Let's remove VAEs and ViTs from video models!
🚀 Introducing 𝗣𝗶𝘅𝗲𝗹𝗨𝗠𝗠: an encoder-free unified multimodal model for image and video understanding and generation, directly in pixel space.
Code and model available today!
🌐 nv-tlabs.github.io/PixelUMM
📄
⚡ One policy, millions of embodiments, over 200 robot models. Can we add yours?
We're building γ₀, a generalist RL policy for motion control trained across millions of randomized embodiments derived from a growing collection of more than 200 robot models.
@dranben Thanks for trying it! UniMate is an early step toward text-to-animation for any skeleton. Part of its capacity goes into handling different topologies, so it still trails specialized models on human motion. We plan to close that gap with more data.
@imost@GokulEpiphany Several of the open-source auto-riggers seem pretty good. SkinTokens is an improved version of UniRig, but I haven't tried it yet.
🪄 Bring your 3D characters to life with words!
Introducing UniMate: one unified model for text-driven animation across diverse skeletons—from humans and animals to articulated objects.
🎬 A rigged asset + a text prompt → motion.
No per-skeleton retraining needed!
🌐 linzhanmou.com/unimate/
@nazimadakli@rahul__gh0sh Thanks for giving it a try! Agreed, agentic approaches handle this better right now. Our data is still limited, which shows. If you can share some of your outputs, that would really help us improve.
@rahul__gh0sh@nazimadakli Nice work on the cost side! I think agentic systems also work well as a final refinement stage: let a motion diffusion model generate the base motion, then have the agent fix the details (contacts, constraints, timing). That might help with the more complex animations too.
@RisingSunInt_ Yes, with motion expansion you can chain prompts, and each segment continues from the end of the last one. That gives you seamless walks of any length without snapping.
New Open-Source AI Animator: Text-to-Animation for Humans, Animals, Creatures, Robots & More
UniMate generates motion from text prompts for rigged 3D characters. Describe an action and turn it into animation.
Highlights:
• One model, different skeletons—no separate retraining for each rig.
• Generate transitions between existing keyframes.
• Edit motion with text while keeping selected joints unchanged.
• Extend animations with a sequence of prompts.
• Export animated meshes as FBX and GLB.
• MIT-licensed code + downloadable preview weights.
github.com/Friedrich-M/Un…
@JohnnyB_222 Thanks! Yes, we support keyframe constraints during diffusion sampling (in-betweening, editing, expansion), and you can combine them with other test-time guidance, e.g. trajectory control.
@DSqi4TZ4nm29308@SIGGRAPHAsia Prompt tweaking alone is hard to control. Let your Codex refine the motion directly with Blender MCP: load the result into Blender and fix the bones and keyframes there.
@sebuzdugan Agreed, foot sliding is still an issue. We haven't designed a unified contact model for heterogeneous rigs (e.g. winged creatures or fish). A natural next step is adding a controller or IK post-processing to handle contacts.
30 Followers 222 FollowingCreative Director & Game Designer at Soul Flare. Working on Visions of Recollection. Pre-alpha demo is linked (not nearly as good as the current game 😂).
713 Followers 3K FollowingI make assets for video games. Throwing generous heaps of atmospheric environments, odd collectibles, and strange creatures out into game space.
245 Followers 2K FollowingLLM Post-Training/ Recursive Self-Improvement for Reasoning
Co-founder/ MTS @ReasonCoreAI
PhD @UCLA, Bachelors @iitbombay
Led a team of ~500 PhD researchers
533 Followers 3K Following𒀭𒂗𒆠 Some rules are golden. 𒀭𒎏𒋚 Meaning is Engineered🔧Optimistic humanist who believes we can decode the old, align the new, and reduce absurdity at scale
172 Followers 622 FollowingCounselor/ Active investor. 30 year old millenial trying to set my family up with 0 debt.
All the while working in social services. I might be crazy.
670 Followers 158 FollowingCS PhD at Stanford | Prev @physical_int, @ucsd_cse, @rai_inst, @StanfordSVL, @NUSingapore | Building intelligence across bodies and teams
2K Followers 241 FollowingPrincipal Animation Programmer @epicgames on @unrealengine. Previously anim tech lead at @amazon and other places. I like coding, investing and gaming.
425 Followers 2K FollowingCEO & Founder @origin_autonomy | Building Time Machines for Construction!
Ex-Founder - Perpule (Acq by Amazon) | AI x Robotics | ACM-ICPC World Finalist
1K Followers 376 FollowingAssistant Professor at Zhejiang University @ZJU_CHINA
Prev: Post-doc at UC Berkeley @berkeley_ai; PhD in CIS at UPenn @GRASPlab; BS at ZJU @ZJU_CHINA