Mario Rocha
@Mario_r_o_c_h_a
ᯅ Crafting Immersive 3D Experiences to transform Real Estate Sales. Aerial 360 photography and AI enthusiast. | Co-founder in @renderinc.mx
Вам может понравиться
Real-time controllable video is here! Watch me demo the new @odysseyml model ⬇️ You create a scene and then prompt actions or changes via text prompt or suggestions that pop-up. It's not perfect (you'll see some artifacts) - but it's INSANELY fast and very fun.
Update 6 Released for Mesh2Motion! 🎉 ✨ Explore page to view all animations ✨ Added a few animations for bird and fox ✨ Better control rigs for animators Full release notes: mesh2motion.org/news Try it out: app.mesh2motion.org Would love feedback
Add a skeleton, spider, black cat or whatever haunts your imagination straight into your video with object insertion in Flow. Just click on the pencil icon on your video, type out your vision, and watch the story unfold.
AI is moving faster and faster Google is dropping Genie 3, it can not only generate 3D world but also characters you can also interact with the elements inside
Announcing two new technologies to empower developers to build with #generativeAI at scale: ✅ Generative AI support in Vertex AI ✅ Generative AI App Builder Learn more here → goo.gle/3TgCXkO
Holy shit... Google just built a system to build AI apps for free I built this 'Image Editing' app while testing Google's new app builder, and the result is insane. Full breakdown 👇
Introducing LTX-2: the most complete open-source AI creative engine. - Synchronized audio and video generation - Native 4K fidelity, up to 50 fps and 10 s+ sequences - API-first design for seamless integration into creative pipelines - Runs efficiently on consumer GPUs - Fully…
Volinga Plugin Pro lets you relight 3D Gaussian Splats in Unreal Engine The #UE5 plugin is pitched as a 'major leap' in integrating #3DGS into #UnrealEngine pipelines for #VFX and #virtualproduction Check out its key features: cgchannel.com/2025/10/voling… #relighting @VolingaAI
やっと完成した！これが最後のトレイラーです！ 撮影した素材をA Iを用いたグリッチ、ノイズ表現をする。これだけがテーマでしたが、face swap、Body Replacement、diffusion upscale、と色々やっています。全てローカル生成AIとBlenderとflameでやっています。…
🌍 Announcing the latest advancements to Google Earth AI - a platform designed to unlock a new level of planetary understanding. ➡️ bit.ly/4quoKkA 🔗 Geospatial Reasoning framework 🧠 Deeper Insights in Google Earth 🎉 Expanded access to Earth AI
Google Veo 3.1 just killed ad agencies now you can create studio level ad in seconds, keep actor, outfit, product, environment consistent here's how to do it on Arcads
I like big splats and I cannot lie. PlayCanvas's new LOD streaming system for 3D Gaussian Splatting is a big deal. It's a key step towards splatting the world and making it explorable. Check out a live demo below in your browser.
Trying out the new Hailuo 2.3 preview. > a tiktok dancer is dancing on a drone, doing flips and tricks
Today's addition to the Three.js Journey's selection: Jordan Breton's Portfolio 👉 jordan-breton.com Great job @JordanBretonDev ! 🔗 linkedin.com/in/jordan-bret… Go checkl all the selected projects 👉 threejs-journey.com/selection #threejsJourney #threeJs
A banger is coming. I got early access to @Hailuo_AI 2.3… And honestly? It’s a visual and technical beast. 🔁 Share if you're hyped to see more exemples
AI video just leveled up with @ltx_model Holy Moly: LTX-2 can generate native 4K video at 50 fps — complete with synchronized sound and dialogue. No tricks, no upscaling. The first true cinematic AI engine built for real creative workflows.
Today, PlayCanvas is sharing a live demonstration of our Streaming LOD system for 3D Gaussian Splatting. Dynamically stream vast splat-based scenes of arbitrary complexity. 100% free. 100% open source. Demo link 👇 [1 / 2]
阿里的 Wan2.2 有点东西！使用方法见评论👇 一段你在说话的视频，一张相同分辨率的其他人物的图片，就能让你不露脸出镜，i 人主播福音！ 理论上直接开直播问题不大，再把音色换一换，死肥宅摇身一变性感美女，也可以去收割其他死肥宅了🤪
This is very exciting. In seconds, I could generate a small splat-based environment I could explore in VR on SuperSplat. The generated splat was very lightweight - and only 2.2MB using the @PlayCanvas SOG format.
Today, we are open-sourcing Hunyuan World 1.1 (WorldMirror), a universal feed-forward 3D reconstruction model. 🚀🚀🚀 While our previously released Hunyuan World 1.0 (open-sourced, lite version deployable on consumer GPUs) focused on generating 3D worlds from text or…
⚡️Your video → a 3D scene. Just in seconds.⚡️ Only *one* model. No more steps❌. Just results🔝. #WorldMirror reconstructs everything (3DGS, depth, cameras) from any inputs (image, video, 3D prior) *all-at-once*! code: github.com/Tencent-Hunyua… arxiv: arxiv.org/abs/2510.10726
United States Тренды
- 1. SNAP 1.02M posts
- 2. Don Lemon 4,055 posts
- 3. $NVDA 87K posts
- 4. Jamaica 261K posts
- 5. Nelson 29.8K posts
- 6. #MarcelReed N/A
- 7. #LumioseOOTD N/A
- 8. Tucker 101K posts
- 9. Riley Gaines 106K posts
- 10. Wikipedia 123K posts
- 11. Nokia 15.7K posts
- 12. Fuentes 81K posts
- 13. Western Union 6,144 posts
- 14. #NationalFirstRespondersDay 1,545 posts
- 15. Amare 2,557 posts
- 16. Hurricane Melissa 186K posts
- 17. Jensen 11.9K posts
- 18. Grokipedia 190K posts
- 19. RedSec 19.9K posts
- 20. New Hope 35.4K posts
Something went wrong.
Something went wrong.