Skip to content

NodeTool Cloud is in alpha. Try it →

Text-to-image · Pruna AI

P-Image in a visual AI workflow

Run Pruna AI's P-Image in a visual AI workflow: sub-second text-to-image and multi-image editing, at provider list price.

P-Image in the NodeTool canvas

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

P-Image is a text-to-image model from Pruna AI built for production use, with generation under one second. P-Image Edit handles multi-image editing at the same speed.

Both have LoRA variants that load trained LoRAs from Hugging Face, so a custom style or subject can run through the same fast path.

NodeTool is bring-your-own-key, so you call P-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 and image editing
Speed
Under 1 second per generation
Models
P-Image, Edit, and LoRA variants of both
Inputs
Prompt, size, seed, LoRA weights

Where to run P-Image

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

ProviderSetting for your key
ReplicateREPLICATE_API_TOKEN

Frequently asked questions

How fast is P-Image?
Pruna AI lists it as a sub-one-second text-to-image model for production use.
Can P-Image use my own LoRA?
Yes. The LoRA variants load trained weights from Hugging Face, including ones trained with Pruna's trainers.
What does P-Image cost in NodeTool?
NodeTool adds no per-image fee. You pay the provider that serves P-Image at its list price, with your own key.

Run P-Image your way.

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

Download NodeTool