Image created with gemini-2.5-flash-image with claude-sonnet-4-5-20250929. Image prompt: A cinematic photograph of a classic film camera on a modern slate grey table, focused on a small birthday cake with two glowing candles, surrounded by suspended colorful film strips and confetti in mid-air, dramatic lighting with deep blue shadows and rich red highlights, high contrast, stylish and joyful composition celebrating two years of motion and storytelling.
Veo is a more general reasoner than you might think. Check out this super cool paper on “”Video models are zero-shot learners and reasoners”” from my colleagues at @GoogleDeepMind. https://x.com/tkipf/status/1971063116734841248
SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views”” TL;DR: feed-forward framework for 3DGS from sparse unposed views; predicts Gaussians + poses, enforces geometry via reprojection, SOTA novel view synthesis, even in extreme settings.”” https://x.com/Almorgand/status/1970910944948781195
Nvidia just released Lyra on Hugging Face Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation TL;DR: Feed-forward 3D and 4D scene generation from a single image/video trained with synthetic data generated by a camera-controlled video diffusion model https://x.com/_akhaliq/status/1970949464606245139
Meta scrapping Unity to build their own game engine (Horizon Engine) is really interesting. I doubt it has as much to do with the Unity tax and more so to allow them to vertically integrate with all their own layers of ~SOTA AI starting with gaussian splatting”” / X https://x.com/nearcyan/status/1968475789021852075
Introducing Vibes: A New Way to Discover and Create AI Videos https://about.fb.com/news/2025/09/introducing-vibes-ai-videos/
Multi-camera shot generation will be a button in every video editor https://x.com/bilawalsidhu/status/1970018366124618077
This is Ray3. The world’s first reasoning video model, and the first to generate studio-grade HDR. Now with an all-new Draft Mode for rapid iteration in creative workflows, and state of the art physics and consistency. Available now for free in Dream Machine. https://x.com/LumaLabsAI/status/1968684330034606372
Veo 3 = Zero-shot video reasoner • Trained on web-scale video, shows broad zero-shot skills (perception → physics → manipulation → reasoning) • New “Chain-of-Frames” reasoning = visual analogue of CoT • Big jump Veo2 → Veo3: edits, memory, symmetry, mazes, analogies • https://x.com/arankomatsuzaki/status/1971042970800701809
What used to take hours in After Effects now takes just ONE prompt. Nano Banana, Seedream 4, Wan 2.2, Runway Aleph et al are pioneering instruction-based editing — collapsing complex VFX pipelines into a single, implicit step. Here’s everything you need to know in 10 mins: https://x.com/bilawalsidhu/status/1970915228536947026
Runway Research | Autoregressive-to-Diffusion Vision Language Models
https://runwayml.com/research/autoregressive-to-diffusion-vlms
Today we’re sharing our first research work exploring diffusion for language models: Autoregressive-to-Diffusion Vision Language Models We develop a state-of-the-art diffusion vision language model, Autoregressive-to-Diffusion (A2D), by adapting an existing autoregressive vision https://x.com/runwayml/status/1970866494729781623
👏We are proud to share that in an internal blind test, where professionals evaluated pairwise comparisons using a win/loss ratio benchmark, the Kling AI 2.5 Turbo model significantly outperformed Seedance 1.0, Veo 3 Fast, and Seedance 1.0 Mini in both text-to-video and https://x.com/Kling_ai/status/1970832920085753893
Introducing: Hyperscape Capture 📷 Last year we showed the world’s highest quality Gaussian Splatting, and the first time GS was viewable in VR. Now, capture your own Hyperscapes, directly from your Quest headset in only 5 minutes of walking around. https://x.com/JonathonLuiten/status/1968474776793403734
Meshcapade can now pull apart both 3D camera tracking + human pose estimation data. Effectively like Wonder Dynamics / Autodesk Flow Studio at this point. Useful AI model for 3D artists and as an input into video-to-video workflows. https://x.com/bilawalsidhu/status/1969458783480135711
I don’t want much. I just want nano banana for video. And i’m sure I’ll get soon :-)”” / X https://x.com/bilawalsidhu/status/1968732880244228490
YouTube is drowning in AI slop. https://x.com/TheHumanoidHub/status/1970899129082802271
Decart has dropped their first version of Nano Banana for video. Image editing is fun, but I really love instruction-based video editing. Feels like going from photoshop —> blender + after effects. https://x.com/bilawalsidhu/status/1968923439369994586
Microsoft introduces Latent Zoning Network (LZN) A unified principle for generative modeling, representation learning, and classification. LZN uses a shared Gaussian latent space and modular encoders/decoders to tackle all three core ML problems at once! https://x.com/HuggingPapers/status/1970218823140687885
🔥 We adapt powerful yet sequential autoregressive vision-language models for parallel diffusion decoding in my summer @runwayml internship! 👇(1/4) https://x.com/mariannearr/status/1970936677922382335
Towards a Physics Foundation Model Proposes GPhyT (General Physics Transformer), a large transformer trained on 1.8 TB of simulation data across fluid flows, shock waves, heat transfer, and multiphase dynamics. Here are a few key notes: https://x.com/omarsar0/status/1968681177189077366
⚡ Introducing Kling AI 2.5 Turbo Video Model! Next-Level Creativity, Turbocharged! Now at Even Lower Price! — From Kling AI Creative Partner @Wildpusa https://x.com/Kling_ai/status/1970439808901362155
🎉 Meet the official judging panel of the Kling AI NextGen Creative Contest! 🙌 This is your opportunity to showcase your talent in front of these world-renowned creative visionaries: 🎨 Tim Yip | Oscar-Winning Art Director 🎬 LEE Hwan-kyung | Film Director & Screenwriter 🚀 Eric https://x.com/Kling_ai/status/1970783972033445965
🚨 Kling 2.5 now live on fal – day 0 access! 🎬 Dramatically improved dynamic quality 🎨 Breakthrough composition aesthetics 🎭 Enhanced style adaptation (2D anime support) 👤 Improved subject response & emotional expression https://x.com/fal/status/1970404272551367009
A major moment – UNLIMITED Kling 2.5 exclusively inside Higgsfield. Live now. Day-0 access. A reasoning engine powers a video creation model, in one system. Higgsfield thinks, Kling creates. Retweet in 4 hours to receive 50 credits via DM. https://x.com/higgsfield_ai/status/1970456455473168437
Luma Labs has launched Ray 3, the first video model with 16-bit HDR support, and a significant upgrade over their Ray 2 model Using a chain-of-thought approach, Ray 3 iterates on video generations, analyzing them at each step to ensure a quality bar and prompt adherence is met. https://x.com/ArtificialAnlys/status/1970546709890768993
Nice. Kling 2.5 Turbo is a really strong model and at $0.35 for a 5s video on FAL is cheap enough to use for personal experiments. I’ve been using this prompt to test video models for a while and this is one of the best outputs. https://x.com/TomLikesRobots/status/1970418753533096418
Pretty wild to see the demographic split on YouTube based on the niche you’re in. Left (my vfx channel) vs. Right (my ai channel) https://x.com/bilawalsidhu/status/1970514756944699515
We are building “Open Source Nano Banana for Video” – here is open source demo v0.1 We are open sourcing Lucy Edit, the first foundation model for text-guided video editing! Get the model on @huggingface 🤗, API on @FAL, and nodes on @ComfyUI 🧵 https://x.com/DecartAI/status/1968769793567207528
Movie Studio Lionsgate is Struggling to Make AI-Generated Films With Runway | PetaPixel https://petapixel.com/2025/09/23/movie-studio-lionsgate-is-struggling-to-make-ai-generated-films-with-runway/
