Generate images from a style reference using Stability AI's Style Guide model, paid per call via MPP.
What it does
This endpoint provides access to Stability AI's Style Guide capability through the Locus MPP (Micropayment Protocol) gateway. It generates new images that match the visual style of a provided reference image, guided by a text prompt. You supply a style reference image and a prompt describing the desired output, and the model produces an image that combines the reference style with the prompt content. Parameters include fidelity (0–1, controlling how closely the output adheres to the reference style), aspect ratio, negative prompt, output format (jpeg/png/webp), and a reproducibility seed.
The endpoint is part of a broader Stability AI service suite available through the same MPP gateway, which includes text-to-image generation (Ultra, Core, SD3), image editing (erase, inpaint, outpaint, search-and-replace, search-and-recolor), background removal and replacement with relighting, upscaling (fast, conservative, creative), sketch-to-image, structure-guided generation, style transfer, image-to-3D (Stable Fast 3D, Stable Point Aware 3D), and audio generation/editing. Each endpoint is individually priced.
The Style Guide endpoint costs $0.057 per call (57,000 base units of pathUSD with 6 decimals), settled via the Tempo method on pathUSD. Payment is per-request (intent: charge). The endpoint accepts POST requests with a JSON body. The probe returned 404 on HEAD/GET, which is expected since this is a POST-only endpoint. The OpenAPI spec is well-documented with full request schemas for all sibling endpoints.
Capabilities
Use cases
- —Generating product images that match an established brand visual style
- —Creating illustrations consistent with a reference artwork's aesthetic
- —Producing marketing assets that adhere to a specific design language
- —Building automated pipelines that generate on-brand imagery from style templates
- —Rapid prototyping of visual concepts using a style reference and text description
Fit
Best for
- —Agents needing programmatic style-consistent image generation with per-call payment
- —Workflows requiring images that match a specific visual reference without API key management
- —Applications combining text prompts with style references for controlled creative output
Not for
- —Free or high-volume batch image generation (each call costs $0.057)
- —Full style transfer between two images (use the separate /style-transfer endpoint instead)
- —Text-only image generation without a style reference (use /generate-ultra, /generate-core, or /generate-sd3)
Quick start
curl -X POST https://stability-ai.mpp.paywithlocus.com/stability-ai/style-guide \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <MPP_TOKEN>" \
-d '{
"image": "<base64-encoded-style-reference>",
"prompt": "A cozy cabin in the mountains at sunset",
"fidelity": 0.5,
"aspect_ratio": "16:9",
"output_format": "png"
}'Example
Request
{
"seed": 42,
"image": "<base64-encoded-style-reference-image>",
"prompt": "A cozy cabin in the mountains at sunset",
"fidelity": 0.5,
"aspect_ratio": "16:9",
"output_format": "png",
"negative_prompt": "blurry, low quality"
}Endpoint
Quality
The OpenAPI spec is comprehensive with full request schemas and pricing for this and all sibling endpoints. However, the probe did not capture a live 402 challenge (404 on HEAD/GET is expected for a POST-only endpoint), no response schema is documented, and no example responses are available. The crawl pages all returned generic 404 JSON.
Warnings
- —Probe returned 404 on HEAD and GET — endpoint is POST-only; liveness not confirmed via 402 challenge on POST
- —No response schema documented — output format (base64 image, URL, etc.) is unknown from available material
- —Currency address 0x20c000000000000000000000b9537d11c60e8b50 assumed to be pathUSD with 6 decimals based on sibling endpoint descriptions; not independently verified
Citations
- —Style Guide endpoint costs 57,000 base units via Tempo method with intent 'charge'https://stability-ai.mpp.paywithlocus.com
- —Required parameters are image and prompt; optional parameters include fidelity, aspect_ratio, negative_prompt, output_format, seedhttps://stability-ai.mpp.paywithlocus.com
- —API reference available at platform.stability.aihttps://platform.stability.ai/docs/api-reference
- —LLM-readable docs available at beta.paywithlocus.comhttps://beta.paywithlocus.com/mpp/stability-ai.md