Cosmos 3 Super Image2Video

Released
2026-05-31
Last refreshed
2026-06-01
Status
Researched 135d ago
Open weightsCommercial use: permittedMultimodalVisionOpen SourceVideo

Cosmos 3 Super Image2Video is a released vision model with open-weight; evaluate it while provider pricing coverage matures.

NVIDIA AI releases · 19 in the last 12 months · this family litChangelog →
Specifications
Family
Cosmos 3
Released
2026-05-31
Context
4K
Parameters
64B
Architecture
Mixture of Transformers
Specialization
video-generation
Openness
Open weights
License
OpenMDW 1.1Commercial use: permitted
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by
NVIDIA AI

Accelerated AI for enterprise solutions

Santa Clara, California, United States
Founded 2015
Website
Pricing

No tracked provider token pricing is available yet.

Links
Website HuggingFace

About

Cosmos 3 Super Image2Video is a 64B-parameter fine-tuned variant of Cosmos 3 Super specialized for temporally coherent image-to-video generation. Takes a single image (jpg/png/webp at 256p-720p) plus an optional text prompt (up to 4096 tokens) and outputs MP4 video with 5-400 frames (default 189) at up to 720p, with optional muxed AAC stereo audio at 48kHz. Ranked #1 on Artificial Analysis image-to-video leaderboard (open models). Available via Hugging Face Diffusers and vLLM-Omni.

Providers

No active provider routes are tracked for this model yet.

Capabilities

VisionMultimodalAudioFine-tuning

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

cosmos-3-super-image2video