Skip to content

NodeTool Cloud is in alpha. Try it →

Text-to-image · Runway

Gen-4 Image in a visual AI workflow

Run Runway's Gen-4 Image in a visual AI workflow: reference-guided text-to-image with up to three reference images, at provider list price.

Gen-4 Image in the NodeTool canvas

Fresh Gen-4 Image examples are on the way. Meanwhile, here's the NodeTool canvas where you'll run it.

Gen-4 Image is Runway's image model with references. You give it up to three reference images, tag each one, and describe the scene, and it builds the image around those subjects. Gen-4 Image Turbo is cheaper and 2.5 times faster.

References are a good fit for graphs: a character or product image from an upstream node feeds in, and the same references can drive many shots.

NodeTool is bring-your-own-key, so you call Gen-4 Image 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.

Modality
Text-to-image with reference images
References
Up to 3, with tags
Turbo
Cheaper and 2.5x faster
Inputs
Prompt, aspect ratio, resolution, seed

Where to run Gen-4 Image

NodeTool is bring-your-own-key: you call Gen-4 Image through a provider you already have access to and pay their list price — no credits, no markup. These providers serve Gen-4 Image today.

ProviderSetting for your key
ReplicateREPLICATE_API_TOKEN

Frequently asked questions

How many reference images can Gen-4 Image use?
Up to three, each with a tag you can refer to in the prompt.
Gen-4 Image or Turbo?
Turbo is cheaper and 2.5 times faster. Use Gen-4 Image when you want the full model.
What does Gen-4 Image cost in NodeTool?
NodeTool adds no per-image fee. You pay the provider that serves Gen-4 Image at its list price, with your own key.

Run Gen-4 Image your way.

Download NodeTool Studio and build across image, video, audio, and text with your own keys.

Download NodeTool