Vidu 2.0 is a Sleeper HIT for AI Video!

In this video, I dive into the newly released Vidu 2.0 model, exploring its image-to-video, reference-to-video features, and overall performance. I compare it to Lumia’s Ray 2 text-to-video approach, as well as Sora’s evolving capabilities, highlighting where each model shines (and where they still struggle). Along the way, I run through fun experiments like blending my own portrait into cyberpunk scenes, creating crowd shots, and even conceptualizing an animated “zombie dogs” project. I also check out how the upcoming Kinetix Tech platform may change character motion control—especially if TikTok ever gets banned! Watch till the end for tips, tricks, and my honest thoughts on these emerging AI video tools.

If you find these demos helpful or inspiring, please hit that Like button, consider subscribing, and let me know in the comments what you’d like to see in future videos. Thanks for watching!

LINKS:
Video on Point Diffusion:
Today's Sponsor: Hubspot! Thank you!

Chapters
0:00 Introduction
0:32 Vidu 2.0 Features & Comparing Versions
1:07 UI Walkthrough & Generating Options
1:43 Amplitude, Duration, & Motion Examples
2:22 First Example
3:01 Man in a Blue Business Suit Update
3:54 Combining Outputs (Luma Ray 2 & Vidu)
4:44 Wizard Orb & Prompting Examples
5:26 Vidu's Scene Understanding
5:49 First Frame Last Frame
6:27 Editing for First and Last Frames
6:55- Limitations of First and Last Frames
7:15 Crowd Scenes & Decoherence Fixes
7:51 Anime/Cartoon Style Tests
8:13 ‘Paws of the Dead’—Animated Zombie Dogs
9:07 - Hubspot's ChatGPT Resouces
10:46 Reference-to-Video is the solution
11:45 Improving Results with Rerolls & Blending
12:08 More experiments with References in Vidu
13:01 Rockstar Tim
13:35 Trying to "break" Reference Video
14:11 Sora Remix Experiments
14:46 Pros & Cons of Longer Clips
15:04 The Best Remix yet
15:29 Kinetix Tech for Motion Capture
16:37 - Pro Use?
17:23 - Closing

17:24 Wrap-Up & Reminders

[Ryoku]

Vidu has actually been the video generator that I've had the most success with. Other models don't give me much usable to actually tell a story. Vidu can ALMOST give me fight scenes and the reference to video is actually quite good.

[thirdphaseofmoon]

Thanks for your hard work on keeping us up to date on the latest AI features!

[theironalchemist]

4:49 Tim's dad jokes are so undefeated. 😅 He's one of my favorite people I'm subscribed to. Thanks for the review. I appreciate you.

[shnook]

Thanks for keeping me up to date, Tim. Love Vidu and it just keeps getting better. Today, Kling pretty much nuked their free trials, as they've eliminated generating more than 1 vid at a time, and it seems all the models have the 3+ hour wait time now. The party was fun while it lasted!

[fabianeer]

the 3 mixed references got really well fused together. actually impressive

[Foolsjoker]

You don't have to cancel at the end of your plan. You can cancel today and when you sub expires it will not renew.

[ArtificiallyCreative-AI]

Great update + classic Zappa on the shelf!

[vidiot]

Great stuff as usual.. served up with side of Tim humor.. Always entertaining..

[themjstory]

Anime use case is really good. Consistency has jumped a good amount from 1.5 to 2.0

[estrangeiroemtodaparte]

I really love the stylization possibilities of Vidu. With Sora, I’ve been trying out some ideas for subtle, 'invisible' VFX that blend into the scene, and it’s been really fun to experiment with.

[rodrigodonosoperalta]

The generations on video used to cost 4 credits but now they cost 12 credits. So you can make 6 videos per month free

[AIOneMusic-djmu]

The competition is just getting Hotter, Just yesterday I was complaining about tighter censorship on vidu which was unnecessary! Vidu was one of the first I subscribed to because of its ability to handle fight scenes better

[danielrosenplanter]

Zappa…nice. Jazz isn’t dead, it just smells funny. Anyway, I’m digging Vidu, thus far I tend to get better dynamics through reference to vid compared to image to vid. But it’s cool since you can basically start your character out from a different angle, and it does of great job at keeping the details of of the character and background consistent. I am still somewhat perplexed by Sora. It can’t do the simple stuff you ask it to do, but I really like blending features. It does a great job at sampling characters from the driving video into the motions of the secondary clip. You can get some pretty interesting results with mixing as well. I mainly use the storyboard if I want to make a 10 or 20 second clip by letting Sora handle the transitions between 2 clips from another platform. I would be interested to see what type of results your cartoon / zombie apocalypse gets using Sora’s mix blending. Thanks for keeping us up to date of everything!

[DesertedFilmsu]

Tbh neither Luma nor Vidu still anywhere closer to kling and hailuo yet lol
Thanks for the update though:)

[calinia]

Holy advertisements!! Absolutely abysmal to try to watch this video through them all!!

[MrZellie]

I love your videos however this video was unwatchable because YouTube decided to play an ad every minute. Not cool YouTube

[danielschweig]

🔥 It is essential to scale an image before animating it. The best way to do this is with Krea ai or Pixeldojo. The result of the animation is WORLDS better afterwards.

This is because the Ki such as Vidu or Kling etc. recognizes more with more pixel density. The output of your input is therefore better and you no longer have a blur.

[leglessrestsyndrome]

Paws of the dead is a great idea. I like the style of it.

[CaroleBaskin]

Just makes me want to edit videos all day.

[Harddiskfail]

I still have Pika Videos that have not finished from when they did the "free unlimted event"