Pinned Tweet
A tiny guesthouse in Tuscany could never afford a cinematic ad.
So it imagined one instead.
A retired superhero, a monster truck, and the easiest parking in Montepulciano.
2'22", made solo. Sound on.
🤖 Made with AI
Parts one and two of the Christmas episode of "Villa Paola", my AI comedy series about a retired superhero in Tuscany.
Every hero was a kid once. This one was never given a toy. Now a whole village thinks he's Santa Claus, and he hears it as orders.
Half toon (minimax H3 MAX, 'cause I love the speed), half photoreal (Seedance 2.5), a Tuscan Christmas crooner made on Suno, all dialogue dubbed in post. One-man pipeline.
The night itself comes in December. Sound on.
2
113
Cryptico10 retweeted
The world's largest brokers is entering into the realm of the @avax 🔺
Charles Schwab, with $13.33T in client assets, just added $AVAX trading to Schwab Crypto.
Now, $13 Trillion of assets can be tradeble onchain right on Avalanche.
For once, Wall Street likes seeing red. 🔺
The only financial chain where Institutions loved their money parked and tradeable onchain
BREAKING: $13T @CharlesSchwab adds AVAX to Schwab Crypto
Schwab Crypto clients can now trade AVAX, marking the platform’s first crypto expansion beyond Bitcoin & Ethereum.
Halloween special of "Villa Paola", my AI comedy series about a retired superhero in Tuscany. Full episode, one-man pipeline, ~48h from script to upload.
Stack: MiniMax H3 for the toon prologue (open weights, ran some prompts locally), Seedance 2.5 for the photoreal part (omni-reference + multicut), Suno for the creepy children's choir, ElevenLabs for extra voices.
Stick around for the post-credits scene. Feedback welcome, especially on the multicut pacing.
He has been informed that a Christmas is approaching.
The anthem is in Klingon. Subtitles included.
Minimax H3 and Seedance 2.5 did the job.
#tlhinganHol
115
A retired superhero, a bottle, a corkscrew, and one glorious memory. 20 seconds.
Two engines (Seedance 2.5 + Minimax H3), one 6,700-character prompt for 7 cuts in a single generation, lip-sync windows timed to the millisecond on my own guide audio.
He had some experience.
2
4
172
New in Nook: Train LLMs
Give it a few examples and Nook fine-tunes a model on your own GPU, completely privately.
We taught Qwen3 4B to talk like a pirate with 32 examples: 14 seconds of training on an RTX 4060. Then it answered questions it never saw.
usenook.ai
9 months ago I made “The Dev”, my first short for @CartoonHero_ by @Framer_X . Then came a crazy difficult stretch, and I stopped generating. I picked it back up one month ago. This is what came out.
1
15
Why this film exists, in short.
As AI democratized content creation, eye-catching stuff grew exponentially and audiences grew numb. The emerging problem is not producing with AI: it is making what you produce emerge. The competition no longer comes from every production house. It comes from every house.
So, winking at Taleb: I joined the futility of cinematic storytelling (once highly improbable) with the renting of a roof (a demand that is highly probable). An asymmetric bet. The “here” is a real guesthouse in Montepulciano. The story is a procession of infinities and zeros.
This is not a commercial. Technically it’s a brand film. In practice it’s me, alone, telling the stories I love to tell.
1
15
1/3
Nook's source code is now public.
A local AI that promises privacy should let you check that promise yourself. So here's every line: the app, the Nooklets, the coding agent's sandbox. No telemetry, no analytics, no crash reports.
github.com/UseNookAI/nook-ap…
Cryptico10 retweeted
Before joining Cartoon Hero, I was learning on my own and progressing pretty slowly. Since joining, I’ve learned so much in such a short time, especially techniques I didn’t even know about before. Everything he shares in his videos and all the tools he introduces have also been really helpful, and being part of a community where we can share, learn, and help each other is amazing!!!



















