openapi: 3.1.0 info: title: Hyperbolic Audio Generation Image Generation API description: 'Convert text to natural-sounding speech using audio models hosted by Hyperbolic — Melo TTS (sunset) and Whisper (coming soon). Returns base64-encoded audio. Pricing from $0.001 per 1000 characters. ' version: v1 contact: name: Hyperbolic Support email: support@hyperbolic.ai url: https://docs.hyperbolic.ai license: name: Hyperbolic Terms of Use url: https://www.hyperbolic.ai/terms-of-use servers: - url: https://api.hyperbolic.xyz/v1 description: Hyperbolic Production Inference Server security: - BearerAuth: [] tags: - name: Image Generation description: Text-to-image diffusion endpoint paths: /image/generation: post: summary: Hyperbolic Generate An Image description: 'Generate one or more images from a text prompt using the specified diffusion model. Returns base64-encoded images in the `images` array. ' operationId: generateImage tags: - Image Generation requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ImageGenerationRequest' examples: SDXLBasic: summary: Basic SDXL generation value: model_name: SDXL1.0-base prompt: A photorealistic cyberpunk cat wearing sunglasses steps: 30 cfg_scale: 7.5 height: 1024 width: 1024 responses: '200': description: Successful image generation content: application/json: schema: $ref: '#/components/schemas/ImageGenerationResponse' '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Too Many Requests content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: ImageGenerationResponse: type: object properties: images: type: array items: type: object properties: image: type: string description: Base64-encoded image bytes. seed: type: integer inference_time: type: number description: Seconds spent in inference. ImageGenerationRequest: type: object required: - model_name - prompt properties: model_name: type: string description: 'Image model identifier — e.g. `SDXL1.0-base`, `SD3.5`, `FLUX.1-dev` (sunset), `FLUX.1-schnell` (sunset), `ControlNet-SDXL`. ' prompt: type: string negative_prompt: type: string steps: type: integer minimum: 1 maximum: 100 default: 30 cfg_scale: type: number minimum: 1 maximum: 20 default: 7.5 height: type: integer minimum: 64 maximum: 2048 default: 1024 width: type: integer minimum: 64 maximum: 2048 default: 1024 seed: type: integer n: type: integer minimum: 1 maximum: 4 default: 1 lora: type: object description: Custom LoRA configuration when supported by the model. ErrorResponse: type: object properties: error: type: object properties: message: type: string type: type: string code: type: string securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Key