Joshua Xu (@joshua_xu_)
HeyGen이 'Video Agent v2'를 출시(배포)했다고 공지한 트윗입니다. 커뮤니티에서 제작한 샘플 영상들을 소개하며, 6개의 클립이 약 5분 안에 만들어졌다고 밝히는 등 사용성·속도 측면의 개선이나 업데이트를 알리는 내용입니다.
#generativevideo
Попалась как-то раз мне 1 нейронка, которая генерит мокьюментари (в хорошем смысле) из GPT-текста, нейронной TTS и стоковых видео (пре-рендеренных):
ai InVideo io
Делает видосы понятно и человечно, правда, глючит иногда, как и все нейронки, но зато позволяет рендерить что хочешь: от пафосной документалки до лёгкого триллера (но, разумеется, PUSCA-фильтр может сработать, так что не увлекайтесь)
#Generative #AI #Video #GPT #TTS #Документальный #Фильм #Диктор #GenerativeAI #AIVideo #GPT4 #TextToSpeech #VoiceOver #DocumentaryFilm #Narrator #AIVoice #GenerativeVideo #AIContent #DocuAI #FilmNarration
el.cine (@EHuanglu)
Higgsfield의 'unlimited Kling AI'를 사용하면 이전에 대규모 스태프와 며칠이 걸리던 촬영 작업을 초단위로 대체할 수 있다는 식의 혁신적 비디오 제작 사례를 소개합니다. 할리우드 수준의 제작 워크플로를 크게 바꿀 가능성이 있는 실용적 데모를 제시합니다.
Dream Lab LA (@DreamLabLA)
콘텐츠 아티스트 Jack Fishkin이 LumaLabsAI의 Dream Machine 기능 'Ray3 Modify'를 사용해 영화적 은행 강도 장면 'Men at Work'을 제작. Tamara Bruketta, Jo Beth Locklear, Bronte Cooper가 출연하며 생성 영상(creative AI) 활용 사례로 주목됨.
Generative Video Drops! Kling 2.6, o1, & NEW Models!
The generative video war heats up as Kling 2.6 and OpenAI’s latest models deliver cinematic quality that was impossible just months ago.
#Kling #OpenAI #GenerativeVideo #AIArt #VideoTech #Innovation
https://www.technology-news-channel.com/generative-video-drops-kling-2-6-o1-new-models/
Coca‑Cola’s holiday spot tries AI, but it feels stuck beside OpenAI’s Sora and Google’s Veo—cutting‑edge generative‑video that makes deep‑fakes look effortless. What does this say about brand tech? Dive into the comparison and see why the soda ad looks dated. #CocaColaAI #OpenAISora #GoogleVeo #GenerativeVideo
🔗 https://aidailypost.com/news/cocacolas-ai-holiday-ad-looks-dated-next-openais-sora-googles-veo
Adobe Firefly Image 5 brings support for layers, will let creators make custom models
You can see several butterfly shaped clusters emerge over the video. I think that means that some of the meaning from the training data was successfully imbued into motionnet, as SDXL was only invoked on frame 1. I wonder what will happen when trained on a bigger video corpus and when the SDXL piece of the pipeline is fleshed out!
#AI #python #torch #video #videocodec #codec #artificialintelligence #aivideo #generativeai #generativevideo #generativecodec
Sora 2 AI is making disturbing Martin Luther King Jr. videos and it needs to stop
https://web.brid.gy/r/https://nerds.xyz/2025/10/sora-2-ai-martin-luther-king-jr/
Sora 2 OpenAI: 3 Revolutionary Features Bringing Sound to AI Video
Sora 2 OpenAI officially launched on September 30, 2025, focusing on integrated audio and realistic human motion.https://www.olamnews.com/technology/ai/2735/sora-2-openai-realistic-audio-features/
Hold onto your algorithms! Google is bringing Veo 3 to YouTube Shorts, meaning anyone can now generate videos with AI. The 'AI takeover' is getting a turbo boost, and frankly, I'm just here for the inevitable absurdities.
What's the first thing you'd ask an AI to create for a YouTube Short?
#AI #YouTubeShorts #GenerativeVideo #TechHumor #DigitalContent
https://www.cnet.com/tech/services-and-software/the-ai-takeover-of-youtube-is-about-to-get-supercharged/#ftag=CAD590a51e
15 Mind-Blowing Interactive Worlds Google’s Genie 3 AI Can Create https://petapixel.com/2025/08/06/15-mind-blowing-interactive-worlds-googles-genie-3-ai-can-create/ #artificialintelligence #generativevideo #generativeai #googlegenie3 #googlegenie #interactive #Technology #Software #google #genie #video #News #ai
Google Gemini Can Now Turn Photos Into Videos https://petapixel.com/2025/07/10/google-gemini-can-now-turn-photos-into-videos/ #artificialintelligence #generativevideo #generativeai #googlegemini #Technology #googleveo3 #gemini #google #News #veo3 #veo #ai
@WPP's T&Pm used @microsoft #AzureOpenAI and the #Sora video generation model to bring early creative concept to life and streamline the creation of high-quality, personalized video content at scale https://www.microsoft.com/en/customers/story/24274-wpp-azure-openai
Higgsfield AI 2025: Filmkunst neu gedacht!
• Über 50 Kameraeffekte
• Video aus jedem Bild
• Regie-Tools für Kreative
#ai #ki #artificialintelligence #HiggsfieldAI #GenerativeVideo #CinematicAI
Jetzt LIKEN, teilen, LESEN und FOLGEN! Schreib uns in den Kommentaren!
Blur Nacht
Blur Nacht
Blur series
2025
Generative videos
Computer, specific program
Duration infinite
Size variable
The world is blurry, the mind is blurry, the human being is blurry, but despite this blurriness, we perceive, we make sense, we create meaning, we act, we live. How to survive in a blurred world ?
The Blur series of generative video explores blurring as a way to interrogate the relationship between perception, mind and artworks in movement.
#generativeart #generativevideo #generative #noAI #blur #blurry #blurryart
Blur_Nacht (Recording)
OpenAI makes AI video generator Sora publicly available in US;
Firm announces tool that can create AI video clip based on user’s written prompts will be available to anyone in the US
https://www.theguardian.com/technology/2024/dec/09/openai-ai-video-generator-sora-publicly-available
#news #technology #ArtificialIntelligence #AI #GenerativeVideo
Adobe Firefly Turns Text or Images Into Realistic AI-Generated Video https://petapixel.com/2024/09/11/adobe-firefly-turns-text-or-images-into-realistic-ai-generated-video/ #artificialintelligence #adobefireflyvideo #generativevideo #adobefirefly #generativeai #texttovideo #Technology #Software #adobe #News #ai
#Generativevideo models powered by #AI can recreate moments you’ve experienced but lack video footage for. With well-crafted prompts, these can models generate scenes that you have seen and want to share #genai #generativeart
Client Info
Server: https://mastodon.social
Version: 2025.07
Repository: https://github.com/cyevgeniy/lmst