Loading video...

Video Failed to Load

Go Home

Wan-Streamer v0.1 End-to-end Real-time Interactive Foundation Models

119,953 views • 4 months ago •via X (Twitter)

32 Comments

AK's profile picture
AK4 months ago

paper:

Sanjay's profile picture
Sanjay4 months ago

Single guys gonna love it for sure and gold diggers rn:

Progyan's profile picture
Progyan4 months ago

It's almost opensource if someone is willing to contribute an extra 10% of perf.

Pils10's profile picture
Pils104 months ago

AI Wifus coming soon!

Adam's profile picture
Adam4 months ago

that's really cool

Völkisch's profile picture
Völkisch4 months ago

That's very impressive, its expressions are very realistic. I hope they release the models for us to play around with. Perhaps we can add custom characters to it via training.

James's profile picture
James4 months ago

need full upper body like at desk or sitting etc so you can see the hand gestures not cut off, so can be composited on scene

briton's profile picture
briton4 months ago

another stunning example of Alibaba's new model - Ali-Catfish1.0

Bin Chen's profile picture
Bin Chen4 months ago

avtr-1 is doing this pretty good with a single 3090 in realtime, it renders lip-synced speech and active listening at 25 fps on a single GPU. the only drawback is it only has facial change but not neck rotation etc.

James' AI Takes's profile picture
James' AI Takes4 months ago

real-time interactive foundation models are the fun part. the ugly part is whether latency, state, controllability, and failure recovery survive past the demo clip. streaming magic still needs boring systems engineering.

Hrittik Das's profile picture
Hrittik Das4 months ago

she was more expressive than the guy

Joannot Fampionona's profile picture
Joannot Fampionona4 months ago

We need that ASAP in the wan app even if it's a paid feature

Hammad Hamid's profile picture
Hammad Hamid4 months ago

amazing man

ΛIΚO's profile picture
ΛIΚO4 months ago

@grok wtf is this real?

Gordon Olson's profile picture
Gordon Olson4 months ago

This is really cool. Was thinking about this last week. But didn’t take it as far as full transformer architecture for everything. So this is fascinating I’ll be looking at this to run via webgpu

ansuman's profile picture
ansuman4 months ago

Final piece in AI wifu!

Colbert's profile picture
Colbert4 months ago

I like this

oo's profile picture
oo4 months ago

is this available to use anywhere?

TongHe's profile picture
TongHe4 months ago

Real-time interactive AI is impressive. I think the next hard problem is shared-room conversation: multiple people, multiple languages, interruptions, accents, names, and context. Not just one human and one AI. A whole group staying in the same conversation.

Zakaria's profile picture
Zakaria4 months ago

@Justiniansli

JackWison's profile picture
JackWison4 months ago

good idear

Cris Lenta's profile picture
Cris Lenta4 months ago

so awesome!

sarahgamedev's profile picture
sarahgamedev4 months ago

Oh gawd, I am real. She’s not real

makyō's profile picture
makyō4 months ago

Model/code release?

☣ GBLW 's profile picture
☣ GBLW 4 months ago

Great !

TechMD's profile picture
TechMD4 months ago

amazing work

veloX's profile picture
veloX4 months ago

Gerçek zamanlı etkileşim için video akışı yeterli değil — sistem lokal girdi işleyebiliyorsa neden AI ajanın web kameraya erişmesi gerekiyor? Latency, gizlilik ve inference maliyeti açısından stream-based mimari daha pahalı.

MinG.AI's profile picture
MinG.AI4 months ago

This so unreal brooo

Sebastian Buzdugan's profile picture
Sebastian Buzdugan4 months ago

once end to end delay passes 200ms interactivity feels fake can wan-streamer stay below that

Taran Mann's profile picture
Taran Mann4 months ago

Is it on Comfy yet

Raj's profile picture
Raj4 months ago

Great

ReggieJ's profile picture
ReggieJ4 months ago

我要做一个 @CuiMao 的

Related Videos

Time to end it
5:29

Sensitive content

Time to end it

NRM84

22,902 views • 1 year ago