DNA Insider
繁中
Back
Official Source· AWS Artificial Intelligence· AI· Published Sep 30, 2026

AWS Demonstrates Image and Video Generation With vLLM-Omni on SageMaker AI

AWS’s Part 2 tutorial shows how to deploy FLUX.2-klein and Wan2.1-VACE from one vLLM-Omni Deep Learning Container: generate an image through real-time inference, animate it into video through asynchronous inference, and retrieve the MP4 from Amazon S3.

AWS Demonstrates Image and Video Generation With vLLM-Omni on SageMaker AI

Full Report

AWS published “Generate images and video with vLLM-Omni on SageMaker AI – Part 2,” a technical tutorial demonstrating two generative-media models deployed from one AWS vLLM-Omni Deep Learning Container on Amazon SageMaker AI. It focuses on an image-to-video workflow carried out in two stages.

The tutorial first uses FLUX.2-klein to generate an image through real-time inference. It then uses Wan2.1-VACE for asynchronous inference to animate that image into a video, and demonstrates retrieving the resulting MP4 from Amazon S3.

The post is the second part of AWS’s vLLM-Omni and SageMaker AI tutorial series. The related Part 1 demonstrates deploying Qwen3-TTS on SageMaker AI and streaming generated speech through a Gradio application over a persistent bidirectional connection. Together, the examples cover speech generation and an image-to-video workflow.

Why This Matters

The tutorial gives developers a concrete example of combining image and video generation in one vLLM-Omni container deployment, while showing where real-time and asynchronous inference fit into the workflow. It also covers the practical handoff from image generation to video creation and MP4 retrieval, rather than presenting only a single-model task.

Evidence

Start with the primary evidence, then review supporting sources and context.

1 items

Primary Evidence

1
  • OfficialAWS Artificial IntelligenceDocumentOriginal

    Generate images and video with vLLM-Omni on SageMaker AI – Part 2

    Yadan Wei

    “Deploy two generative media models from one AWS vLLM-Omni Deep Learning Container on Amazon SageMaker AI. Generate an image with FLUX.2-klein through real-time inference, then animate it into video with Wan2.1-VACE through asynchronous inference, and retrieve the MP4 from Amazon S3.”

Recommended signals

Recommended by brand, topic, and recent related coverage

No more recommended signals right now

Official statement

Open original source
Back to Live FeedExplore more signals