Generate images and video with vLLM-Omni on SageMaker AI – Part 2
AWS vLLM-Omni DLC enables unified text-to-image-to-video pipelines on SageMaker AI
AWS published a tutorial deploying FLUX.2-klein-4B and Wan2.1-VACE-1.3B via a single vLLM-Omni Deep Learning Container on SageMaker AI, enabling a text-to-image-to-video pipeline. The workflow uses a real-time endpoint for image generation and an async endpoint for video generation with S3 for output storage. This is a practical engineering guide rather than a major announcement, but signals AWS's push to unify multimodal inference serving under OpenAI-compatible APIs.