Tag
A retired person shows his MS Paint paintings to AI for feedback, and the AI invents an entire fake art movement with critics, manifestos, and legal defenders, which Google now recognizes as real.
Elon Musk announces that Grok can be used for prototyping game assets directly.
The author reflects on how AI-generated art challenges traditional notions of artistic value, questioning whether beauty alone suffices and whether the human intent behind AI-assisted art matters.
This study analyzes 130,882 images from 368 Artbreeder 'remix parties' over 13 months, finding that collective human-AI co-created images become simpler and converge toward common thematic attractors, while users paradoxically prefer to remix less novel images despite novelty producing more engaged children.
User tested Grok's image generation function and found that the first time it successfully generated a complete image, but the second time it missed part of the prompt content, resulting in an incomplete generation.
The author presents the second installment of a series featuring 3D cultural relics of the Twelve Bronze Heads of Yuanmingyuan, created using AI image generation (Image 2.0) and 3D modeling tools (Tripo). The goal is to promote Chinese culture on platform X, viewing the combination of AI and Chinese culture as a path to national rejuvenation and cultural confidence.
A webcam-style art project features Emily, an AI girl living in a Tokyo apartment who ages and will die within three years, challenging viewers to contemplate existence, awareness, and mortality without interaction.
An X user posted an actual Monet painting as AI-generated art and asked for critiques, exposing how eager critics are to find flaws in AI art even when it's genuine.
A Twitter user posted a genuine Claude Monet painting, falsely claiming it was generated by AI.
Image 2.0 has launched on ChatGPT, offering dramatically improved image generation capabilities. The update enables handling of much more complex compositions, including 10x the complexity of previous grids, with near-perfect results.
This Hugging Face repository provides workflows and model downloads for Lightricks' LTX-2.3 video generation model, designed for use with ComfyUI, including split models, GGUF versions, and required custom nodes.
Animator Lyndon Barrois discusses how OpenAI's Sora video generation tool enables creators to bypass traditional studio processes and bring imaginative visions to life independently.
OpenAI shares first impressions of Sora from visual artists, filmmakers, and creative directors who used the text-to-video model in their workflows, highlighting its ability to bring surreal and previously impossible ideas to life. Featured creators include shy kids, Paul Trillo, Nik Kleverov, and August Kamp.
OpenAI introduces Outpainting for DALL·E, enabling users to extend generated or uploaded images to create large-scale images in any aspect ratio while maintaining visual consistency with shadows, reflections, and textures.
The article highlights the emerging scene of AI-generated art using OpenAI's CLIP model as a steering mechanism for generative models, showcasing various examples of text-to-image outputs.
A guide to building a camera that uses AI to alter the view in real-time, such as turning the world into cheese, leveraging OpenAI's image generation technology.