NodeTool Cloud is in alpha — run workflows in the browser, on your own keys.NodeTool Cloud is in alpha. Try it →
HiDream in a visual AI workflow
Run HiDream in a visual AI workflow: Dev, Fast, and Full text-to-image variants, at provider list price.

Fresh HiDream examples are on the way. Meanwhile, here's the NodeTool canvas where you'll run it.
HiDream is a text-to-image model family. The Replicate listings run optimised builds from Pruna AI of the Full, Dev, and Fast variants, tuned with the Pruna optimisation toolkit. Newer HiDream models are also served by other providers.
The nodes expose a resolution, a seed, an output format and quality, and a speed mode, so you can trade latency against detail per run.
NodeTool is bring-your-own-key, so you call HiDream 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 HiDream
NodeTool is bring-your-own-key: you call HiDream through a provider you already have access to and pay their list price — no credits, no markup. These providers serve HiDream today.
| Provider | Setting for your key |
|---|---|
| AtlasCloud | ATLASCLOUD_API_KEY |
| fal.ai | FAL_API_KEY |
| Replicate | REPLICATE_API_TOKEN |
Frequently asked questions
- What are the HiDream L1 variants?
- Full, Dev, and Fast. The Replicate listings are Pruna AI optimised builds of each.
- Can I change speed per run?
- Yes. The nodes have a speed mode input along with resolution and seed.
- What does HiDream cost in NodeTool?
- NodeTool adds no per-image fee. You pay the provider that serves HiDream at its list price, with your own key.
Run HiDream your way.
Download NodeTool Studio and build across image, video, audio, and text with your own keys.