austin castle retweeted
Using 3D assets with Gen-4 References is a simple way to bring highly detailed and specific models into your generative workflows for even more consistency and control. To do so, simply provide a location plate, a quick comp of your 3D model in that space and a style reference.
austin castle retweeted
Ray2 is coming to #AdobeFirefly — bringing the next frontier of video generation to Firefly and Firefly Boards. From simple, natural prompts to cinematic motion, create with #Ray2 wherever Firefly is available. lumalabs.ai/blog/news/ray2-i…
austin castle retweeted
BTS: Frozen in Motion — Still Life
Made with #Ray2 Camera Motion Concepts #aivideo #surrealism #cinematography
austin castle retweeted
Today we're introducing Gen-4, our new series of state-of-the-art AI models for media generation and world consistency. Gen-4 is a significant step forward for fidelity, dynamic motion and controllability in generative media.
Gen-4 Image-to-Video is rolling out today to all paid plans and Enterprise customers.
1/8
austin castle retweeted
🚀Major update to Blender MCP:
🌄 Generate high-quality 3D assets in Blender by just prompting, thanks to @DeemosTech's Rodin AI.
🎬 Demo: Creating a cozy scene with a cat. Just describe the assets you want, and it will show up right in Blender. No manual modeling needed!
austin castle retweeted
At the Dalí Museum, visitors can pick up a surrealist lobster phone and hear the artist’s voice respond in real time.
More than 70,000 conversations have taken place with AI Salvador Dalí in the last year.
austin castle retweeted
MIDJOURNEY → Quality of life update.
"Smart Select" now is within Editor.
PROCESS:
01. Open "Edit"
02. Upload an image
03. Choose "SELECT"
04. Highlight the area.
05. Select "Remove" or "Isolate"
06. Add prompt + generate
#midjourney
austin castle retweeted
Today with Ray2 Flash we are introducing a new method of distilling frontier models that retains all their capabilities and ultra high quality -- at 500% higher efficiency! (we are using some gains to offer higher throughput so users have shorter queues) Our team has been perfecting this method for a while and I am proud to finally be able to release it, starting with our subscribers! Come join us if inventing the frontier is your jam - lumalabs.ai/join
Introducing #Ray2 Flash—3x faster, 3x cheaper new model. Flash brings Ray’s frontier production-ready Text-to-Video, Image-to-Video, audio, and control capabilities with high quality and speed to all subscribers—so you can create more, faster, and without limits. Available now.
austin castle retweeted
Wow. This is one of the best AI hybrid commercials I've ever seen.
Rufus Blackwell shot this partially live-action (opening and closing shots) and did a ton of keyframe AI animation.
They probably saved $100K and four weeks of VFX work by doing this as a hybrid commercial.
austin castle retweeted
Presenting ShaderGPT™, an AI experiment.
Which LLM is best at coding visual GLSL fragment shaders?
OpenAI vs. DeepSeek vs. Mistral vs. Anthropic.
Write prompts and explore examples.
shadergpt.14islands.com/
Built with AI SDK by @vercel.
austin castle retweeted
One of my favorite SREFs, it's perfect for creating blueprints on almost any topic
--sref 3982351386
austin castle retweeted
Introducing Claude 3.7 Sonnet: our most intelligent model to date. It's a hybrid reasoning model, producing near-instant responses or extended, step-by-step thinking.
One model, two ways to think.
We’re also releasing an agentic coding tool: Claude Code.
austin castle retweeted
Today we are introducing Ray2! Scaling pretraining by 10x on a novel efficient architecture, we are able to unlock the next frontier in video generation - fast natural coherent motion and physics. This skyrockets the success rate of usable production-ready generations and makes video storytelling accessible to a lot more people.
Ray2 is initially available to our paid subscribers in Dream Machine to keep queues in check, and it launches with 5s and 10s text-to-video generations.
image/video-to-video and much longer generations will follow soon!
The @LumaLabsAI team has worked tirelessly to invent, scale, and deploy this advanced model. I am proud of what we have accomplished and excited for what's to come.
Introducing Ray2, a new frontier in video generative models. Scaled to 10x compute, #Ray2 creates realistic videos with natural and coherent motion, unlocking new freedoms of creative expression and visual storytelling. Available now. Learn more lumalabs.ai/ray.
austin castle retweeted
Introducing Ray2, a new frontier in video generative models. Scaled to 10x compute, #Ray2 creates realistic videos with natural and coherent motion, unlocking new freedoms of creative expression and visual storytelling. Available now. Learn more lumalabs.ai/ray.
austin castle retweeted
✨ Welcome to MAR BAR ✨
→ immersive beauty experience
→ interactive community space
→ next-gen creator content
Created with iR Studio for @MarialeOficial. Visit now on desktop or Android (iOS is coming!): irlty.io/marbar
Create your own immersive space with iR Studio for FREE for a limited time: irlty.io/4dPXS7e
austin castle retweeted
Want to learn more about our browser-based tool for building #immersive experiences? 🥽✨
Join our Discord Community and chat with the team! Our next Office Hours call is tomorrow, Oct. 24 at Noon ET / 9AM PT: irlty.io/officehours
austin castle retweeted
Using photogrammetry of an old TV's circuitry to generate an aerial view of a post-apocalyptic cityscape through @runwayml Gen-3 V2V. Did I ever mention I’m obsessed with experimentation?























