Joey Daoud

🎬 The full Inside the AI Studio series is now live...and the trailer just dropped. Filmed at @aionthelot, this 12-part series features conversations with the creative minds shaping the future of AI in filmmaking. We dive into: • How AI is actually being used on real productions • New workflows for VFX, previs, editing, and animation • How creators are training custom models for storytelling • Where the tools are headed next - and how fast and a lot more Featuring: Amit Jain at Luma AI @gravicle / @lumalabsai Andrew Hevia at Fabula @andrew_hevia / @fabula_prod Davide Bianca at GRAiL Edward Dawson-Taylor at CG Pro @becomecgpro Eliot Mack at Lightcraft Technology @lightcraftpro Kavan The Kid at Phantom X @kavanthekid / @phantomx_ai Max Einhorn at Gennie @maxeinhorn / @genniestudio Michael Lingelbach at Hedra @mjlbach / @hedra_labs Michaela Ternasky-Holland at MTH Studio @ImMichaelaTH Monji Batmunkh at Topaz Labs @monjibatmunkh / @topazlabs Parag Mital at The Garden in the Machine @pkmital Reza Sixo Safai at Massive Studios @rezawrecktion / @ai_massive ▶️ Watch the full series → youtube.com/playlist?list=…

Church:

@kelseytsutton @AMCTheatres Thanks for triggering the music to play in my head

.@AMCTheatres it’s time to change the coca-cola ad that shows before movies. enough with the dance battle and car race 😭

@TrungTPhan Is this ai Friday?

The team behind Tilly Norwood — the AI model with 90k IG followers — has caused controversy by trying to make her the first mainstream AI actress in Hollywood. They just released a music video (titled “Take The Lead” and it is “created by 18 humans”) that claps back with this chorus: “AI isn’t the enemy, it’s the key”. It is so bad, Tilly’s Hollywood dreams are almost certainly over and this may single-handedly pop the AI bubble.

Not outright calling it Big Foot. Keeping the Skunk Ape dream alive

is it bad i knew which erewhon this is based on the layout?

One step closer…

Same thoughts. One of the best races in a long time

Netflix bought an AI studio, Seth MacFarlane became Bill Clinton, and Luma just shipped a model that thinks and renders at the same time. 11 updates in AI this week(ish): • Netflix acquired Ben Affleck's AI filmmaking studio InterPositive. He's been building it since 2022 with a proprietary dataset shot on a controlled soundstage. • Seth MacFarlane used AI to make himself look like Bill Clinton in Ted Season 2. • Google launched Nano Banana 2. Lots of features in Nano Banana Pro at half the price. • Luma launched Uni-1. First model that reasons and generates images at the same time, plus an agent platform. • Corridor Crew open-sourced CorridorKey. It reconstructs the true color and transparency of every pixel at a green screen edge, so hair, motion blur, and soft edges key cleanly without manual rotoscoping. • Foundry released Nuke 17.0. Native Gaussian splat support and a new USD-based 3D system out of beta. • Perplexity launched Perplexity Computer. One interface that orchestrates a bunch of different AI models with persistent memory. • Anthropic shipped three Claude updates in 48 hours. Mobile access to coding sessions, scheduled recurring tasks, and memory that carries over between sessions. • Quiver AI launched Arrow-1.0. Generates clean editable SVGs natively from text or images, backed by a16z. • Lightricks released LTX Desktop. Full open-source video editor with local AI generation built in. • LTX-2.3 also dropped. Sharper detail, stronger motion, native vertical video support.

Hollywood opinion on AI - youtu.be/25nOtTIRJ9g?si…

At this point i'm convinced this is an elaborate prank

@bilawalsidhu THIS is how you monitor a situation

Between Gemini 3.1 and Claude 4.6 it's honestly wild what you can build. This feels like Google Earth and Palantir had a baby. Made this with all the geospatial bells and whistles -- real time plane & satellite tracking, real traffic cams in Austin, and even got a traffic system working. Panoptic detection on everything. Skinned the whole thing to look like a classified intelligence system. EO, FLIR, CRT. Got a bunch more stuff on the roadmap. This is fun.

@jonfavs @PeterHamby Calabasas

@PeterHamby Can't believe no one's said Beverly Hills or the Valley

Bondi would probably live in Culver City tbh. Or Marina Del Rey.

@mattworkman Oh I wonder if it's Remotion under the hood

@C47 the Higgsfield UI is a wrapper for it. I still need to dig in more with it, I’ve only done a few tests. But overall I like the UI and interface, it’s like it’s whole own new app.

@mattworkman @Gossip_Goblin VEED Lipsync LatentSync MuseTalk Pixverse Lipsync Sync Lipsync 2.0 nothing was amazing but Veed was the best out of a quick test

@C47 @Gossip_Goblin Hmm I know audio + image like Kling avatar 2. What model does audio + video. That sounds like a tough challenge

What is the best lipsync tool at the moment? Will insta block if you say Kling.

@mattworkman @Gossip_Goblin there's also 2 buckets of lipsync: audio + image and audio + video to dup/change speech

@C47 @Gossip_Goblin there are so many, but I want to try the different audio to lip sync models

@mattworkman @Gossip_Goblin It’s great, one stop shop for just about all the models

@C47 @Gossip_Goblin Fal

@mattworkman @Gossip_Goblin Fal or the models?

@C47 @Gossip_Goblin interesting I saw people promoting that recently

@mattworkman @Gossip_Goblin Fal

@C47 @Gossip_Goblin how do you access those to test? their own platforms?

@mattworkman @Gossip_Goblin Veed and omnihuman

@Gossip_Goblin following