ST

Model profile

Stable Image Ultra

Built by Stability AI

Stable Image Ultra is Stability AI’s hosted text-to-image service built from its advanced image models, including Stable Diffusion 3.5. The official API positions Ultra for high-detail, photorealistic output, typography, and complex compositions.[1]

CategoryImage Generation
Directory statusCatalogued
Official model cardVisit source ↗

Developer snapshot

Key specifications

Verified Jul 18, 2026

Modality
Text to image[1]
API route
/v2beta/stable-image/generate/ultra[1]
Default output
1024 × 1024[1]
Output size
1 megapixel[1]
Formats
JPEG, PNG, WebP[1]
Successful result
8 API credits[1]

Technical profile

What developers should know

01

What the service is for

Stability describes Ultra as its most advanced hosted text-to-image service, emphasizing prompt understanding, photorealism, typography, complex compositions, lighting, color, and overall visual cohesion. These are provider capability claims, not an independent quality ranking.[1]

02

API contract

The Ultra endpoint accepts POST requests authenticated with a Stability API key. A prompt is required; output can be returned as image bytes or base64 JSON, and the documented image formats are JPEG, PNG, and WebP.[1]

03

Operational limits

The platform documents moderation and validation failures as separate HTTP responses and applies API-level rate limits. Applications should treat failed or flagged generations as expected states and should not retry them blindly.[1]

Choose the artifact

Official checkpoints

Use the exact documented model or endpoint identifier and record input assets, parameters, output metadata, and failure states for reproducible media workflows.[1]

Deployment note

Pin the v2beta route and record prompt, seed, output format, and API response metadata in reproducible workflows. Keep the API key outside workflow files and public repositories.[1]