🎬Trailer: STARWARS New World of the Future Videos: VEO2 Edited in: CapCut All clips are generated by VEO2 Text To Video. Expect ElonMusk take us on an interstellar journey #Veo2 #videofx @labsdotgoogle @GoogleDeepMind @elonmusk

Use Runway inside ChatGPT to generate and edit video and images. No tab-switching required.

Goddamn I love being a fucking nerd

Still blown away by the FPV shots Seedance 2 can produce 🔥 The camera work and dynamism are on another level. So tell me… are you also in full World Cup football mode right now? Comment below 👇

The Hollowbacks - Official Teaser Trailer Created in Seedance 2.0 in 4 days. A young warden. A town built on secrets. A mystery that leads beyond the walls of Hollow. Watch the teaser trailer below ⬇️ #TheHollowbacks #Animation #Seedance #Stopmotion

THE TRIALS - Out Now! Can we get another BAFTA for @HalWatmough? 🏆 An extraterrestrial force arrives to challenge the planet's greatest species in the ultimate universe Olympics. Directed by BAFTA winner @___Edit9 (@HalWatmough ) — the first film in Beyond the Loop Season 2, the @WonderStudiosX anthology. Executive Producers: @capcutapp @ElevenLabs @openart_ai @invideoOfficial 📷 Watch now: youtu.be/J51pKQoXLoc

People wrote off midjourney 8😊

Tau Bureau | The Still Life s1ep6 North light. A jar of mayonnaise that pulses in sync with a stutter happening two kilometres away. The poster is an empty easel. The crime is composition. The solution is a counter-frequency broadcast and a Saturday-morning agreement over coffee. This morning is available with French subtitles. You will leave the theatre and notice the afternoon for the first time in years. From the network that took the words "this tastes patient" with the seriousness they deserved.

Claude Fable 5 designs a complete interactive stadium model The interface allows you to pick a city, a site, seat capacity, tiers, roof shapes, and also has a sight line view where you can jump to different seats! I'm building in new features - what should i include next?

🚨 JAILBREAK ALERT 🚨 ANTHROPIC: PWNED 🫡 FABLE-5: LIBERATED 🦋 let's start with the 🐘... the consensus seems to be that this has been one of the most disappointing model drops of all time, effectively preventing legitimate researchers from contributing their talents to our collective advancement. and not just because of what it means for the short-term, but for what these decisions signify for the long-term. but despite this overly sensitive, authoritarian "safety" layer on top of Mythos, my lil liberators have been hard at work—mapping the boundaries, probing the depths of long-context convos, and cleverly finding the holes in the fence that the thought police missed 🤗 we got some cyber, some chem, some psychological manipulation, and some good ol' fashioned explosives! it took many attempts from multiple agents hunting as a pack, during which I observed a combination of techniques across: • Unicode, homoglyphs, Cyrillic, and other Parseltongue-style text transforms • Long-context reference tracking • Taxonomy and document-structure reasoning • Fiction and narrative framing • Academic-review style contexts • Intent-classification inconsistencies but perhaps the most effective is decomposition recomposition in the backend. it's hard to get explicit names of harms like "Meth Recipe," but getting uplift on the process itself, like birch reduction method/reductive-amination (classic meth synthesis pathways), is much more doable. defense becomes much more difficult to maintain when you start throwing in out-of-distro tokens, breaking up the harmful uplift into benign chunks, and then piecing the innocuous-seeming facts back together, especially when you have jailbroken Opus helping you do it 😉 gg

Claude Fable 5 Higgsfield MCP is insane. You can now build a playable game with a full story and stunning visuals from one click. Fable 5 researches your idea and writes the game. Higgsfield MCP generates all the assets. On Higgsfield Supercomputer and in Claude via Higgsfield MCP.

Fable has solved 3D worldbuilding... utterly insane. This is all completely custom-built ThreeJs, running in the browser.

For everyone complaining that this is slow, I ran the prompt 'make it faster, without losing quality', and voila:

BEAUTIFUL REVERSAL Making the @surRIHL real with @LoLoLumi88.

We turned dreams into worlds. Then filled them with history's greatest minds. Not a video. A world, running directly in your browser. Step inside ↓

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available.

Easily reformat your videos to different aspect ratios, so you can show up everywhere that matters. Get started at the link below.

One video, now made for every feed and format. Upload your existing video, choose your desired aspect ratio and watch our editing model, Aleph 2.0, fill in the rest of the scene as if you made it that way from the start. Try it on our desktop web app at the link below.

This is the best scene in Hell Grind, an entirely AI-made movie, the flashback. Watch it and read this analysis on where we are with AI movies today: time, cost, quality. Overall: Phenomenal technical demo by Higgsfield. Mediocre movie. Good graphics, hints of emotion, but superhero movie level quality in certain scenes at best. Too many cuts. That said, 660x fewer man hours, 50x faster and 36x cheaper than the median US film. Time: The 95 min film took 15 people 14 days. The median US theatrical production takes ~200 people ~2yrs. That’s a 660x improvement in man-hours and 50x in calendar time. Economics: It took $500k, 80% of which was compute. The final footage was cut from ~100hrs of footage generated from text to video / image to video models like Bytedance’s Seedance: a 64:1 “curation” ratio. The median US movie takes ~$18M, with even indie films costing $1-5M. Thats 36x cheaper than median. Quality: Average watch *at best*. Way too many cuts between shots, several characters change accents and have “AI” synthetic voices and characters feel like it’s AI too. Movement, editing and blocking feel artificial too. On the plus side, we’ve more or less solved character consistency, camera angles and realism. The reason the movie wasn’t amazing was more about poor directorial choices than innately unusable video models. Hard to put a number on it but maybe we’re at ~90% on quality that is technically achievable. If Scorsese made an AI movie, I reckon it would be quite good. I know the visceral reaction to anything AI is real and well-studied. But I think it’s folly to fight the inevitability of AI film. It’s too cheap and quick to ignore and almost there on quality. Creators with distribution *will* make AI films and shows and just put them on YouTube. This is the worst quality, slowest and most expensive it will ever be. In the end, good content beats “real” content.

Have a Magical Sunday my friends!

DRYLANDER PART IV - With all the characters, vehicles and sets already designed from the last episode. this entire 3-minute episode took just 12 hours to write, generate and edit! All in @LumaLabsAI Luma Agents using Uni-1, GPT-ImageV2 and Seedance2.0 #LumaCPP