NodeTool Cloud is in alpha — run workflows in the browser, on your own keys.NodeTool Cloud is in alpha. Try it →
Product
StudioCloud (alpha)AgentsNode-based workflowsAI video editorAI image editorStoryboardsMCP serverSupported modelsDownloadSolutions
DevelopersMarketingGame developmentLocal-firstResearchersAll solutionsResources
TemplatesRecipesPresetsAd libraryCompare alternativesFAQSANA-Sprint in a visual AI workflow
Run NVIDIA's SANA-Sprint in a visual AI workflow: one-step text-to-image diffusion, at provider list price.
Fresh SANA-Sprint examples are on the way. Meanwhile, here's the NodeTool canvas where you'll run it.
SANA-Sprint is NVIDIA's 1.6B parameter text-to-image model. It uses continuous-time consistency distillation to generate in a single step.
The node exposes inference steps, an intermediate timesteps setting, guidance, width, height, and a seed, so you can move between one-step previews and a few-step render.
NodeTool is bring-your-own-key, so you call SANA-Sprint through a provider you already use and pay that provider's list price. The table below lists the providers that serve it and the model ids their `--list-models` output reports.
Where to run SANA-Sprint
NodeTool is bring-your-own-key: you call SANA-Sprint through a provider you already have access to and pay their list price — no credits, no markup. These providers serve SANA-Sprint today.
| Provider | Setting for your key |
|---|---|
| Replicate | REPLICATE_API_TOKEN |
Frequently asked questions
- What does one-step mean?
- SANA-Sprint is distilled so it can produce an image in a single diffusion step, instead of the dozens a standard model uses.
- Can I use more than one step?
- Yes. The node has an inference steps input.
- What does SANA-Sprint cost in NodeTool?
- NodeTool adds no per-image fee. You pay the provider that serves SANA-Sprint at its list price, with your own key.
Run SANA-Sprint your way.
Download NodeTool Studio and build across image, video, audio, and text with your own keys.