Dynamo supports serving diffusion models across multiple backends, enabling generation of images and video from text prompts. Backends expose diffusion capabilities through the same Dynamo pipeline infrastructure used for LLM inference, including frontend routing, scaling, and observability.

Status: ✅ Supported | ❌ Not supported

TRT-LLM video output currently supports MP4 only and requires an NVENC-capable GPU. GPUs without NVENC are not supported for TRT-LLM video output.

For deployment guides, configuration, and examples for each backend:

• vLLM-Omni
• SGLang Diffusion
• TRT-LLM Diffusion
• FastVideo (custom worker)