SSyncDev

Cosmos3-Nano-Sim-Transfer

SyncDev model directory · Profile updated Nov 19, 2026

Compare with another model

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.

Key specifications

Specification score
14.8
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

  • Video input
  • Text input
  • Image input

Produces

  • Video output

Capabilities

VisionOpen weights

What is Cosmos3-Nano-Sim-Transfer?

Simulators are good at physics and bad at looking real. Cosmos3-Nano-Sim-Transfer keeps the simulator for the first job and takes over the second. Feed it per-frame depth maps, segmentation masks, edge maps or blurred renders from a tool like Isaac Lab, add a text prompt, and it returns photorealistic RGB video that preserves the geometry and motion the simulator specified.

Because the simulator still owns physics, scene state and ground-truth labels, a policy can train on realistic images while its reward signal stays exact.

Specification

Item Detail
Released 20 October 2026, Cosmos3 examples family
Base Cosmos3-Nano, post-trained for control and causally distilled
Architecture Mixture-of-Transformers, 16B trainable parameters
Inputs Control video (depth, segmentation, edge or blur) + text
Output Up to 600 frames at 480p, 30 fps playback
Batching Designed for up to eight parallel environments on one GB200
Runtimes PyTorch, vLLM-Omni, SGLang
Licence OpenMDW-1.1, commercial use allowed

The repository was opened at the end of August, but the release date given is 20 October.

Causal, few-step, chunked

Unlike offline transfer models, this one generates in small latent-frame chunks conditioned on cached history and the newest controls. That is what makes closed-loop use possible: the next frame can depend on what the policy just did. Throughput depends on batch size and settings, and no single FPS figure is published, so profile it.

Where it fits among its siblings

The Cosmos3 examples split by domain. Video-to-video transfer for driving lives in Transfer-Auto and its causal sibling Sim-Auto; robot-action simulation in Sim-Bimanual. Sim-Transfer is the general robotics renderer that sits on top of a classical simulator.

A quick validation plan

  1. Render one Isaac Lab scene with depth and segmentation.
  2. Generate video and re-segment it with your perception stack.
  3. Measure how far object masks drift from the simulator's ground truth over 600 frames.
  4. Train a small policy on transferred frames and test it on a handful of real images.

Step three is the one that matters. NVIDIA itself notes that simulator annotations describe the simulated scene and their alignment with generated imagery should be validated for each use.

A quick-start skill ships in the cosmos-framework repository. Other NVIDIA physical-AI releases are on the NVIDIA provider page.

How to evaluate Cosmos3-Nano-Sim-Transfer

Compare the model on the work you need to complete.

Tasks and inputs

Cosmos3-Nano-Sim-Transfer is listed for Text-to-video, Video-to-video. It accepts video, text, 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

Simulator-rendered control video such as depth maps, segmentation masks, edge maps or blurred images, plus a text prompt.

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-Auto

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.

— 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