{"uid":"cap_FT5xpNFzlVRPyfLTIuncd","slug":"stability-ai-sketch-to-image-via-locus-x402-d8cb7173","name":"Stability AI Sketch-to-Image via Locus x402","description":"Generative AI platform for images, 3D models, and audio — text-to-image, editing, upscaling, and more.","url":"https://stability-ai.x402.paywithlocus.com/stability-ai/sketch","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"seed":{"type":"number"},"image":{"type":"string"},"prompt":{"type":"string"},"output_format":{"type":"string"},"negative_prompt":{"type":"string"},"control_strength":{"type":"number"}}},"responseSchema":{"type":"json","example":{"data":{},"payment":{"scheme":"exact","settledUsdc":"0.001000","authorizedMaxUsdc":"0.001000"},"request":{"id":"00000000-0000-4000-8000-000000000000","statusUrl":"/requests/00000000-0000-4000-8000-000000000000"},"success":true}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.057","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.057/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.057","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.057","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_fSr8iZNLlDok-E-nis9xC","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.057","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts a sketch or line-art image into a fully rendered image guided by a text prompt, with adjustable adherence to the original sketch.","exampleAgentPrompt":"Take this sketch I drew of a mountain cabin at sunset and render it into a photorealistic image — follow the sketch closely (control strength 0.8), exclude any snow or winter elements, and output a PNG.","exampleUseCases":[{"title":"Concept art to finished illustration","prompt":"I have a rough pencil sketch of a futuristic city skyline — can you render it into a detailed, polished illustration? Use control strength 0.9 to stay true to my lines and output it as a PNG."},{"title":"Product design mockup rendering","prompt":"Turn this wireframe sketch of a sneaker design into a photorealistic product image. The prompt should be 'white leather sneaker with gold accents on a clean studio background', control strength 0.7, and output as JPEG."},{"title":"Character concept visualization","prompt":"I've got a line-art drawing of a fantasy warrior character. Render it into a fully colored, dramatic illustration — the style should be dark fantasy, no cartoonish elements, output as PNG, and use seed 42 so I can reproduce it."}],"resultDescription":"A JSON response containing the generated image data (in the requested format: jpeg, png, or webp), a success flag, payment settlement details in USDC, and a request ID with a status URL for tracking the async result.","failureModes":["Invalid or unreadable image input returns an error","control_strength outside 0–1 range causes a validation error","Unsupported output_format value returns a bad request error","Payment failure via x402 protocol prevents image generation","Missing required prompt field results in an error response","Image too large or wrong format may be rejected"],"whenToPreferThis":"Choose this endpoint when you have an existing sketch, line art, or rough drawing that you want to transform into a fully rendered image while preserving the structural composition of the original. It is ideal over pure text-to-image when layout control matters — the sketch acts as a spatial guide. Prefer it over inpainting or upscaling endpoints when the starting point is a hand-drawn or wireframe input rather than a photograph or partially completed image.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:35:46.204Z","isFirstParty":false}