Commands from "Make Your First Gaussian Splat From Your Own Photos" (AssociationAI.ai, October 7, 2026)

Copied exactly from the tutorial. The tutorial took them from the Nerfstudio and COLMAP documentation as it read on October 7, 2026; the only change is the COLMAP version pin (=3.8) in step 8. We have not run these steps ourselves yet.
Command lines are indented by four spaces. Placeholders in braces or angle brackets are the documentation's own; replace them with your own folder names and paths.

Step 3. Create and activate a separate environment for the install.
    conda create --name nerfstudio -y python=3.8
    conda activate nerfstudio
    python -m pip install --upgrade pip

Step 4. Install the machine learning library at the version the guide pins.
    pip install torch==2.1.2+cu118 torchvision==0.16.2+cu118 --extra-index-url https://download.pytorch.org/whl/cu118

Step 5. Install the GPU toolkit that Nerfstudio's extensions are built with.
    conda install -c "nvidia/label/cuda-11.8.0" cuda-toolkit

Step 6. Install the extra GPU bindings the guide lists next.
    pip install ninja git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch

Step 7. Install Nerfstudio.
    pip install nerfstudio

Step 8. Install COLMAP, pinned to version 3.8.
    conda install -c conda-forge colmap=3.8
Note: the pin matches the version the custom data guide's own check expects.

Step 9. Print COLMAP's help screen to confirm the install.
    colmap -h

Step 10. Work out where each photo was taken.
    ns-process-data images --data {DATA_PATH} --output-dir {PROCESSED_DATA_DIR}
Note: use your photo folder as the data path and a new folder name for the output.

Step 11. Train the splat on the processed folder.
    ns-train splatfacto --data <data>

Step 12. Open the viewer address in your browser while training runs.
    ns-viewer --load-config {outputs/.../config.yml}

Step 13. Export the trained splat, pointing at the same config file.
    ns-export gaussian-splat --load-config <config> --output-dir exports/splat

Worked example from the tutorial (invented folder names: booth-photos, booth-processed)
    ns-process-data images --data booth-photos --output-dir booth-processed
    ns-train splatfacto --data booth-processed
    ns-export gaussian-splat --load-config outputs/.../config.yml --output-dir exports/splat
