This video has been entirely generated with AI (face and voice) on the last version on Argil AI 🤯 I have known @LaodisOfficial for years, and for the first time, we have reached the point where the difference between going into a studio and using AI is no different. Do you https://x.com/BrivaelLp/status/1890311661241749821
“we just dropped SmolVLM2: world’s smollest video models in 256M, 500M and 2.2B ⏯️🤗 we also release the following 🔥 > an iPhone app (runs on 500M model in MLX) > integration with VLC for segmentation of descriptions (2.2B) > a highlights extractor (2.2B) https://x.com/mervenoyann/status/1892576290181382153
“This video has been entirely generated with AI (face and voice) on the last version on Argil AI 🤯 I have known @LaodisOfficial for years, and for the first time, we have reached the point where the difference between going into a studio and using AI is no different. Do you https://x.com/BrivaelLp/status/1890311661241749821
“Surprise. Google Veo 2 is now available inside the YouTube app! The $0 VFX studio is here. I gave it a test drive; here’s what you need to know: > Wayyyy faster than the standalone version of Veo 2 (likely a distilled model optimized for serving?) > Can use Veo 2 clips as https://x.com/bilawalsidhu/status/1890103127732343253
“The challenge in text-to-video generation lies in achieving high visual quality at high resolutions due to immense computational costs. Single-stage diffusion models require substantial parameters and function evaluations, making high-resolution video generation inefficient. https://x.com/rohanpaul_ai/status/1892179215631499459
“Amazing new open-source text-to-video model just dropped. Image-to-video generation models struggle with synchronizing motion and maintaining realism. Existing diffusion-based models generate high-quality frames but fail in complex physics and logical sequences. Step-Video-T2V https://x.com/rohanpaul_ai/status/1891413622867288100
“Testing Topaz Starlight, their new diffusion-based video upscaling tech to breathe new life into old videos. Candidate #1: My VFX showreel from 2002. The results are…. interesting 🫣 Input vs. Output. More examples below (1/3) https://x.com/bilawalsidhu/status/1890499502899142927
“Image-to-video generation offers limited control over synchronizing camera and object movements in cinematic shots. Current methods lack intuitive and precise control over these intertwined movements, hindering creative expression. This paper proposes MotionCanvas, a system https://x.com/rohanpaul_ai/status/1891406891047104699
“Adobe just launched AI video generator. key features: – generate motion graphics (new in AI world) – text/image to video – Shot size control (close up, wide shot.. ) – Camera angle control (low angle, aerial shot ..) – camera motion control – keyframe link in comment https://x.com/EHuanglu/status/1889726675862098159
“This has Scooby Doo meets Adult Swim energy — and I just knew Kendrick was gonna pop out from somewhere 😂 https://x.com/bilawalsidhu/status/1891530521861116102
““No VFX” these days is more like imperceptible VFX” / X https://x.com/bilawalsidhu/status/1891267370716406065
“We are claiming SOTA for AI Avatar, but the ultimate test is big face. We don’t use post process or blurring hacks to hide misery. 5 videos. Same script. Generate with Argil 👇 https://x.com/BrivaelLp/status/1890435559127986463
“2. Goku+: Product and Human Interaction https://x.com/minchoi/status/1890074266244395495
“Nothing better than user love!! Congrats @HeyGen_Official https://x.com/saranormous/status/1892945844376047679
Min Choi on X: “2. Goku+: Product and Human Interaction https://t.co/KGtK4DPxTw” / X
https://x.com/minchoi/status/1890074266244395495
“Dialing in that “found footage” vibe with OpenAI Sora. Adding a gentle VHS filter hides some of the artifacts while creating that retro aesthetic. https://x.com/bilawalsidhu/status/1891311402352099551
“StepFun open-sources Step-Video-T2V, a SotA 30B text-to-video model – Capable of understanding both Chinese and English prompts – Generates high-quality videos – Featuring strong motion dynamics, high aesthetics, and consistent content https://x.com/arankomatsuzaki/status/1891330624436220069
“ByteDance presents Phantom Subject-consistent video generation via cross-modal alignment https://x.com/_akhaliq/status/1892073250974216476
“Meta presents: Intuitive physics understanding emerges from self-supervised pretraining on natural videos Predicting outcomes in a rep space leads to physics understanding, unlike video prediction in pixel space and MLLMs, which reason through text. https://x.com/arankomatsuzaki/status/1891721882065391692
“Microsoft is preparing to host OpenAI’s GPT-4.5 as early as next week, followed by GPT-5 in late May. GPT-4.5 (codenamed Orion) is OpenAI’s last non-chain-of-thought model, while GPT-5 will integrate OpenAI’s o3 reasoning model, aiming for a more unified AI experience. These https://x.com/rohanpaul_ai/status/1892738219055120486
“I built tiktok to discover top tech people using @v0 🙂 Check out the demo! 👇 Reply or send me a DM with your feedback. All feedback is welcomed 🙂 https://x.com/vixclotet/status/1888692170825351243
“StepFun open-sources Step-Video-T2V, SOTA 30B text-to-video model Step-Video-T2V 544px992px204frame Step-Video-T2V-turbo 544px992px136frame 80G VRAM needs🤪 https://x.com/bdsqlsz/status/1891348664460714425?s=46
“NEW: @StepFun_ai dropped a 30B text to video model – capable of generating upto 204 frames! – MIT licensed 🔥 They also release a Turbo model (distilled) for faster inference! ⚡️ https://x.com/reach_vb/status/1891415982003949726
“MaskFlow: Discrete Flows for Flexible and Efficient Long Video Generation CompVis lab introduces MaskFlow, a chunkwise autoregressive approach to long video generation that uses frame-level masking and confidence-based heuristic sampling to produce seamless, high-quality video https://x.com/iScienceLuvr/status/1891726104991502786
“this looks insane, snapchat just dropped Dynamic Concepts Personalization from Single Videos propose a new technique for personalizing text-to-video models, enabling them to capture, manipulate and combine Dynamic Concepts. https://x.com/_akhaliq/status/1892782271763034385
“Today we’re launching Pikaswaps: replace anything in your videos using photos you upload, or scenes you describe. The results are unbelievably believable, and the possibilities are as unlimited as your imagination. Try it at Pika dot art https://x.com/pika_labs/status/1892620122818294109
fal Raises $49M Series B to Power the Future of AI Video https://blog.fal.ai/fal-raises-49m-series-b-to-power-the-future-of-ai-video/
