Agent skill · research science · nvidia
nv-generate-vae-finetune
Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. Not for clinical or production data approval.
Why this skill is useful
Adds a specialized script for finetuning a VAE model with specific configurations and data handling that the AI wouldn't generate on its own.
What it needs
Requires python installed locally. About 6k tokens when loaded. Last updated 2026-08-07. 2,816 stars on the source repository.
What this skill does
NV-Generate-VAE-Finetune Purpose Used for finetuning the NV-Generate-CTMR MAISI VAE/autoencoder from user-supplied CT or MRI NIfTI training volumes. Not for clinical interpretation, regulatory use, or approving synthetic data for production training. Upstream currently documents VAE training in trainvaetutorial.ipynb and provides configs/helpers, but not a scripts.trainvae CLI. This skill does not execute the notebook; it stages the required config/datalist glue locally and uses upstream helper APIs. Manifest I/O: inputs are datalist and databasedir; outputs are autoencodercheckpoint, discriminatorcheckpoint, and resultjson. The underlying training contract is the upstream config/env JSON (configmaisivaetrain.json + environmentmaisivaetrain.json, as used in trainvaetutorial.ipynb). The wrapper stages those JSON files for you and exposes the most-tuned fields as CLI flags; the sections below document the fields, their defaults, and how to monitor/tune a run. Instructions Read skillmanifest.yaml before changing arguments, side effects, or validation gates. Run scripts/runvaefinetune.py from the Medical AI Skills repo root. If a host agent exposes runscript, use runscript("scripts/runvaefinetune.py", args=[...]); otherwise run the Bash/Python command below. Use --preflight first when checking a new datalist; remove --preflight only when the user explicitly wants to launch GPU finetuning. For a staged preflight input bundle directory, use BUNDLE/preflightdatalist.json as the datalist and BUNDLE/preflightdataset as --data-base-dir when those files are present. Examples Validate and stage a preflight finetune check from an input bundle (the recommended first step — no GPU, no training). This is the single canonical command; replace INPUTBUNDLE and OUTDIR with your paths: For real GPU finetuning and other variations, see Usage below. Available Scripts Script Purpose Arguments --- --- --- scripts/runvaefinetune.py Primary entrypoint declared by skillmanifest.yaml. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nvidia/nv-generate-vae-finetune