LLM Reference

Stable Image Models by Stability AI

Stability AIProprietary
2 models2024

Details

ResearcherStability AI
LicenseProprietary
Commercial useCommercial use: conditional
Models2
Released2024

Capabilities

MultimodalAll models

Links

Website

About

Stability AI's managed image generation API product line, offering Core (SDXL-based, fast/affordable) and Ultra (SD 3.5 Large-powered, premium quality) tiers. Distinct from the open-weight Stable Diffusion models — Stable Image is API-only with per-image pricing.

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

2 in view

Use when the workload needs image generation and multimodal inputs.

2024-09image generationmultimodal inputs

Use when the workload needs image generation and multimodal inputs.

2024-04image generationmultimodal inputs

Release Timeline

2 release groups
2024-09
1 current
Stable Image Ultra
image generationmultimodal inputs
Current
2024-04
1 current
Stable Image Core
image generationmultimodal inputs
Current

Specifications(2 models)

Stable Image model specifications comparison
ModelReleasedMultimodal
Stable Image Ultra2024-09Yes
Stable Image Core2024-04Yes

Available From(1 provider)

Frequently Asked Questions

What is Stable Image used for?
Stable Image is used for image generation and vision and multimodal work. The family description and listed model capabilities point to those workloads as the best fit.
How does Stable Image compare to Stable Virtual Assistant?
Stable Image by Stability AI is strongest where you need image generation, while Stable Virtual Assistant by Stability AI is the closest related family to check for adjacent model selection. Stable Image has 2 listed variants, so compare the specs and pricing tables before choosing a production model.
Which Stable Image model should I use?
If price is the main constraint, use the pricing table first because Stable Image does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Stable Image Ultra with multimodal inputs.