π§΅ THREAD: THE FREE-EST WAY TO MAKE AI UGC VIDEO EVER,
Ok I was dming @mdnlabs
But thought lemme end this in one go, so here is what you've all been waiting for, ask me questions. But when diving into this there's 2 things
1) you quit
2) you generate 30+ videos per hour
π§΅ THREAD: THE FREE-EST WAY TO MAKE AI UGC VIDEO EVER,
Ok I was dming @mdnlabs
But thought lemme end this in one go, so here is what you've all been waiting for, ask me questions. But when diving into this there's 2 things
1) you quit
2) you generate 30+ videos per hour
As a founder
How are you actually using AI today?
-replacing developers
-speeding up development
-validating ideas faster
-building MVPs
-just experimenting
β οΈ Supply chain attack in progress: someone is squatting Anthropic-internal npm package names targeting people trying to compile the leaked Claude Code source.
`color-diff-napi` and `modifiers-napi` β both registered today, same person, disposable email. Do NOT install them. π§΅
My IOS app FINALLY has a distribution pipeline ππ
A dynamic script that gathers UGC, adds hook text, stitches App Demo, adds music, and publishes to all platforms to the next available time slots.
Time to make slideshow accounts now π
This is getting SUPER fun π
Seedance 2.0 is impressive. But it's closed-source!
Introducing our daVinci-MagiHuman β a single-stream 15B Transformer trained from scratch that jointly generates video + audio. No cross-attention. No multi-stream branches. Just self-attention.
β‘ 5s 1080p video in 38s on a single H100
π 80% win rate vs Ovi 1.1 | 60.9% vs LTX 2.3 (2,000 human comparisons)
π 6 languages
π¦ Fully open-source
Speed by simplicity.
By @SII_GAIR Γ @SandAI_HQ
π https://t.co/SgFOunlEIj
π» https://t.co/9rwNWzlMKN
π€ https://t.co/txduP5FgIC
Okay, my app was meant to be done like 2weeks ago, but 1, I got kinda lazy and burnt out with it, now it's taking a month to finish. Cuz I'm setting up ugc and all, school break is this week so thank Christ. Likely I'll finish it up this week, I feel bad anytime I postpone it