> ## Documentation Index > Fetch the complete documentation index at: https://docs.square1.dev/llms.txt > Use this file to discover all available pages before exploring further. # Generate an illustration (NovelAI-compatible) > A synchronous, NovelAI-protocol image endpoint — point any client that speaks NovelAI's `/ai/generate-image` (e.g. RisuAI's Lightboard) at this path with your Square1 key as the Bearer token. Checkpoint, LoRAs, sampler, and quality settings come from your **active illustration preset** (dashboard → Images → ILLUSTRATION), not from the request — the NAI `model` field is accepted and ignored. See the Illustration API guide for the full parameter-precedence rules. The response is a ZIP archive containing one PNG (exactly what a NovelAI client expects). Errors use NovelAI's `{statusCode, message}` shape, **not** the OpenAI envelope used by the rest of this API. Generated images are private — they never enter the public gallery. Members-only: requires an active account (and a registered email when email enforcement is on). Image generation draws from the image queue capacity, not from your LLM token quota. ## OpenAPI ````yaml /openapi.yaml post /v1/images/nai/generate-image openapi: 3.1.0 info: title: Square1 API version: 1.0.0 description: | OpenAI-compatible LLM gateway API. All endpoints live on `https://inference.square1.dev` and require a Square1 API key (`sq-arca-...`, or a legacy `ws-...` key) sent as a Bearer token. The wire format follows the OpenAI Chat Completions / Embeddings / Models conventions, with a small set of documented vendor extensions: the `reasoning_effort` request field, the `reasoning` delta/message field, and the `wellspring` quota-receipt block on chat responses. servers: - url: https://inference.square1.dev security: - bearerAuth: [] tags: - name: Chat description: OpenAI-compatible chat completions. - name: Embeddings description: OpenAI-compatible embeddings. - name: Models description: The model catalog as visible to your key. - name: Account description: Read-only introspection for the authenticated key. - name: Illustration description: NovelAI-compatible synchronous image generation. paths: /v1/images/nai/generate-image: post: tags: - Illustration summary: Generate an illustration (NovelAI-compatible) description: | A synchronous, NovelAI-protocol image endpoint — point any client that speaks NovelAI's `/ai/generate-image` (e.g. RisuAI's Lightboard) at this path with your Square1 key as the Bearer token. Checkpoint, LoRAs, sampler, and quality settings come from your **active illustration preset** (dashboard → Images → ILLUSTRATION), not from the request — the NAI `model` field is accepted and ignored. See the Illustration API guide for the full parameter-precedence rules. The response is a ZIP archive containing one PNG (exactly what a NovelAI client expects). Errors use NovelAI's `{statusCode, message}` shape, **not** the OpenAI envelope used by the rest of this API. Generated images are private — they never enter the public gallery. Members-only: requires an active account (and a registered email when email enforcement is on). Image generation draws from the image queue capacity, not from your LLM token quota. operationId: naiGenerateImage requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/NaiGenerateRequest' examples: basic: value: input: 1girl, silver hair, looking at viewer, masterpiece action: generate parameters: negative_prompt: lowres, bad anatomy width: 832 height: 1216 steps: 28 seed: 1234567890 scale: 5 responses: '200': description: A ZIP archive containing the generated PNG. content: application/x-zip-compressed: schema: type: string format: binary '400': description: > Invalid request, unsupported `action`, or blocked content (the message lists the blocked category). content: application/json: schema: $ref: '#/components/schemas/NaiError' '401': description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/NaiError' '403': description: Admin-only mode, or account not eligible. content: application/json: schema: $ref: '#/components/schemas/NaiError' '429': description: > Your pending illustration queue is full (up to 2 queued requests per account) — wait for the current generation. content: application/json: schema: $ref: '#/components/schemas/NaiError' '500': description: Generation failed. content: application/json: schema: $ref: '#/components/schemas/NaiError' '503': description: > Feature disabled, maintenance, server queue congested, or no GPU worker currently available. content: application/json: schema: $ref: '#/components/schemas/NaiError' '504': description: The generation did not finish within 180 seconds. content: application/json: schema: $ref: '#/components/schemas/NaiError' components: schemas: NaiGenerateRequest: type: object required: - input properties: input: type: string maxLength: 8000 description: The prompt, in NovelAI syntax (converted server-side). model: type: string maxLength: 128 description: >- Accepted for protocol compatibility and ignored — the checkpoint comes from your active illustration preset. action: type: string description: If present, must be `generate`. parameters: type: object properties: negative_prompt: type: string maxLength: 8000 width: type: integer maximum: 4096 description: > Snapped (with `height`) to the nearest allowed resolution by aspect ratio (e.g. 832×1216, 1024×1024, 1216×832). Both must be present to take effect. height: type: integer maximum: 4096 steps: type: integer minimum: 1 maximum: 60 description: > Clamped to the preset's step bounds. Precedence: request > profile default > preset default. seed: type: integer minimum: 0 scale: type: number description: > NAI guidance scale (CFG). If your illustration preset sets a CFG default, the preset value wins over this field. NaiError: type: object description: NovelAI-shaped error — used ONLY by the illustration endpoint. required: - statusCode - message properties: statusCode: type: integer message: type: string description: Human-readable, in Korean. securitySchemes: bearerAuth: type: http scheme: bearer description: > A Square1 API key: `Authorization: Bearer sq-arca-...` (legacy `ws-...` keys remain valid). Create and rotate keys from the dashboard. ````