Pinned Tweet
$0.003/sec changes the economics of running real-time AI video.
I’ve been testing Vivix W1, and that number is hard to ignore.
The comparison shows visual quality on par with the models alongside W1. About a second of generation time per second of footage, too.
But W1 isn’t rator.
It’s built for real-time interactive video, where the model keeps generating as the experience moves forward.
Every second of that experience adds to the generation bill.
At $0.003/sec, you can actually start thinking about a story that keeps going as viewers make choices.
@VivixLabs_HQ already supports real-time generation through the API. The browser playground currently uses offline generation, with real-time browser tools coming soon.
Continuous video is one thing. Giving viewers meaningful control is another. If I change my mind halfway through a story, how much can it actually change with me? That’s the interesting challenge.
The next plot twist could be yours 👇
platform.vivix.ai/vivix-w1-model…
I’ve been testing Vivix W1, and that number is hard to ignore.
The comparison shows visual quality on par with the models alongside W1. About a second of generation time per second of footage, too.
But W1 isn’t rator.
It’s built for real-time interactive video, where the model keeps generating as the experience moves forward.
Every second of that experience adds to the generation bill.
At $0.003/sec, you can actually start thinking about a story that keeps going as viewers make choices.
@VivixLabs_HQ already supports real-time generation through the API. The browser playground currently uses offline generation, with real-time browser tools coming soon.
Continuous video is one thing. Giving viewers meaningful control is another. If I change my mind halfway through a story, how much can it actually change with me? That’s the interesting challenge.
The next plot twist could be yours 👇
platform.vivix.ai/vivix-w1-model…
34
97
362
224,106
It's like having a furniture designer who can bring your ideas to life.
Describe the sofa, table, or rug you're picturing, and @Maketplans turns it into a 3D asset you can add to your floor plan.
No settling for what's available. No endless searching.
Your next favourite piece of furniture might start with a simple sentence.
Describe the sofa, table, or rug you're picturing, and @Maketplans turns it into a 3D asset you can add to your floor plan.
No settling for what's available. No endless searching.
Your next favourite piece of furniture might start with a simple sentence.
Describe it. Create it. See it in your space.
Turn a text prompt into 3D furniture you can add to your floor plan.
Text-to-Furniture is now live in Maket.
19
89
319
38,477
One thing that limits creativity in design? Sometimes, the options available.
You have a vision for your living room, but the furniture library doesn't have what you're picturing.
@Maketplans is tackling that with Text-to-Furniture.
Instead of adapting your ideas to available assets, create assets around your ideas.
You have a vision for your living room, but the furniture library doesn't have what you're picturing.
@Maketplans is tackling that with Text-to-Furniture.
Instead of adapting your ideas to available assets, create assets around your ideas.
Describe it. Create it. See it in your space.
Turn a text prompt into 3D furniture you can add to your floor plan.
Text-to-Furniture is now live in Maket.
20
82
294
40,619
Describe it. Create it. See it in your space.
Turn a text prompt into 3D furniture you can add to your floor plan.
Text-to-Furniture is now live in Maket.
Turn a text prompt into 3D furniture you can add to your floor plan.
Text-to-Furniture is now live in Maket.
38
16
176
192,965
A curved velvet sofa with walnut legs🤔
That's no longer just a description of furniture.
With @Maketplans, you can turn a text prompt into a 3D furniture asset and place it directly into your floor plan.
We're moving towards a world where describing what you imagine is becoming just as important as knowing how to create it.
That's no longer just a description of furniture.
With @Maketplans, you can turn a text prompt into a 3D furniture asset and place it directly into your floor plan.
We're moving towards a world where describing what you imagine is becoming just as important as knowing how to create it.
Describe it. Create it. See it in your space.
Turn a text prompt into 3D furniture you can add to your floor plan.
Text-to-Furniture is now live in Maket.
18
85
331
33,762
AI StackLab retweeted
Describe it. Create it. See it in your space.
Turn a text prompt into 3D furniture you can add to your floor plan.
Text-to-Furniture is now live in Maket.
Turn a text prompt into 3D furniture you can add to your floor plan.
Text-to-Furniture is now live in Maket.
38
16
176
192,965
What we do all day, roughly: take a team's question ("what should the robot learn?") and turn it into clips ready to train on. Task design, our own recording hardware, processing, hand pose and language labels, quality checks. Same setup for all 50+ teams in our pipeline.
Come CoRL, Mon Nov 9: luma.com/wq7neni9
Come CoRL, Mon Nov 9: luma.com/wq7neni9
28
5
48
137,683
Teaching robots new skills starts with good training data.
From recording clips to labelling hand movements and checking quality, there’s a lot happening behind the scenes.
50+ teams using the same pipeline. That’s impressive.
From recording clips to labelling hand movements and checking quality, there’s a lot happening behind the scenes.
50+ teams using the same pipeline. That’s impressive.
What we do all day, roughly: take a team's question ("what should the robot learn?") and turn it into clips ready to train on. Task design, our own recording hardware, processing, hand pose and language labels, quality checks. Same setup for all 50+ teams in our pipeline.
Come CoRL, Mon Nov 9: luma.com/wq7neni9
14
82
345
26,003
AI StackLab retweeted
What we do all day, roughly: take a team's question ("what should the robot learn?") and turn it into clips ready to train on. Task design, our own recording hardware, processing, hand pose and language labels, quality checks. Same setup for all 50+ teams in our pipeline.
Come CoRL, Mon Nov 9: luma.com/wq7neni9
Come CoRL, Mon Nov 9: luma.com/wq7neni9
28
5
48
137,683
Sometimes a product ad just needs one more shot to feel complete.
Generate your starting visuals in Dreamina Marketing Studio, then use CapCut PC’s AI Extend to add more footage and build out your Black Friday product ad.
AI Edit and EditPilot give you more options to refine finishing touches.
More out of your footage, without starting the whole ad over.
Dreamina: bit.ly/4k0KTGe
CapCut PC: tinyurl.com/2v23rn22
#CapCutPC #CapCutDidThat #Dreamina #Smallbusinessmarketing
Generate your starting visuals in Dreamina Marketing Studio, then use CapCut PC’s AI Extend to add more footage and build out your Black Friday product ad.
AI Edit and EditPilot give you more options to refine finishing touches.
More out of your footage, without starting the whole ad over.
Dreamina: bit.ly/4k0KTGe
CapCut PC: tinyurl.com/2v23rn22
#CapCutPC #CapCutDidThat #Dreamina #Smallbusinessmarketing
14
80
351
49,743
🚨 20.000 DÓLARES por crear vídeos con IA.
Topview ha lanzado un desafío mundial en el que puedes participar creando vídeos de hasta 30 segundos con su modelo T1.
Hay premios en efectivo, 180.000 créditos y oportunidades para creadores de todo el mundo.
Tienes hasta el 6 de ar.
Topview ha lanzado un desafío mundial en el que puedes participar creando vídeos de hasta 30 segundos con su modelo T1.
Hay premios en efectivo, 180.000 créditos y oportunidades para creadores de todo el mundo.
Tienes hasta el 6 de ar.
Want to try our latest AI video model, Topview T1? 🎬
Bring your ideas to life—and enter the T1 Challenge for a chance to win cash + credits!
🏆 $20,000 cash + 180,000 credits
🎁 Follow + repost, then apply for FREE creation credits
📅 Enter by Dec 6 gv
#TopviewAI #TopviewT1 #TopviewT1Challenge
8
17
34
38,140
AI StackLab retweeted
🚨 20.000 DÓLARES por crear vídeos con IA.
Topview ha lanzado un desafío mundial en el que puedes participar creando vídeos de hasta 30 segundos con su modelo T1.
Hay premios en efectivo, 180.000 créditos y oportunidades para creadores de todo el mundo.
Tienes hasta el 6 de ar.
Topview ha lanzado un desafío mundial en el que puedes participar creando vídeos de hasta 30 segundos con su modelo T1.
Hay premios en efectivo, 180.000 créditos y oportunidades para creadores de todo el mundo.
Tienes hasta el 6 de ar.
Want to try our latest AI video model, Topview T1? 🎬
Bring your ideas to life—and enter the T1 Challenge for a chance to win cash + credits!
🏆 $20,000 cash + 180,000 credits
🎁 Follow + repost, then apply for FREE creation credits
📅 Enter by Dec 6 gv
#TopviewAI #TopviewT1 #TopviewT1Challenge
8
17
34
38,140
AI StackLab retweeted
BREAKING: Over $1,000,000,000,000 wiped out from the US stock market
24% chance of a recession next year
24% chance of a recession next year
205
160
1,298
1,507,623
My two shots look like they were filmed on different planets. The billboard trick is apparently offering interstellar travel.
Bring your ad together in CapCut PC.
tinyurl.com/2v23rn22
#capcutpc #capcutblackfriday
Bring your ad together in CapCut PC.
tinyurl.com/2v23rn22
#capcutpc #capcutblackfriday
13
52
292
61,859
One patch of the product still has the wrong color.
I tell Edit Pilot which area needs matching and ask it to preserve the hand and background.
I check the edited product through the motion before keeping it.
#capcutmarketing
I tell Edit Pilot which area needs matching and ask it to preserve the hand and background.
I check the edited product through the motion before keeping it.
#capcutmarketing
1
0
26
4,019
I play both shots back to back.
The product can do the impossible billboard escape without the entire afternoon changing color around it.
Try bringing your own product reveal together in CapCut PC.
#CapCutDidThat
The product can do the impossible billboard escape without the entire afternoon changing color around it.
Try bringing your own product reveal together in CapCut PC.
#CapCutDidThat
0
0
25
3,530