Skip to main content
MindStudio
Pricing
BlogAbout
My Workspace
Image Generation Model

Stable Image Core

Stable Image Core is a text-to-image generation model from Stability AI, supporting style presets, aspect ratios, and multiple output formats.

PublisherStability
TypeImage
Context Window77 tokens
Released2024
Price$0.03–$0.04/image

Text-to-image generation with style presets

Stable Image Core is a text-to-image generation model developed by Stability AI and released in 2024. It accepts text prompts and converts them into images, with a 77-token context window for prompt input. The model supports a range of style presets, configurable aspect ratios, and multiple output formats, giving users direct control over the visual style and composition of generated images.

Stable Image Core is designed for use cases where structured image generation with predictable stylistic control is needed. Its inputs include a negative prompt field to exclude unwanted elements, a seed parameter for reproducible outputs, and selectable style presets that guide the aesthetic of the result. These features make it well-suited for creative workflows, prototyping visual concepts, and applications that require consistent, repeatable image generation.

What Stable Image Core supports

Text-to-Image Generation

Converts a text prompt into an image using a 77-token context window to interpret the input description.

Style Preset Selection

Allows users to choose from predefined style presets that guide the overall aesthetic of the generated image.

Negative Prompting

Accepts a negative prompt as a text input to explicitly exclude unwanted elements or styles from the generated output.

Aspect Ratio Control

Supports selectable aspect ratios so users can define the dimensions and framing of the generated image before generation.

Seed-Based Reproducibility

Accepts a seed value that enables deterministic outputs, allowing the same image to be reproduced from identical inputs.

Output Format Selection

Lets users choose the file format for the generated image output, supporting integration into different downstream workflows.

Ready to build with Stable Image Core?

Get Started Free

Common questions about Stable Image Core

What is the context window size for Stable Image Core?

Stable Image Core has a context window of 77 tokens, which is the maximum prompt length it can process for image generation.

What input controls does Stable Image Core support?

The model supports a text prompt, a negative prompt, a style preset selector, an aspect ratio selector, a seed value, and an output format selector.

Can I reproduce the same image multiple times with Stable Image Core?

Yes. By providing the same seed value along with the same prompt and settings, you can reproduce identical or near-identical outputs.

What is the pricing for Stable Image Core?

Pricing information for Stable Image Core is not published in the available metadata. Check MindStudio or Stability AI's official channels for current pricing details.

Does Stable Image Core support image input or only text?

Based on the available metadata, Stable Image Core accepts text-based inputs only — including a prompt, negative prompt, style preset, aspect ratio, seed, and output format. It does not list image input as a supported input type.

Parameters & options

Style PresetSelect

Guides the image model towards a particular style.

3d-modelanalog-filmanimecinematiccomic-bookdigital-artenhancefantasy-artisometricline-artlow-polymodeling-compoundneon-punkorigamiphotographicpixel-arttile-texture
Negative PromptText

A blurb of text describing what you do not wish to see in the output image.

Aspect RatioSelect
Default: 1:1
1:12:33:24:55:49:169:2116:921:9
SeedSeed

A specific value that is used to guide the 'randomness' of the generation. Omit this parameter or pass 0 to use a random seed.

Output FormatSelect
Default: png
jpegpngwebp

Start building with Stable Image Core

No API keys required. Create AI-powered workflows with Stable Image Core in minutes — free.