Image created with GPT Image 1. Image prompt: fragmented marble cherub statue in neon pink and teal, Technique pastel palette, minimalist graphic design inspired by New Order’s ‘Technique’, metaphor for streaming frame ribbons, flat color, subtle texture, 1980s Saville typography style
Gemini 2.5 Pro (05-06) is SOTA at most video understanding tasks (by a large margin) 📽️. Lots of work by the Gemini multimodal team to make this happen, excited to see developers push this capability in new ways. More details below! https://x.com/OfficialLoganK/status/1920863634374172853
Advancing the frontier of video understanding with Gemini 2.5 – Google Developers Blog https://developers.googleblog.com/en/gemini-2-5-video-understanding/
BTW, Gemini one shotted these chapter summaries w/amazing accuracy. I just pointed it at the yt video. First time I’ve seen a model do this https://x.com/HamelHusain/status/1922119981526880515
🎥 @higgsfield_ai Hollywood-Level Videos from a Single Image Uses 50+ pro-level camera moves — from bullet time to crash zooms, robo arms, and FPV chases — to turn static images into cinematic videos Some beutiful examples.. 🧵 1/n – 3D Rotation The subject or product spins https://x.com/rohanpaul_ai/status/1922241875089543546
Hamlet II: The Return of Ophelia (I am surprised at how well Veo 2 worked in animating Sir John Everett Millais painting off a text prompt, and how much consistency there was in the water and flowers. https://x.com/emollick/status/1921752765769908457
Lovart | The World’s First Design Agent
https://www.lovart.ai/
Creativity unleashed! https://x.com/lovart_ai/status/1921958554312831133
I built an 8-bit retro dashboard in 10 minutes using: – @nextjs – @shadcn – @v0 – 8bitcn ⚔️ Watch the full video below 👇 https://x.com/theorcdev/status/1915716377194660120
Introducing AI Alive: Bringing Your Photos to Life on TikTok Stories – Newsroom | TikTok https://newsroom.tiktok.com/en-us/introducing-tiktok-ai-alive
It’s fun to see all the new uses cases coming up with this latest References update. Feels like Christmas but every day. Here is zero-shot novel view synthesis for people and characters, works straight out of the box. https://x.com/c_valenzuelab/status/1922656353354412332
UC Berkeley researchers announced VideoMimic, a real-to-sim-to-real pipeline that trains robots with mobile videos It mines videos, reconstructs the humans and the environment, and produces policies for humanoids, enabling skills like climbing stairs https://x.com/adcock_brett/status/1921597176028733566
If you’re a good data engineer, or an engineer who loves looking at data creating datasets for games, video, images, audio, text … please send me a message here or on LinkedIn. We still have plenty of data jobs at @MicrosoftAI – but hurry 😅”” / X https://x.com/NandoDF/status/1922362860820165019
Tencent released HunyuanCustom, an open-source AI system for video generation — powered by HunyuanVideo-13B It generates customized video from text, images, audio, and video inputs with consistent subjects Outperforms open-source rivals! https://x.com/rowancheung/status/1921815682540343488
This Canadian pharmacist is key figure behind world’s most notorious deepfake porn site https://www.cbc.ca/amp/1.7527626
There’s nothing quite like throwing on a VHS filter with some camera shake to really throw off everyone’s “”is this real or fake”” detector — works every damn time.”” / X https://x.com/bilawalsidhu/status/1920923430699823376
Video Understanding! 📽️ Gemini 2.5 Pro (05-06) is changing on how we will work with videos! You can now share recordings of videos on what the model should change in your code or process up to 6 hours in a single request (‘lower resolution’). 😮 TL;DR: 🏆 Gemini 2.5 Pro achieves https://x.com/_philschmid/status/1921838835735867533
Kling 2.0 is now the leading Image-to-Video Model, surpassing Veo 2 and Runway Gen 4 in the Artificial Analysis Video Gen Arena! Kling 2.0 is the latest video model by Kuaishou, who’s Kling 1.6 Pro had previously been leading the Image to Video Leaderboard. Kling 2.0 also excels https://x.com/ArtificialAnlys/status/1922299716051796148
Runway References for zero-shot testing of clothes, locations, and poses https://x.com/c_valenzuelab/status/1922742658620903885
LTXV https://ltxv.video/
Think of References in @runwayml as ingredients you can mix and ask for any combination possible. A near-realtime machine for making anything. Also, what a nice goal. https://x.com/c_valenzuelab/status/1921356668027249126
We trained Gen-4 References as a general-purpose model. It has infinite workflows that are yet to be discovered, which makes it really interesting because you don’t need any sort of fine-tuning or customization to make it do what you want. Just ask for it.”” / X https://x.com/c_valenzuelab/status/1921583557333389637
