Today in Generative Media

Amazon's AI image model; HeyGen's avatars & funding; SI's use of AI infuriates staff

• Amazon joins AI image creation fray with new model (The Verge)

• AI Video Startup HeyGen Launches Near-Instant Avatar Generator, Adds $5.6 Million In Funding (Forbes)

• Sports Illustrated’s use of AI infuriates a staff already in turmoil (Washington Post)

• Stability AI Explores Sale as Investor Urges CEO to Resign (Yahoo Finance)

• Stable Diffusion XL Turbo can generate AI images as fast as you can type (Ars Technica)

• Introducing llamafile (Mozilla)

• Generative AI can easily be made malicious despite guardrails, say scholars (ZDNet)

• World’s first AI minister likens risk of overregulation to calligraphers that kept the printing press out of the Middle East for nearly 200 years (Fortune)

• Microsoft Paint’s OpenAI-powered ‘Cocreator’ image generator is here (The Verge)

• AI can now recreate a website's code from just a screenshot (Creative Bloq)

• Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer (project page)

• Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models (project page)

• Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation (project page)

• LEDITS++: Limitless Image Editing using Text-to-Image Models (project page)

• DiffusionMat: Alpha Matting as Sequential Refinement Learning (project page)

• Generative Models: What do they know? Do they know things? Let's find out! (project page)

• Surf-D: High-Quality Surface Generation for Arbitrary Topologies using Diffusion Models (project page)

• Wired Perspectives: Multi-View Wire Art Embraces Generative AI (project page)

• HiDiffusion: Unlocking High-Resolution Creativity and Efficiency in Low-Resolution Trained Diffusion Models (arXiv)

• 🎥 Video AI is now live for everyone on PhotoAI.com (X)

• My workflow combining different AI tools to create full 3D animated movies! (X)

• Midjourney images upscaled with Magnific AI 🪄 (X)

• SDXL Turbo passed to SD15 for refinement (X)

• LaVie: Text-to-Video generation Gradio demo is out on HuggingFace (X)

• Added direct area capture to the real time LCM custom node for ComfyUI! (X)

• Generate tikz code for an object using GPT-4 → render the image → use GPT4-V to get feedback on the image and improve tikz code → repeat! (X)

• Now that ChatGPT has vision and DALL·E in the same context it can generate avatars 😁 (X)