The Developer Platform for World Models.

San Francisco
Joined November 2025
Introducing NVIDIA Cosmos-3-Nano on Reactor. Two new models, available now via the Reactor API. • Sim-Bimanual predicts what a robot sees as you move its arms and grippers. • Sim-Transfer turns simulations into photorealistic video. Try them now: reactor.inc/cosmos-bimanual
7
15
8
53
4,281
reactor retweeted
Introducing NVIDIA Cosmos-3-Nano on Reactor. Two new models, available now via the Reactor API. • Sim-Bimanual predicts what a robot sees as you move its arms and grippers. • Sim-Transfer turns simulations into photorealistic video. Try them now: reactor.inc/cosmos-bimanual
7
15
8
53
4,281
Sim-Bimanual: preview robot actions before running them on hardware. • Compare predicted outcomes of action plans. • Prototype robot controls without physical hardware. • Generate robot’s-eye demonstrations from action sequences. Try it here: reactor.inc/cosmos-bimanual
1
6
297
Sim-Transfer: turn simulation into photorealistic video. • Create training examples across lighting and material conditions. • Re-render robot demonstrations in new environments. • Turn rough 3D scenes into realistic previews. docs.reactor.inc/robotics/co…
6
191
Introducing Eden-Live, a realtime generative renderer by @tripoai. • Turn 3D scenes and prototypes into rich interactive worlds by redrawing them with Eden-live. • Restyle any scene live with references images + text. • Edit the prompt on the fly. Available Day 0 on Reactor.
20
12
6
95
8,943
Excited to share the official open source release of FastH3 Omni in collaboration with @haoailab, following last week’s preview. Try the model now on Reactor: reactor.inc/models/fast-h3-o…
As promised, FastVideo open-sources @MiniMax_AI FastH3 Omni, training code included! 🚀 - Real-time gen @ 12x faster on NVIDIA Blackwell - NVFP4/FP8 for Spark + RTX! - ComfyUI day-0 Collab with @NVIDIAAI , Nuva Lab @nuvalab and Reactor @reactorworld Open source must win! ♥️
9
7
2
56
4,051
Join us next week at Long Horizon Summit by @encord_team and learn about robotics on Reactor! 📅 Oct 20–21 📍 Fort Mason, San Francisco 🤖 Booth SU #1 There may or may not be limited edition Reactor swag if you track us down...
6
1
2
22
2,190
Join us in conversation with Will Lin from FastVideo @haoailab as we get technical about all things realtime video! Live from 12:30 PT. xitter.cf/i/broadcasts/1jxXgBlMA…
3
3
2
25
2,710
The future of media is so bright
In celebration of our FastH3-Omni launch, I vibecoded a pre-visualization studio. Now today, I'm down in LA showing it to studios. What you're seeing here is generated all in real-time, just from reference images and prompts. ⚡️ Open Source repo is in the comments to get started with this on the Reactor API!
1
30
2,296
We're honored to be named to the #Disruptors60 Class of 2026 curated by @Greenfield Partners at @TechCrunch Disrupt. Thank you to our team, and to the customers and partners who helped us get here.
8
4
2
34
1,798
reactor retweeted
Introducing FastH3-Omni. The fastest and highest-quality open-source version of realtime H3 by @MiniMax_AI, post-trained by FastVideo @haoailab with @nuvalab. Exclusive preview on the Reactor API until 10.20.2026. • First and last frame conditioning • Audio input + strong dialogue • Up to 3 reference images • Frontier-level performance
39
61
36
429
72,550
Introducing FastH3-Omni. The fastest and highest-quality open-source version of realtime H3 by @MiniMax_AI, post-trained by FastVideo @haoailab with @nuvalab. Exclusive preview on the Reactor API until 10.20.2026. • First and last frame conditioning • Audio input + strong dialogue • Up to 3 reference images • Frontier-level performance
39
61
36
429
72,550
We made the Wan VAE decoder 2.2x faster for real-time world models. Decode time per chunk went from 133.8 ms to 60.2 ms with the same output quality, 10% faster than vLLM-Omni’s fast path and 1.7x faster than SGLang’s. Wan-based decoders are used in Cosmos 3, DreamZero, Lingbot-World 2 and many other world models. On a single B200, Lingbot-World goes from about 36 to 46 fps. Read the full article: reactor.inc/blog/optimizing-…
21
6
4
86
8,876
Join our CTO @_bschmidtchen and @nebius for a live webinar on October 15 at 9AM PT: “What Makes Real-Time AI Video Possible?” We’ll cover our custom inference stack, what developers are building on Reactor, and how Nebius keeps interactive sessions fast and dependable under load. Register: nebius.com/events/webinar-sc…
2
3
1
24
2,106
Yesterday, 100 builders spent a day in NYC making things with world models at the Reactor x Google hackathon. Thank you to every participant, and to @Google for hosting us.
6
3
28
1,766
The first real-time models supported in @ComfyUI. All Reactor models now run as nodes in your workflow, from world models to live try-on and subject replacement. Try it now: github.com/reactor-team/comf…
Real time character control demo using @reactorworld
6
1
2
34
2,308
Introducing WorldPlay2, the latest world model running on Reactor by @TencentHunyuan. Move through a world that stays consistent, and steer what happens in it with a prompt as you explore. Try the demo now: reactor.inc/worldplay2 Project page: worldplay2.github.io/
12
23
10
230
18,942