Veo 3.1 and Sora 2 have a new rival. And it's open source
All the news from the AI world for creators
Good day, Directors
In today’s Newsletter:
1️⃣ There is a new open source contender to Veo 3.1 and Sora 2
2️⃣ Add the voice of Michael Caine to your videos with Elevenlabs
3️⃣ Turn your images into ingredients in Google’s Flow
4️⃣ Disney+ to allow user-generated content via AI
5️⃣ Quick news you may have missed
6️⃣ AI Videos of the Week
Let’s go.
There is a new Open Source contender
LTX-2 is a next-generation, open-source artificial intelligence (AI) model for professional video and audio generation, developed by Lightricks.
There are three key features you should know:
High Quality: It is capable of generating cinematic-quality video in native 4K resolution at up to 50 frames per second (fps).
Synchronized Audio and Video: It generates synchronized dialogue, ambiance, and music along with the video in a single unified process. This is a BIG one, as currently only Veo 3.1 and Sora 2 can do this.
Longer Generations: Users can generate continuous video clips up to 20 seconds long ( 👀 ), which is ideal for creating more complete scenes or narrative moments.
Try it yourself with this prompt for 20 seconds for the video above (feel free to tinker and modify as you need):
Prompt: INT. OVEN – DAY. Static camera from inside the oven, looking outward through the slightly fogged glass door. Warm golden light glows around freshly baked cookies. The baker’s face fills the frame, eyes wide with focus, his breath fogging the glass as he leans in. Subtle reflections move across the glass as steam rises.
Baker (whispering dramatically): “Today… I achieve perfection.”
He leans even closer, nose nearly touching the glass.
“Golden edges. Soft center. The gods themselves will smell these cookies and weep.”
Baker: “Wait—”
(beat)
“Did I… forget the chocolate chips?”
Cut to side view — coworker pops into frame, chewing casually.
Coworker (mouth full): “Nope. You forgot the sugar.”
Quick zoom back to the baker’s horrified face, pressed against the oven door, as cookies deflate behind the glass. Steam drifts upward in slow motion.
pixar style acting and timing
Add the voice of Michael Caine to your videos
Michael Caine and Matthew McConaughey have teamed with the AI audio company ElevenLabs to produce AI replications of their famous voices.
“To everyone building with voice technology: keep going. You’re helping create a future where we can look up from our screens and connect through something as timeless as humanity itself — our voices,” McConaughey says, in an interview with Variety.
Turn your images into high-quality ingredients in Flow
Edit your images with Nano Banana to isolate your subject on a neutral background. This makes a focused, clean ingredient that’s ready to be refined, saved, and dropped seamlessly into the scenes you create.
Disney+ to allow user-generated content via AI
Disney boss Bob Iger has said the company’s streaming service will soon allow subscribers to create and view AI-generated content.
Speaking during the company’s latest earnings call, Iger said Disney+ would change to also host user-generated content for the first time, in a step that looks set to open the floodgates for fans keen to make their own creations featuring the likes of Darth Vader, Iron Man and characters from Frozen.
If that’s your mojo, now it’s the time to sharpen those AI Video skills.
Quick news you may have missed
LeonardoAI has released Blueprints, combining models, prompts, and settings into one streamlined flow. Users will be able to build their own Blueprints, and share them with the community.
ImagineArt 1.5 is a cutting-edge text-to-image AI model, an AI creative suite platform specializing in generating images, videos, and voice content. It’s a significant upgrade from ImagineArt 1.0, focusing on hyper-realism and precision to produce lifelike visuals that rival professional photography.
Best AI Videos of the Week
Enjoy!
Coca-Cola Ad by Secret Level
Wave by @MIZNOM
The Chronicles of Bone - The Last Lost Boy by @Kavanthekid
That’s all, friends. I will release the next stage of the Zero to Director Challenge on Tuesday. I had family visits, and it was difficult to ship the video. Be ready.
Disclosure: This post may contain affiliate links. If you click on a link and make a purchase, I may earn a small commission at no extra cost to you.