Adaptive Caching for Faster Video Generation with Diffusion Transformers
https://adacache-dit.github.io/
“🎉Excited to introduce our latest work, LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity! ✨For the first time, we demonstrate high-resolution 68-second video generation at 16fps on a single GPU— without relying on
https://x.com/HongjieWang3/status/1868474506760560889
“@karpathy Two reasons why video progresses faster than text. 1) Signal per compute. Images have rich structure so you can process much more signals per computation, while text is discrete and even for a single dumb token it takes lot of flops. In 2015 I didn’t choose to work on NLP” / X
https://x.com/shaneguML/status/1868804945295949832
Google (Veo)
“Google just released Veo 2, a new state-of-the-art AI video model. In testing, Veo beat OpenAI Sora in BOTH quality and prompt adherence. The video compilation below is 100% created by AI (more details in thread):
https://x.com/rowancheung/status/1868703589520359905
Google debuts new AI video generator Veo 2 claiming better audience scores than Sora | VentureBeat
Google debuts new AI video generator Veo 2 claiming better audience scores than Sora
“BREAKING: Google just dropped Veo 2 and Imagen 3 — their next gen video and image generation models. Turns out Google’s been closing the gap quietly — not just on LLMs, but on visual creation too. Here’s everything you need to know w/o the hype 🧵
https://x.com/bilawalsidhu/status/1868702809568559390
Veo 2 – Google DeepMind
https://deepmind.google/technologies/veo/veo-2/
“Today, we’re announcing Veo 2: our state-of-the-art video generation model which produces realistic, high-quality clips from text or image prompts. 🎥 We’re also releasing an improved version of our text-to-image model, Imagen 3 – available to use in ImageFX through
https://x.com/GoogleDeepMind/status/1868703624714395907
“”A pair of hands skillfully slicing a ripe tomato on a wooden cutting board” #veo
https://x.com/agrimgupta92/status/1868745017571131582
“Veo 2 prompt: “Eating soup like they do in Europe, the old fashioned way”
https://x.com/bilawalsidhu/status/1869182358454505959
Kling
“Kling 1.6 is amazing! Look at the way it retains the details even at distance, look at the movement of the woman and the tiger, the hair, the chain! This could be a shot from a movieđź‘€I used @javilopen new Mystic Super real model to create the prompt image (see replies). 2025 is
https://x.com/Uncanny_Harry/status/1869075336798912994
Pika
“Pika Labs launched Pika 2.0 It’s the startup’s new image-to-video model that lets you combine characters, objects, clothes, and locations in an AI-generated video
https://x.com/adcock_brett/status/1868341175062593889
“Our holiday gift to you: Pika 2.0 is here. Not just for pros. For actual people. (Even Europeans!) Now available at
https://x.com/pika_labs/status/1867641187898995179
Runway
Runway Talent Network
https://talent.runwayml.com/
