AWS generates images, video and speech with vLLM-Omni on SageMaker AI
What happened
On 29 September 2026, AWS Machine Learning Blog published two tutorials on building multimodal generation applications with the vLLM-Omni DLC on SageMaker AI. The first, part two, demonstrates two endpoints using the same DLC image: a real-time endpoint runs FLUX.2-klein-4B to generate images, and an asynchronous endpoint runs Wan2.1-VACE-1.3B for image-conditioned video generation. A text prompt first generates a PNG, which is sent with a motion prompt through Amazon S3 to the video endpoint; the resulting MP4 is then retrieved from S3. The example includes a command-line workflow and an optional Streamlit interface. The second, part one, introduces deployment of Qwen3-TTS, using one persistent bidirectional connection for incoming text and outgoing audio streams so speech starts playing before generation finishes.
Written by AI from the reports · updated 2 d ago
Timeline
Follow the reports to see the event from each side.
- AWS Machine Learning BlogBuild real-time voice applications with vLLM-Omni on SageMaker AI – Part 1
AWS released a vLLM-Omni DLC for deploying Qwen3-TTS on SageMaker AI. A single persistent bidirectional connection streams text in and audio out, with playback beginning before generation finishes.
- AWS Machine Learning BlogGenerate images and video with vLLM-Omni on SageMaker AI – Part 2
AWS published a tutorial deploying two endpoints from the same vLLM-Omni DLC image on SageMaker AI: a real-time endpoint running FLUX.2-klein-4B for images and an asynchronous endpoint running Wan2.1-VACE-1.3B for image-conditioned video. A text prompt first generates a PNG, which is sent with a motion prompt through Amazon S3 to the video endpoint; the resulting MP4 is retrieved from S3. The example includes a command-line workflow and an optional Streamlit interface.
Heat of this event
Current heat 3·Peak in the comparable range 5（Sep 30 01:00）·Change over 24 hours in the comparable range –
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.