SiliconFlow icon

SiliconFlow

调用 SiliconFlow（硅基流动）AI 能力：Chat Completion / Embedding / Image / Rerank

Actions4

Image Generation → Generate

AI-generated

Summary

Generates images from a text prompt by sending a request to SiliconFlow’s image generation API for each incoming item.

Inputs

  • Model (required) — SiliconFlow image model ID; defaults to stabilityai/stable-diffusion-2-1.
  • Prompt (required) — Text prompt describing the image to generate.
  • Negative Prompt — Optional description of elements to exclude.
  • Image Size — Image dimensions: 512×512, 768×768, 1024×1024, 1024×576, or 576×1024. Defaults to 1024×1024.
  • Num Images — Number of images to request, from 1 to 4; defaults to 1.
  • Seed — Optional random seed. A value of 0 is omitted from the request, allowing a random seed.
  • Guidance Scale — Optional guidance scale, from 1 to 20; defaults to 7.5.
  • Num Inference Steps — Optional inference step count, from 1 to 100; defaults to 20.

Output shape

A list of n8n items containing the API response JSON for each incoming item.

The operation sends a POST request to /images/generations. Each response item is paired with its input item. If continue-on-fail is enabled, an item error is returned as `{ "error": "…" }.

Links

Discussion