正在加载视频...

视频加载失败

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

119,953 次观看 • 4 个月前 •via X (Twitter)

32 条评论

AK 的头像
AK4 个月前

paper:

Sanjay 的头像
Sanjay4 个月前

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

Progyan 的头像
Progyan4 个月前

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

Pils10 的头像
Pils104 个月前

AI Wifus coming soon!

Adam 的头像
Adam4 个月前

that's really cool

Völkisch 的头像
Völkisch4 个月前

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 的头像
James4 个月前

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 的头像
briton4 个月前

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

Bin Chen 的头像
Bin Chen4 个月前

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 的头像
James' AI Takes4 个月前

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 的头像
Hrittik Das4 个月前

she was more expressive than the guy

Joannot Fampionona 的头像
Joannot Fampionona4 个月前

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

Hammad Hamid 的头像
Hammad Hamid4 个月前

amazing man

ΛIΚO 的头像
ΛIΚO4 个月前

@grok wtf is this real?

Gordon Olson 的头像
Gordon Olson4 个月前

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 的头像
ansuman4 个月前

Final piece in AI wifu!

Colbert 的头像
Colbert4 个月前

I like this

oo 的头像
oo4 个月前

is this available to use anywhere?

TongHe 的头像
TongHe4 个月前

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 的头像
Zakaria4 个月前

@Justiniansli

JackWison 的头像
JackWison4 个月前

good idear

Cris Lenta 的头像
Cris Lenta4 个月前

so awesome!

sarahgamedev 的头像
sarahgamedev4 个月前

Oh gawd, I am real. She’s not real

makyō 的头像
makyō4 个月前

Model/code release?

☣ GBLW  的头像
☣ GBLW 4 个月前

Great !

TechMD 的头像
TechMD4 个月前

amazing work

veloX 的头像
veloX4 个月前

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 的头像
MinG.AI4 个月前

This so unreal brooo

Sebastian Buzdugan 的头像
Sebastian Buzdugan4 个月前

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

Taran Mann 的头像
Taran Mann4 个月前

Is it on Comfy yet

Raj 的头像
Raj4 个月前

Great

ReggieJ 的头像
ReggieJ4 个月前

我要做一个 @CuiMao 的

相关视频

Time to end it
5:29

Sensitive content

Time to end it

NRM84

22,902 次观看 • 1 年前