Light Remix [Music 4] Luigi's Mansion Theme - Piano Version [Music 5] Celeste - Alex the Bard [Music 6] Lofi Hollow Knight - City of Tears [Music 7] Lofi Hollow Knight - Greenpath [Music 8] Dj Quads - The Improv [Music 9] elden ring main theme but it's lofi [Music 10] Dark Souls 3 - Abyss Watchers (Lofi/Chillhop Remix) [Music 11] Elden Ring - OST Main Theme Synthwave Remix [Music 12] Celeste: Resurrections Synthjazz Remix - lemonlimebeats 0:00 Intro 1:28 The Stone Age of AI Art 3:06 An Object That Holds THings Together 6:51 Goodbye GAN, Hello Diffusion 7:56 CLIP Diffusion 8:30 Disco Diffusion 10:19 JAX Diffusion 10:58 Latent Diffusion & Centipede Diffusion 12:00 DALL-E 2 13:41 Many other Text to Image Synthesizer 14:18 MidJourney 15:53 Art Competition Announcement 16:42 Discussion, Imagen & Flamingo 17:46 Sponsor 18:44 Outro