コント: 世界を７回救った女 RunwayのCPPになりました！(Thank you Cristóbal Valenzuela and 🍥 Timmy 🍥 !!)ということでAlephをガッツリ使ってその良さを伝えたいと思います。(モバイルでやりました！) この動画、元画像は1個のみ。あとは全部Alephです。

🚨New horror show coming to Showrunner 🚨 Incredibly excited for upcoming horror show 'HEAVEN' We worked with brilliant artist Gizem Akdag as she created the unique style for this new show.

People often ask me how do I vibecode so well? What's my secret? Here I tell it in this exclusive interview -- bookmark it if you agree!

If you're coming to great film producer Jeremy Thomas' talk about Merry Christmas Mr Lawrence, Young Adam, Sexy Beast, The Last Emperor etc Edinburgh International Film Festival tomorrow, a treat: he has curated 40 mins playlist of the great music from his movies. Will be played from 7.50pm. come early!

We are releasing a paper I'm very excited about. We know test-time scaling is a path to greatly improved results, and achieves reasoning in the case of LLMs. We present a new and promising way to amortize it into training using HyperNetworks for image generation models.

Unleash your inner director with Wan2.2! 🎬 From "Long Lens" to "Dutch Angle”, you can control the camera with simple prompts. Your vision, now cinematic. Ready for your director's debut? Watch our crash course & start creating!

🚀 WAN 2.2 Fun Control is wild! Wan ✨ Generate 2 minutes-long videos with next-level AI dancing. 🎥 No need to upload control videos — just drop a clip, and WaveSpeedAI does the magic. Experience effortless video creation: wavespeed.ai/models/wavespe… #AI #AIGeneration

The career interview I did with the great Terence Stamp - he was so enthusiastic about his collaborators, methods, experiences youtu.be/ViJ3BoeS-kQ?si…

🚀 Excited to introduce Qwen-Image-Edit! Built on 20B Qwen-Image, it brings precise bilingual text editing (Chinese & English) while preserving style, and supports both semantic and appearance-level editing. ✨ Key Features ✅ Accurate text editing with bilingual support ✅

This 13-minute fully AI film is about to blow your mind. Created with LTX Studio by Yoav Lutzky. Set in the Kyrgyz steppe, this film explores what happens when the mind meets the unsolvable. Consistent characters. Real storytelling.

Break the Dimension between the human world and AI on the screen. Use your real mobile phone camera to take a photo of your hand + the AI image on the screen. Feed that photo into a convenient video generation tool (I used Wan2.2 locally) #wan #aivideo

Today we're releasing a number of updates and new features to bring even more control, flexibility and speed to your creative workflows within Runway. Learn more below. (1/5)

実写の変換テスト

Today we're adding Voices to Act-Two, giving you even more control and expressiveness within your workflow. With Voices, you can easily change how your performance sounds to better suit your generated character. Learn how with today's Runway Academy.

The first A.I. actor finally gets his story told. We all know Zack Steel — his films are legendary. But only now do we begin to see what he was really going through. #mockumentary #aidocumentary #googledeepmind #veo3

We’re proving WAN 2.2 is worth it. It is now LIVE on Higgsfield. The most advanced open-source model is in Higgsfield for BOTH Video & Image. With 30+ viral presets to go with it. The FASTEST WAN 2.2 ever. Only on Higgsfield. Retweet to get a full guide in DMs. See how →

Lets mix Kpop Demon Hunters and Friends! #KPOPDEMONHUNTERS #kpopdemonhuntersfanart #Friends

Interesting. A Meta/Midjourney partnership. Whatever it looks like, it should accelerate adoption of Gen AI.

Sim Francisco and other simulated cities and worlds will power the Netflix of AI. Your characters will have little lives while you’re not watching…