nowfound

Life & fun · May 20, 2025

Daydream

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 honestly 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.…

Daydream launched on May 20, 2025 with 19 votes, #853 of 7,905 launches that month and more than 90% of that year's launches. The site was still online in September 2026, 1 year on.

In plain words

The Daydream AI Video Program is a free, two-week hands-on lab for developers and creative technologists building with real-time AI video. Running February 9–20, participants receive one-on-one support, access to cloud infrastructure, and opportunities to collaborate with others in the space. The program distributes over $5,000 in prizes throughout the two weeks. Applications close February 6.

written from the facts on this page · September 2026

From the sources

Daydream transforms any livestream into interactive visuals so you can create limitlessly. Real-time AI for real-time imagination.

Chase it, arrange it, chop it into a kit — in a style from our catalog, or one you train yourself on your own stems and mixes. Yours to keep. VST3/AU/AAX, Max for Live, or TouchDesigner.

Play, arrange, sample, and mix. Explore our catalog, or personalize with your own audio. Turn a rough input — a hum, a click, a scrap of noise — into any sound you want. Build a drum kit or beat from novel hits you shape live — not sounds pulled from a pack. Turn a raw field recording into usable production material — at whatever creative distance you want. Reshape a vocal take into anything — from a subtly different version to a horn solo. Slice a phrase into pads, and decide per hit how far each drifts from the original. Turn one instrument into a different one — same idea, new identity — in real time. Say goodbye to generic sounds. Create a personal sound profile on your stems or mixes…from daydream.live

In the maker’s words, at launch

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…

Does a similar job

all alternatives →
  • GA
    Get a Professional Headshot in Minutes with AI2023 · virtualface.app · ▲147

    After playing with AI Avatars (like many of us I guess around here), I started to wonder if we could instead bring real value to people by producing affordable professional head-shots using a combination of Dreambooth and ControlNet. Obviously it's only the beginning and there are still many imperfections, but the foundational tech behind this (Dreambooth and ControlNet) are only respectively 6 months and 1.5 month old, and already delivers pretty amazing results. I came up with this little service "Virtual Face" and I'm looking for feedback if some of you are willing to try it (you can use…

  • DreamFlow2025 · ▲283

    Turn map screenshots into aerial cinematic videos with Veo3

  • LS
    Lemon Slice Live – Have a video call with a transformer model2025 · ▲195

    Hey HN, this is Lina, Andrew, and Sidney from Lemon Slice. We’ve trained a custom diffusion transformer (DiT) model that achieves video streaming at 25fps and wrapped it into a demo that allows anyone to turn a photo into a real-time, talking avatar. Here’s an example conversation from co-founder Andrew: https://www.youtube.com/watch?v=CeYp5xQMFZY. Try it for yourself at: https://lemonslice.com/live. (Btw, we used to be called Infinity AI and did a Show HN under that name last year: https://news.ycombinator.com/item?id=41467704.) Unlike existing…

  • Daydream.VR2016 · daydream.io · ▲77

    Virtualize Your Reality!

  • DeepDream for Video with Temporal ConsistencyJan 2026 · github.com · ▲72

    I forked a PyTorch DeepDream implementation and added video support with temporal consistency. It produces smooth DeepDream videos with minimal flickering, and is highly flexible including many parameters and supports multiple pretrained image classifiers including GoogLeNet. Check out the repo for sample videos! Features: - Optical flow warps previous hallucinations into the current frame - Occlusion masking prevents ghosting and hallucination transfer when objects move - Advanced parameters (layers, octaves, iterations) still work - Works on GPU, CPU, and Apple Silicon

  • Lifecast2022 · github.com · ▲74

    Convert any VR180 video/photo to 6DOF or Unreal Engine

More life & fun this month

the category →

Source: Product Hunt launch ↗ · launch text quoted in part

Launched alongside, May 2025

the whole month →
  • Tapflow 2.0▲1,125

    We built Tapflow for devs, designers, PMs, and tech folks who’ve been sitting on internal docs, templates, and systems — but never productized them. Upload a PDF, notes, or workshop deck, and Tapflow drafts a structured product (with chapters, teaser and pricing plans). It’s good for AI kits, onboarding guides, design systems, and frameworks. You can sell through Stripe, LemonSqueezy, or PayPal. Real-time collaboration is in early beta. No site builder, no LMS — clean design and just focused tools to ship. Fully bootstrapped and just launched on PH today →…

    Work · 2025 · tapflow.ai

  • C9

    Life & fun · 2025 · felixrieseberg.github.io

  • Appwrite 2.0 brings a new engine, a rebuilt Console, five database types, an S3 API, an OAuth 2.1 server, and organization-level Domains and Firewall.

    Dev tools · 2025 · appwrite.io

  • Perfect meeting memory in Notion

    AI · 2025 · notion.com

  • Den▲948

    Multiplayer AI agent builder

    AI · 2025 · getden.io

  • Powerful productivity on the go

    AI · 2025 · raycast.com