Eric is Daydreaming

2.8K posts

Eric is Daydreaming banner
Eric is Daydreaming

Eric is Daydreaming

@ericxtang

All I do is @daydreamliveai ☁️ Cofounder of @livepeer. Cohost of ComfyUI NYC. My creator profile: https://t.co/DdYVomhSjD

Austin 가입일 Ocak 2009
6.5K 팔로잉5.9K 팔로워
Eric is Daydreaming
Eric is Daydreaming@ericxtang·
@signulll The person who can connect culture with business opportunities - can lead a small team of super builders and win by speed.
English
0
0
0
137
signüll
signüll@signulll·
the most underrated hire right now is a great product person. when i say product person i'm def not talking about a product manager. perhaps i think there has to be somewhat of a new role. i don't have a good name for it yet but maybe something like "product thinker".. someone with an intuitive grasp of the product as it exists, where it's soft, where it sings, & how to iterate it toward something even sharper. in some sense, this person has to cohesively hold in their head where this product should be 2 years from now & work backwards from that. i say this cuz when building was hard, engineering was the bottleneck & the status hierarchy often reflected that. building is no longer hard. which means the variance in outcomes has shifted almost entirely to judgment on what to build, how to sequence it, & how to talk about it. & the story matters as much as the thing. internally, it organizes the team around a shared model of why. externally, it shapes the interpretive frame users bring to their first experience. you can't retrofit narrative onto a product & expect it to land, it has to be load bearing from the start. the rarest version of this person sits at the intersection of culture & deep technology. someone genuinely bilingual. they know what's technically possible & they know which cultural currents are real vs. ephemeral. that combo is what separates products that feel inevitable from products that feel assembled. before ppl clap back with this person has always been valuable, i know.. i am just saying now they might be the most *important* person in the room. their value compounds like never before.
English
449
740
6.3K
1.4M
Bruce van Zyl
Bruce van Zyl@brucevanzyl·
Anyone @Livepeer know what’s going on with transcoding. We’ve been unable to consistently encode videos for 2 weeks. Affecting 550k+ MAU. @ericxtang
English
1
0
0
241
Eric is Daydreaming 리트윗함
RyanOnTheInside
RyanOnTheInside@RyanOnTheInside·
For full technical details, please see arxiv.org/abs/2602.14381
RyanOnTheInside@RyanOnTheInside

YO, I adapted VACE to work with real-time autoregressive video generation. Here's what it can do right now in real time: - Depth, pose, optical flow, scribble, edge maps — all the v2v control stuff - First frame animation / last frame lead-in / keyframe interpolation - Inpainting with static or dynamic masks - Stacking stuff together (e.g. depth + LoRA, inpainting + reference images) - Reference-to-video is in there too but quality isn't great yet compared to batch Getting ~20 fps for most control modes on a 5090 at 368x640 with the 1.3B models. Image-to-video hits ~28 fps. Works with 14b models as well, but doesnt fit on 5090 with VACE. This is all part of Daydream Scope, an open source tool for running real-time interactive video generation pipelines. The demos were created in/with Scope, and is a combination of Longlive, VACE, and Custom LoRA. There's also a very early WIP ComfyUI node pack wrapping Scope. But how is a real-time, autoregressive model relevant to @ComfyUI ? Ultra long video generation. You can use these models distilled from Wan to do V2V tasks on thousands of frames at once, technically infinite length. I havent experimented much more than validating the concept on a couple thousand frames gen. It works! Full technical details on real-time VACE + more examples here (link in comments) Curious what people think. Happy to answer questions. Video + Custom LoRA links also in comments. Love, Ryan p.s. I will be back with a sick update on ACEStep implementation tomorrow (links in first comment)

English
7
3
42
1.7K
Eric is Daydreaming 리트윗함
Daydream
Daydream@DaydreamLiveAI·
We adapted VACE for real-time autoregressive video generation. Depth, pose, inpainting, temporal extension, reference-to-video, all composable. 20+ FPS. No retraining needed.
English
10
3
27
2.4K
Eric is Daydreaming
Eric is Daydreaming@ericxtang·
🤯 Real-time, open source, and local-first video editing is here. Make your own plugins or customize with LoRAs. Use it inside ComfyUI, Unreal, TouchDesign through NDI/Spout. Completely free.
English
14
4
39
642
Eric is Daydreaming 리트윗함
andrew
andrew@as_ws__·
touchdesigner + mediapipe + arcane lora + VACE = real time sfx for season 3 arcane? @DaydreamLiveAI @1null1
English
2
2
7
327
Ariel Shaulov
Ariel Shaulov@ariel__shaulov·
1/🚀 Just dropped ✨ TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation 🎥
English
6
11
70
5.1K
Eric is Daydreaming
Eric is Daydreaming@ericxtang·
Video AI is making big leaps. But we are just getting started. Visual storytelling is deeply personal, and 99% is still locked away in people’s minds due to lack of resources / tooling. I can’t wait for the Cambrian explosion of visual tastes coming to life.
English
6
0
7
184
Decart
Decart@DecartAI·
Drag, Drop and Try it live That's just a small glimpse of what’s possible when AI runs in Realtime, powered by Lucy 2.0. What else can you build?
English
79
230
2.2K
309K
Eric is Daydreaming 리트윗함
andrew
andrew@as_ws__·
combining depth maps in @1null1 and then running that into an arcane lora! real-time sfx! @DaydreamLiveAI
English
1
4
16
542
Eric is Daydreaming 리트윗함
Daydream
Daydream@DaydreamLiveAI·
3. Days. Left. This is your last chance to apply to the Daydream Interactive AI Video Program👇 daydream.live/interactive-ai…
English
2
2
9
233
ComfyUI
ComfyUI@ComfyUI·
Thank you, @bria_ai_ and @DaydreamLiveAI, for the amazing event! It's wonderful to see the Comfy creatives continue to grow!
BRIA AI@bria_ai_

ICYMI: @bria_ai_ took over the ComfyUI NYC event on Friday! It was incredible to see the community's response as @mfofana246 took the stage to demonstrate the power of Bria AI’s native ComfyUI integration. We spent the evening diving into the full visual pipeline, showing how developers can now use our modular building blocks for everything from FIBO generation to precise object erasing and image expansion. Thank you to @ComfyUI, @DaydreamLiveAI, @ZeroSpaceNYC, @Lightricks, and our very own @Gilshefler for helping organize the event, and a big thank you to everyone who joined us in person and via livestream. Let’s keep pushing the boundaries of modular AI! #GenAI #NYC #ResponsibleAI

English
2
2
49
7.1K