Skip to content

NodeTool Cloud is in alpha. Try it →

Text-to-image · Stability AI

Stable Diffusion 3.5 in a visual AI workflow

Run Stability AI's Stable Diffusion 3.5 in a visual AI workflow: Large, Large Turbo, and Medium text-to-image, at provider list price.

Stable Diffusion 3.5 in the NodeTool canvas

Fresh Stable Diffusion 3.5 examples are on the way. Meanwhile, here's the NodeTool canvas where you'll run it.

Stable Diffusion 3.5 is Stability AI's text-to-image family. Large generates high-resolution images with fine detail across artistic styles and produces varied outputs from the same prompt, thanks to Query-Key Normalization. Large Turbo targets fewer inference steps. Medium is a 2.5 billion parameter model with an improved MMDiT-X architecture.

Each node takes a prompt, a negative prompt, a seed, and a guidance value. An optional input image and prompt strength turn the same node into an image-to-image step.

NodeTool is bring-your-own-key, so you call Stable Diffusion 3.5 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-to-image
Models
Large, Large Turbo, and Medium
Medium size
2.5 billion parameters
Inputs
Prompt, negative prompt, seed, guidance, optional image

Where to run Stable Diffusion 3.5

NodeTool is bring-your-own-key: you call Stable Diffusion 3.5 through a provider you already have access to and pay their list price — no credits, no markup. These providers serve Stable Diffusion 3.5 today.

ProviderSetting for your key
ReplicateREPLICATE_API_TOKEN

Frequently asked questions

Which Stable Diffusion 3.5 model should I use?
Large for detail, Large Turbo when you want fewer inference steps, and Medium when you want the smaller 2.5 billion parameter model.
Does Stable Diffusion 3.5 support negative prompts?
Yes. All three nodes take a negative prompt, a seed, and a guidance value.
What does Stable Diffusion 3.5 cost in NodeTool?
NodeTool adds no per-image fee. You pay the provider that serves Stable Diffusion 3.5 at its list price, with your own key.

Run Stable Diffusion 3.5 your way.

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