## Basic model info - Model name: qwen/qwen qwen-image-layered - Model description: Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers. - Endpoint name: image-to-image ## Model schema The model schema is defined in the OpenAPI schema: [OpenAPI Schema](https://oapi.sunra.ai/main/qwen/qwen-image-layered/latest.json) ### Model input schema The model input schema is: ```json { "description": "Input model for Qwen Image Layered - decomposes an image into multiple RGBA layers.", "properties": { "prompt": { "description": "A caption for the input image.", "title": "Prompt", "type": "string", "x-sr-order": 201 }, "guidance_scale": { "default": 5, "description": "The guidance scale for image generation.", "maximum": 20, "minimum": 1, "title": "Guidance Scale", "type": "number", "x-sr-order": 404 }, "seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "Random seed for reproducibility.", "title": "Seed", "x-sr-order": 406 }, "negative_prompt": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Content to avoid in the generated image.", "title": "Negative Prompt", "x-sr-order": 202 }, "acceleration": { "default": "regular", "description": "Acceleration level for image generation.", "enum": [ "none", "regular", "high" ], "title": "Acceleration", "type": "string", "x-sr-order": 405 }, "image": { "anyOf": [ { "format": "uri", "maxLength": 2083, "minLength": 1, "type": "string" }, { "type": "string" } ], "description": "The URL of the input image to decompose into layers.", "title": "Image", "x-sr-order": 200 }, "num_inference_steps": { "default": 28, "description": "The number of inference steps to perform.", "maximum": 50, "minimum": 1, "title": "Num Inference Steps", "type": "integer", "x-sr-order": 403 }, "num_layers": { "default": 4, "description": "The number of layers to generate.", "maximum": 10, "minimum": 1, "title": "Num Layers", "type": "integer", "x-sr-order": 402 }, "output_format": { "default": "png", "description": "Output image format.", "enum": [ "png", "webp" ], "title": "Output Format", "type": "string", "x-sr-order": 407 } }, "required": [ "image" ], "title": "ImageToImageInput", "type": "object" } ``` ### Model output schema The model output schema is: ```json { "properties": { "images": { "items": { "properties": { "content_type": { "description": "The mime type of the file.", "title": "Content Type", "type": "string" }, "file_name": { "description": "The name of the file. It will be auto-generated if not provided.", "title": "File Name", "type": "string" }, "file_size": { "description": "The size of the file in bytes.", "title": "File Size", "type": "integer" }, "url": { "description": "The URL where the file can be downloaded from.", "title": "Url", "type": "string" } }, "required": [ "content_type", "file_name", "file_size", "url" ], "title": "SunraFile", "type": "object" }, "title": "Images", "type": "array" } }, "required": [ "images" ], "title": "ImagesOutput", "type": "object" } ``` ## Example inputs and outputs Use the following example inputs and outputs to understand the model. ### Input example ```json { "prompt": "", "guidance_scale": 5, "seed": null, "negative_prompt": null, "acceleration": "regular", "image": "", "num_inference_steps": 28, "num_layers": 4, "output_format": "png" } ``` ### Output example ```json { } ``` ## Model code examples ### JavaScript ```javascript import { sunra } from "@sunra/client"; const result = await sunra.subscribe("qwen/qwen-image-layered/image-to-image", { input: { image: '', prompt: '', negative_prompt: null, num_layers: 4, num_inference_steps: 28, guidance_scale: 5, acceleration: 'regular', seed: null, output_format: 'png' }, logs: true, onQueueUpdate: (update) => { console.log(`Status Update: ${update.status}, Request ID: ${update.request_id}`); }, }); console.log(result.data); console.log(result.requestId); ``` ### Python ```python import sunra_client result = sunra_client.subscribe( "qwen/qwen-image-layered/image-to-image", arguments={ "image": "", "prompt": "", "negative_prompt": None, "num_layers": 4, "num_inference_steps": 28, "guidance_scale": 5, "acceleration": "regular", "seed": None, "output_format": "png" }, with_logs=True, on_enqueue=print, on_queue_update=print, ) print(result) ``` ### Java ```java import ai.sunra.client.*; import java.util.Map; import com.google.gson.JsonObject; var client = SunraClient.withEnvCredentials(); var response = client.subscribe( "qwen/qwen-image-layered/image-to-image", SubscribeOptions.builder() .input(Map.of( "image", "", "prompt", "", "negative_prompt", null, "num_layers", 4, "num_inference_steps", 28, "guidance_scale", 5, "acceleration", "regular", "seed", null, "output_format", "png")) .resultType(JsonObject.class) .onQueueUpdate(update -> System.out.printf( "\nStatus Update: %s, Request ID: %s%n", update.getStatus(), update.getRequestId() )) .logs(true) .build() ); System.out.println("Completed!"); System.out.println(response.getData()); ``` ### Kotlin ```kotlin import ai.sunra.client.kt.* import com.google.gson.JsonObject val client = createSunraClient() val response = client.subscribe( endpointId = "qwen/qwen-image-layered/image-to-image", input = mapOf( "image" to "", "prompt" to "", "negative_prompt" to null, "num_layers" to 4, "num_inference_steps" to 28, "guidance_scale" to 5, "acceleration" to "regular", "seed" to null, "output_format" to "png"), options = ai.sunra.client.kt.SubscribeOptions(logs = true), onUpdate = { update -> println("\nStatus Update: ${update.status}, Request ID: ${update.requestId}") } ) println("Completed!") println(response.data) ``` ### Curl ```bash curl --request POST \ --url https://api.sunra.ai/v1/queue/qwen/qwen-image-layered/image-to-image \ --header "Authorization: Key $SUNRA_KEY" \ --header "Content-Type: application/json" \ --data '{"image":"","prompt":"","negative_prompt":null,"num_layers":4,"num_inference_steps":28,"guidance_scale":5,"acceleration":"regular","seed":null,"output_format":"png"}' ``` ## Model readme >