Diffusion

Dynamo SGLang supports three types of diffusion-based generation: LLM diffusion (text generation via iterative refinement), image diffusion (text-to-image), and video generation (text-to-video). Each uses a different worker flag and handler, but all integrate with SGLang’s DiffGenerator.

Overview

LLM Diffusion

Diffusion Language Models generate text through iterative refinement rather than autoregressive token-by-token generation. The model starts with masked tokens and progressively replaces them with predictions, refining low-confidence tokens each step.

LLM diffusion is auto-detected: when --dllm-algorithm is set, the worker automatically uses DiffusionWorkerHandler without needing a separate flag. For more details on diffusion algorithms, see the SGLang Diffusion Language Models documentation.

Launch

$
cd $DYNAMO_HOME/examples/backends/sglang
$
./launch/diffusion_llada.sh

See the launch script for configuration options.

Test

$
curl -X POST http://localhost:8001/v1/chat/completions \
>
  -H "Content-Type: application/json" \
>
  -d '{
>
    "model": "inclusionAI/LLaDA2.0-mini-preview",
>
    "messages": [{"role": "user", "content": "Explain why Roger Federer is considered one of the greatest tennis players of all time"}],
>
    "temperature": 0.7,
>
    "max_tokens": 512
>
  }'

Image Diffusion

Image diffusion workers generate images from text prompts using SGLang’s DiffGenerator. Generated images are returned as either URLs (when using --media-output-fs-url for storage) or base64 data, in an OpenAI-compatible response format.

Launch

$
cd $DYNAMO_HOME/examples/backends/sglang
$
./launch/image_diffusion.sh

Supports local storage (--fs-url file:///tmp/images) and S3 (--fs-url s3://bucket). Pass --http-url to set the base URL for serving stored images. See the launch script for all configuration options.

Test

$
curl http://localhost:8000/v1/images/generations \
>
  -H "Content-Type: application/json" \
>
  -d '{
>
    "model": "black-forest-labs/FLUX.1-dev",
>
    "prompt": "Explain why Roger Federer is considered one of the greatest tennis players of all time",
>
    "size": "1024x1024",
>
    "response_format": "url",
>
    "nvext": {
>
      "num_inference_steps": 15
>
    }
>
  }'

Video Generation

Video generation workers produce videos from text or image prompts using SGLang’s DiffGenerator with frame-to-video encoding. Supports text-to-video (T2V) and image-to-video (I2V) workflows.

Launch

$
cd $DYNAMO_HOME/examples/backends/sglang
$
./launch/text-to-video-diffusion.sh

Use --wan-size 1b (default, 1 GPU) or --wan-size 14b (2 GPUs). See the launch script for all configuration options.

Test

$
curl http://localhost:8000/v1/videos \
>
  -H "Content-Type: application/json" \
>
  -d '{
>
    "prompt": "Roger Federer winning his 19th grand slam",
>
    "model": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
>
    "seconds": 2,
>
    "size": "832x480",
>
    "response_format": "url",
>
    "nvext": {
>
      "fps": 8,
>
      "num_frames": 17,
>
      "num_inference_steps": 50
>
    }
>
  }'

See Also

• Examples: Launch scripts for all deployment patterns
• Reference Guide: Worker types and argument reference
• SGLang Diffusion LMs (upstream): SGLang diffusion documentation