vfx.ai

AI for movie visual effects • Premium domain name available for purchase via @spaceship

[vfx.ai @vfx_ai]

https://t.co/gPCl3bJ4uY is available for purchase.

Short, premium .ai domain at the exact intersection of Visual Effects and Artificial Intelligence.

Perfect for AI video tools, generative VFX, film studios, post-production houses, or next-gen creative platforms.

[Koh Terai @koh_terai]

I built a list of MCP tools for AI filmmaking.

https://t.co/dpd7BtD6vZ

[AIQUEST @AiquestAcademy]

Training 3D motion AI used to require expensive motion capture studios.

Not anymore.

VideoMDM generates highly accurate 3D human motion using ZERO 3D ground truth. It trains purely on 2D monocular videos like NBA broadcasts.

The math: they proved a depth-weighted 2D reprojection loss is equivalent to direct 3D supervision. This unlocks infinite training data for 3D animation and gaming.

Project demo page is available.
#GenerativeAI #VideoMDM

[Wildminder @wildmindai]

Surflo. turns a few standard photos into clean 3D models for game dev/VR.
- creates usable meshes
- geometric consistency
- predicts millions of oriented surface points
- beats VGGT-1B and DepthAnything-3

https://t.co/fCwoeY9TBK

[Andy Cheng @DrTunnels]

Introducing Flex4DHuman:
a video diffusion model that turns a single video or sparse camera views into synchronized multi-view videos using camera-pose and text conditioning.
The generated views can be reconstructed into 4D Gaussian splats for AR/VR, gaming, and video reshooting.

🌐https://t.co/UhXzpuvuK1

[1/4]

[Google Flow @FlowbyGoogle]

Calling all filmmakers!

Google is partnering with @XPRIZE to challenge you to shape a brighter tomorrow. Submit a 3-min trailer utilizing any production method: live-action, animation, or AI tools (like Google Flow!) winner gets $2.5M+ in funding to bring your full feature film to life. $1M in prizes for runners-up.

Learn more and apply: https://t.co/pX7d8jJuhx

[Arena.ai @arena]

Exciting news: Gemini Omni Flash is now #1 in the Video Arena (both Text-to-Video and Image-to-Video)!

For Text-to-Video this is a massive +158 pt improvement over Veo 3.1 (1080p) and a large +61 pt lead over the next best model, Seedance 2.0.

Congrats @GoogleDeepMind for this huge milestone!

[AI Research @airesearch_ai]

🚀SCAIL-2 just dropped — Z ai's new end-to-end character animation model that ditches skeletons entirely! !🔥

One model handles single-char, multi-char interactions, replacement, zero-shot animal driving.

Mind-blowing results !👀
https://t.co/6CyTkaNOk3

[Mervin Praison @MervinPraison]

Meta's DINOv3 just made training-free segmentation real.

INSID3 segments anything from one example — no fine-tuning, no labels, no training data.

Just frozen features. Just one shot.
Foundation models are rewriting what's possible.

Link in the first reply below.

[Jorge Condor @Arcanous98]

Together with @miazga02, we are announcing today Beyond Spherical Harmonics. We explored if we could do better than Spherical Harmonics in #3DGS, and found a few very interesting takeways in the process.

Code in #gsplat and paper released today
https://t.co/xERT2cimet

🧵🧵🧵

[Autodesk Flow Studio @adskflowstudio]

Studio-grade VFX used to mean weeks of setup and blockbuster budgets.

Now, technology like Flow Studio is closing that gap, putting markerless motion capture, Video to 3D scene technology, and Text & Image to 3D asset generation in the hands of every creator.

Editable, and ready to export straight into your existing pipeline.

Try Autodesk Flow Studio: https://t.co/htEWC7zxIl

[RADU CIUS @CiusRadu]

I’m excited to share a new demo
Houdini AI Assistant: https://t.co/3RxHdeXGld

In this demo I tested:
• MaterialX shader generation
• Pyro
• FLIP
• RBD
• Animation Maker
#Houdini #MaterialX #Solaris #USD #PyroFX #VFX #TechnicalArtist #AIforVFX

[Suzanne @trysuzanne]

🚨The Suzanne API is here 🚨

One call -> full production level 3D

Studios, labs and product teams are already building on it.

visit https://t.co/K36c4Sheaj to get access

[CVPR Journey to Awards Workshop @Journey2Awards]

As we come to the end of the workshop, we are pleased to announce the accepted papers for the First Workshop on Journey to the Awards: Generative AI for Movie-Grade Video Production (J2A) at #CVPR2026.

Congratulations to all authors!

[Michael Black @Michael_J_Black]

I’ve been capturing 3D human motion for 30 years and today is maybe the biggest day in that history. We are presenting MAMMA at CVPR (oral session 2A). MAMMA is a markerless multi-camera system that has accuracy similar to marker-based systems.

[Reve @reve]

Today, we’re launching Reve 2.0, the best 4K image model in the world.

We invented a new way to generate and edit any image using precise layouts. For the first time, it’s possible to create images you can touch.

[Sparseal @sparseal]

Introducing CozyBlanket Pro

A next-generation mesh optimization and cleanup toolkit, built from the ground up with AI-assisted retopology, cutting-edge UV tools, and powerful tool system to transform complex geometry into clean, efficient, production-ready assets.

[Larus Canus @MrLarus]

😱AI flight control is getting crazy!

One red line controlled this first-person Harry Potter-inspired Quidditch POV.

Ride the broom, chase the Golden Snitch, fly through Hogwarts-style towers, skim over Black Lake, dive through a bridge arch, and return for the final catch. 🧹

Workflow breakdown in the comments 👇

[Black Forest Labs @bfl_ai]

Martin Scorsese is an advisor to Black Forest Labs.

He's spent six decades shaping how the world sees stories. Now he's helping us shape visual intelligence with human taste and craft at the center.

We sat down with him for a working storyboarding session using FLUX.

[Tripo @tripoai]

Introducing Project Eden, a world model research preview from @VASTAIResearch

Project Eden is a persistent, multiplayer world model that fundamentally breaks from existing paradigms by decoupling the underlying world state from visual rendering.

Instead of treating the world as a sequence of transient frames, Eden treats it as a structured, evolving environment that runs continuously, can be modified by user actions, and can be consistently observed from any viewpoint.

[Alex Patrascu @maxescu]

The ways you can manipulate footage with Omni are incredible.

I started with a Seedance 2.0 video and prompted different ways the footage could be reimagined, from The Backrooms to simply showing Polaroids on a table as the footage progresses.

Wild stuff from Google: