Pedro Gengo 🐉

Yesterday I saw a website called pixelicious.xyz and I found it amazing! So, last night, I decided to try to create a pixel art tool by myself to have fun and understand how it works under the hood. Follow the thread if you want to know more! 1/4

runway characters represents an important step forward in research: real time video gen that feels smooth, natural, and yet still consistent. Super proud of the team and this amazing accomplishment!

Introducing, Runway Characters. Real-time intelligent avatars that turn the internet into a conversation. Deployable anywhere via the Runway API, Runway Characters can be customized in any way across every style. All with the ability to embed bespoke knowledge banks, custom voices and instructions. Start integrating Runway Characters directly into your apps, websites, products and services today. Available now at the link below.

We showed 1,000 people a series of videos. Some real and some generated with Gen-4.5. Over 90% of people couldn't tell the difference. Can you? Take the test at the link below.

Introducing Image to Video for Gen-4.5, the world's best video model. Built for longer stories. Precise camera control. Coherent narratives. And characters that stay consistent. Gen-4.5 Image to Video is available now for all paid plans.

Introducing our new frontier video model, Runway Gen-4.5. Previously known as Whisper Thunder (aka) David. Gen-4.5 is state-of-the-art and sets a new standard for video generation motion quality, prompt adherence and visual fidelity. Learn more below.

Reframe is here. Outpaint and resize any uploaded video, image, or #DreamMachine creation into every format you need. Customize and reposition freely on the canvas to make every version of your story fit perfectly. Goodbye cropping. Hello creative freedom.

@ariG23498 @karpathy @lusxvr @andimarafioti Amazing (as always)!!!

🚨 nanoVLM: Train a Vision Language Model in under 1000 lines of code 🚨 Taking inspiration from @karpathy's nanoGPT, we are excited to release nanoVLM today, the simplest repository to understand and train your very own VLM. You can run the training script on a FREE COLAB NOTEBOOK! 🤗 The code is written in pure @PyTorch with no bloat and no abstractions. You can read through the entire code base in a day and start experimenting (great for a weekend project). We equip the community with: 1. Vision Backbone ~150 lines 2. Language Decoder ~250 lines 3. Modality Projection ~50 lines 4. VLM ~100 lines 5. A simple training loop ~200 lines This is under active development, and in the coming weeks we will be releasing some really cool things. The following tweet will have all the details for you to get started immediately.

Introducing A Branding New ComfyUI Look and Native API Nodes! Seamlessly integrate 11 amazing online visual AI models into ComfyUI, including @bfl_ml Flux, @Hailuo_AI, @minimax_ai, @Kling_ai, @LumaLabsAI, @PixVerse_, @recraftai, @StabilityAI, @Google Veo2, @ideogram_ai, @OpenAI GPT image-1, and @pika_labs! 🔹One platform, 11 models, 65 nodes, all at once 🔹Chain the APIs with open models and workflows 🔹No hardware limitation!

Introducing #Ray2 Camera Motion Concepts in #DreamMachine — 20+ precision-tuned camera motions designed for smooth cinematic control and great reliability. Concepts compose with each other making hundreds of impossible new camera moves possible. Available now.

Ray2 Flash is now available in API.

@_sam_sinha_ GOAT 🐐

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.

Video to Audio is now here in #DreamMachine. To generate sound for your video generations, just select the new "Audio" button. Create with a single click or describe with prompts for more customized direction. Audio is available now in beta for free to all users.

Image to Video with #Ray2 is here. Drop any image into Dream Machine to make it a video and bring it to life — from historic artifacts and paintings to memes, custom art and photos of any kind. Available now.

Introducing Upscale to 4K – enhance any #DreamMachine video up to 4K resolution with all-new stunning detail. Natively generate in 720p or 1080p, then upscale your creations to 4K for next-level clarity. Available now.

The Ray2 API is here. Developers can now build and scale creative products with our most advanced video generation model yet. From cinematic realism to dynamic motion, the possibilities are limitless. Start building today lumalabs.ai/dream-machine/….

We are thrilled to announce the release of the AI Video Starter Kit by @fal in partnership with @bfl, @LumaLabsAI, @genmoai, @TXhunyuan, @Hailuo_AI, @Kling_ai, @synclabs_so, @play_ht, @LTXStudio, uploadthing by @theo and @vercel. AI Video Starter Kit is an open source in browser editor for AI video.

From basic prompts to cinematic results. 💭➡️🎥 With @LumaLabsAI's new frontier video model, Luma Ray2, you can generate high-quality videos from natural language inputs. Bring your visions to life with rapid, dynamic video content creation. #AWS 👉 go.aws/3E9p1FI

No, this is NOT another episode of The Last of Us. It is FULLY generated with AI! This is @LumaLabsAI #Ray2 🚀 ⚡️Presenting "RUN"⚡️ Having early access to Ray2, this trailer is created entirely with an advanced state-of-the-AI-art text-to-video model by #LumaDreamMachine The quality of shots, visual consistency, camera movement, and precise understanding of the prompts make it a perfect fit for cinematic action! Welcome to the new era of AI filmmaking. 2025 is gonna be awesome! Thanks to the amazing Luma Team for this fantastic new tool! @Kyrannio @vibrantnebula @tuhin @hyperparticle @gravicle @theopanag7 @_sam_sinha_ @baaadas @alexyu00 @AndrewPrifer @AnjneyMidha & all!

@baaadas @_sam_sinha_ @LumaLabsAI I can recommend @_sam_sinha_

@_sam_sinha_ @LumaLabsAI Yes!

More amazing things are on the way for @LumaLabsAI #Ray2 !!! Join us: lumalabs.ai/join (or DM me)