SSyncDev

Cosmos3-Nano-Sim-Auto

SyncDev model directory · Profile updated Nov 19, 2026

Compare with another model

Cosmos3-Nano-Sim-Auto is NVIDIA's open causal driving simulator: real-time multi-camera video and LiDAR that react to an AV policy's planned path.

Key specifications

Specification score
19.8
License
OpenMDW-1.1

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: Open weights; no hosted API price. GPU time is the cost, so confirm throughput on your own hardware.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Text input
  • Video input
  • Image input

Produces

  • Video output

Capabilities

VisionOpen weights

What is Cosmos3-Nano-Sim-Auto?

A driving policy that only ever sees recorded video never learns what happens after its own mistakes. Cosmos3-Nano-Sim-Auto closes that loop. The policy plans a trajectory, a World Scenario Map renderer turns it into scene controls, and the model generates what every camera and the LiDAR would observe next, chunk by chunk.

Release date: 20 October 2026. Its parent is the bidirectional Cosmos3-Nano-Transfer-Auto, and the whole point of the distillation is that this version can generate the next stretch of every sensor stream before the planner has to decide again.

Two stages from the base model

First, Cosmos3-Nano was post-trained on multi-sensor driving data including LiDAR, producing Transfer-Auto. Second, that model was causally distilled into this few-step generator. The architecture stays a 16-billion-parameter Mixture-of-Transformers.

What goes in and what comes out

  • Text describing weather, lighting and time of day, plus the camera configuration.
  • Per-view WSM controls from a renderer fed either by an AV policy's planned trajectory or by a human on a steering-wheel interface.
  • LiDAR range-map controls when LiDAR output is wanted.
  • Optional initial RGB frames and one initial measured LiDAR sweep.

Outputs are MP4 or streamed frames per view and LiDAR range-intensity maps convertible to point clouds.

Hard limits

Constraint Value
Views Up to 11, Hyperion 8.1 rig
LiDAR conditioning One initial sweep only; longer measured prefixes unsupported
Resolution 480p or 720p
Playback 10–30 fps across selected views
Tested GPUs H100, H20, H200, B200, B300, GB200, GB300 among others
Licence OpenMDW-1.1

For a custom rig, the documented path is to post-train Transfer-Auto on your sensors first and then repeat the causal distillation.

Is it good enough for your evaluation loop?

Run three checks before using it to score a planner:

  1. Consistency: drive a straight segment and confirm lane geometry stays put across all views.
  2. Responsiveness: issue a hard lane change and verify every camera and the LiDAR agree on the new pose.
  3. Drift: run the longest rollout you need and track when objects start to deform.

Any failure matters. Closed-loop scores built on a drifting world will mislead you.

Related NVIDIA models include the edge driving model Alpamayo 2 Edge; more video models are in the video-to-video directory.

How to evaluate Cosmos3-Nano-Sim-Auto

Compare the model on the work you need to complete.

Tasks and inputs

Cosmos3-Nano-Sim-Auto is listed for Text-to-video, Video-to-video. It accepts text, video, image and produces video. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Choose duration, resolution and frame rate together. Compare the cost of an accepted clip, including repeat generations.

Choosing a deployment

The weights are downloadable under OpenMDW-1.1. Check runtime support and size the complete model and working context for your expected concurrency.

Frequently asked questions

Sim-Auto is a causal-distilled, few-step version of Transfer-Auto, designed for real-time closed-loop simulation instead of offline generation.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

NVIDIA

Cosmos3-Nano-Sim-Transfer

Cosmos3-Nano-Sim-Transfer is NVIDIA's open 16B model that renders simulator depth, segmentation or edge maps into photorealistic robot video in real time.

— context

NVIDIA

Cosmos3-Nano-Transfer-Auto

Cosmos3-Nano-Transfer-Auto is NVIDIA's open 16B model that generates synchronised multi-camera driving video and LiDAR from map controls and a prompt.

— context

skywork

Matrix-Game 4.0

Matrix-Game 4.0 is Skywork's open set of 5B real-time video renderers that turn a running game's frames into clean styled video, per scene.

— context

Tencent

WeVisCut

WeVisCut is Tencent's 9B tool-calling agent that edits narration scripts into multi-minute videos through 12 editing tools and an editable Studio timeline.

— context

skywork

SkyReels-V3-V2V-14B

SkyReels-V3-V2V-14B is Skywork's 14B video-extension model that continues a clip for 5-30 seconds or cuts to a new shot, at 720p from a text instruction.

— context

AInVFX

AInVFX/SeedVR2_comfyUI

AInVFX/SeedVR2_comfyUI is a source-linked Hugging Face repository assigned to Video-to-video. Its recorded task interface accepts video and produces video.

— context