Cosmos-Predict2 Text2Image Video2World | ComfyUI Workflow

Fast and real! NVIDIA Cosmos with true physics.

Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning — you still choose inputs, prompts, and settings.

Open preloaded workflow on RunComfy

Open preloaded workflow on RunComfy (browser)

Why RunComfy first
- Fewer missing-node surprises — run the graph in a managed environment before you mirror it locally.
- Quick GPU tryout — useful if your local VRAM or install time is the bottleneck.
- Matches the published JSON — the zip follows the same runnable workflow you can open on RunComfy.

When downloading for local ComfyUI makes sense — you want full control over models on disk, batch scripting, or offline runs.

How to use (local ComfyUI)
1. Load inputs (images/video/audio) in the marked loader nodes.
2. Set prompts, resolution, and seeds; start with a short test run.
3. Export from the Save / Write nodes shown in the graph.

Expectations — First run may pull large weights; cloud runs may require a free RunComfy account.

Overview

This comprehensive ComfyUI workflow harnesses NVIDIA's Cosmos-Predict2, a cutting-edge physical world foundation model designed for high-quality visual generation. Create stunning images from text descriptions or transform videos with exceptional physical accuracy and environmental interactivity. The model excels at simulating complex physical phenomena and dynamic scenes, making it perfect for industrial simulation, autonomous driving visualization, urban planning, and scientific research applications.

Important nodes:

• EmptySD3LatentImage

• CLIP Text Encode (Prompt)

• CosmosPredict2ImageToVideoLatent

Notes

Cosmos-Predict2 Text2Image Video2World | ComfyUI Workflow — see RunComfy page for the latest node requirements.