The Heist – YouTube
“🎥 AKiRa provides control over camera motion and optics (focal length, distortion, aperture) in video diffusion, enabling cinematic effects like fisheye, focus shifts, and dolly zoom. 📄 Paper:
https://x.com/xiwang92/status/1870441194959831531
“We’re excited to announce that HunyuanVideo from @TXhunyuan, the groundbreaking 13B open-source video model, is now natively supported in ComfyUI! It is shipped with unified Image and video generative structure. Check out some of the amazing examples!
https://x.com/ComfyUI/status/1870137963193217172
“🎉We’re excited to introduce the KLING AI 1.6 Model: With this update, we have significantly improved the response to prompt, the visual aesthetics, and the physical actions, hoping to bring more consistent and vivid results!🔥 💡What’s new: 1. New KLING AI 1.6 Model: -Improved
https://x.com/Kling_ai/status/1869599147046871488
“veo 2 is very good with photorealistic animals –pretty good consistency across shots; but not perfect. after the cut notice this: the headphones & glasses and drink stay the same — but the cocktail umbrella changes color from red to green.
https://x.com/bilawalsidhu/status/1870926361445163083
“Pika 2.0 is pretty lit
https://x.com/bilawalsidhu/status/1870697475809677439
“Slow down! Playing with the latest Kling 1.6
https://x.com/jamesyeung18/status/1869738357586358356
“Training-free Video Enhancement: Achieved 🎉 Nice work with @oahzxl @shaowenqi126301 @VictorKaiWang1 @VitaGroupUT @YangYou1991 et al. Non-trivial enhancement, training-free, and plug-and-play 🥳 Blog:
https://x.com/YangL_7/status/1870116980717695243
Google (Veo)
“Check out ‘Dogtective.’ Having a little fun with my downtime today, dreaming with Google Veo 2 text-to-video. Blown away by the prompt coherence. This is one powerful AI tool. I hope everyone is enjoying their Holiday break!
https://x.com/Diesol/status/1872021222495863042
“Google Veo prompt: “British chef slices and reveals a Beef Wellington”
https://x.com/bilawalsidhu/status/1869599748392653125
“Google announced the release of Veo 2, a SOTA video generation model that creates high-res outputs The model can generate 8-second clips at 4K resolution (720p at launch) and is rolling out gradually through the VideoFX waitlist
https://x.com/adcock_brett/status/1870877776133214577
Luma
“Introducing the idea multiverse. The only limit is your imagination. How far down the rabbit hole will you go? #DreamMachine #ConceptPills
https://x.com/LumaLabsAI/status/1869760502739681565
