# Stable Diffusion

1. To generate a Stable Diffusion model repository inside a Triton
container:

    - Ensure that you have access to gated repository [Stable
Diffusion](https://huggingface.co/benjamin-paine/stable-diffusion-v1-5)
    - `huggingface-cli` login can be done before you run the script or,
`--auth_token` option can be passed while running the script eg:
`python generate_SD_repo.py --auth_token=<hf_token>`
    - Run the `generate_SD_repo.py` script. The script is located at
“/opt/qti-aic/integrations/triton/release-artifacts/stable-diffusion-ensemble”,
which creates an `ensemble-stable-diffusion` model repository.
2. Start the Triton server: `/opt/tritonserver/bin/tritonserver
-model-repository=/path/to/ensemble-stable-diffusion`
3. Triton server takes about 2 minutes to start on the first go as it
needs to compile QPC.
4. Use `client_example.py` for testing.

Last Published: Aug 25, 2026

[Previous Topic
vLLM Backend](https://docs.qualcomm.com/bundle/publicresource/80-99100-3/topics/vllm-backend.md) [Next Topic
Text Generation Inference (TGI)](https://docs.qualcomm.com/bundle/publicresource/80-99100-3/topics/index_TGI-Serving.md)