Skip to content

AI images

When you do not have a photo, you describe the picture you want in plain words and Sosyabot draws it for you.

Why use it

It saves you from hunting for stock photos. Type what you have in mind, and you get a brand-new image you can drop straight into your post.

Step by step

GenerateUse in post
Three simple steps: describe it, generate it, use it.

Describe what you want

In the image box, type a short, clear description of the picture you have in mind. For example: a cup of coffee on a wooden table near a window.

Generate the image

Click Generate. Wait a few seconds while the picture is created for you.

Pick it and add it to your post

When the image appears, click it to insert it into your post. If you do not like it, change your description and generate again.

TIP

The more specific you are, the better the result. Mention the subject, the setting, the colors, and the mood. "A happy dog" gives a plain result; "a happy golden dog running on a sunny beach" gives a much nicer one.

Good to know

  • Each image you generate costs 5 credits. (For comparison: text or inline AI is 1 credit, an image is 5, a video is 20.)
  • Every picture you make is saved automatically, so you can find and reuse it later.
  • If a result is not quite right, just tweak the words in your description and try again.
For developers

Backed by POST /api/v1/ai/images. Request body: { prompt, provider: "openai" | "stability", size? }.

  • openai uses dall-e-3 (OPENAI_API_KEY required); size is passed straight through.
  • stability uses stable-diffusion-xl-1024-v1-0 (STABILITY_API_KEY required); default size 1024×1024, cfg_scale 7, steps 30; response is base64.

The result is downloaded (OpenAI) or decoded (Stability) and persisted via downloadFileFromUrl() / saveAiImage() into the Files Library; the response returns fileId and url. Rate limit: 5 generations per user per minute (in-memory map in aiImage.controller.ts). Cost: 5 credits per call.