Use AI Portrait SDK for Java - Platform For AI - Alibaba Cloud Documentation Center

Train custom LoRA models and generate AI portraits using the Java SDK.

Prerequisites

A Java environment is installed.
Prepare 5 to 20 training images and one template image. Supported formats: .jpg, .jpeg, and .png.
- For solo portraits, template image must contain a single face. Training images must depict the same person.
- For multi-person portraits, template image must contain multiple faces matching the number of model_id values used for training.
- Image dimensions must be greater than 512 × 512 pixels.

Set up the SDK

Add the aiservice SDK dependency to the <dependencies> section of pom.xml:

<dependency>
 <groupId>com.aliyun.openservices.aiservice</groupId>
 <artifactId>aiservice-sdk</artifactId>
 <version>1.0.1</version>
</dependency>

Initialize the client.

import com.aliyun.openservices.aiservice.ApiClient;

public class AIGCImageTest {
 public static ApiClient apiClient;
 static {
 String host = 'HOST';
 String appId = 'YOUR-APPID';
 String token = 'YOUR-TOKEN';
 apiClient = new ApiClient(host, appId, token);
 }
}

Replace these parameters:

Parameter	Description
<HOST>	Server-side endpoint: `http://ai-service.ce8cc13b6421545749e7b4605f3d02607.cn-hangzhou.alicontainer.com`.
<YOUR-APPID>	Obtain from the AI Portrait page after activation.
<YOUR-TOKEN>	Obtain from the AI Portrait page after activation.

For more information, see the open source code on GitHub.

API examples

AI Portrait involves two stages: model training (several minutes) and portrait creation (seconds).

Check images (aigcImagesCheck)

Sample request:

import com.aliyun.openservices.aiservice.api;
import com.aliyun.openservices.aiservice.ApiClient;
import com.aliyun.openservices.aiservice.ApiException;
import com.aliyun.openservices.aiservice.model.AIGCCreatRequest;
import com.aliyun.openservices.aiservice.model.AIGCImageCheckResponse;
import com.aliyun.openservices.aiservice.model.AIGCImageCreateResponse;
import com.aliyun.openservices.aiservice.model.Response;

import java.util.Arrays;
import java.util.List;

public class AIGCImageTest {
    public static ApiClient apiClient;
    private  AigcImagesApi api ;
    static {
        String host  = 'HOST';
        String appId = 'YOUR-APPID';
        String token = 'YOUR-TOKEN';
        apiClient = new ApiClient(host, appId, token);
        api = new AigcImagesApi(apiClient);
    }

    public void aigcImagesCheckTest() throws Exception {
        // Training image URLs.
        List<String> images =Arrays.asList(
            "https://xxx/0.jpg",
            "https://xxx/1.jpg",
            "https://xxx/2.jpg"
        );

        AIGCImageCheckResponse response = api.aigcImagesCheck(images);
        // Request ID.
        String request_id = response.getRequestId();
        // Request status.
        String code = response.getCode();
        // Request status details.
        String message = response.getMessage();
        // Response content.
        AIGCImageCheckData data = response.getData();

        // Check result code.
        List<AIGCImageCheckResult> CheckResultsList =  response.getCheckResults();
        for(int i=0; i < CheckResultsList.size(); i++ ){
            AIGCImageCheckResult result = CheckResultsList.get(i);
            Integer ResultCode = result.getCode();
            System.out.println(ResultCode);
        }
    }

}

Parameters:

Parameter	Description
images	List of image URLs (List<String>).
<HOST>	Server-side endpoint: `http://ai-service.ce8cc13b6421545749e7b4605f3d02607.cn-hangzhou.alicontainer.com`.
<YOUR-APPID>	Obtain from the AI Portrait page after activation.
<YOUR-TOKEN>	Obtain from the AI Portrait page after activation.

Sample response:

Response type: AIGCImageCheckResponse

{
	requestId: 3c0eeb6b-1faf-4dc4-8f9a-9a02486051c6
	code: OK
	message: success
	data:
		AIGCImageCheckData{
			requestId = '3c0eeb6b-1faf-4dc4-8f9a-9a02486051c6', 
 			images = ["https://xxx/0.jpg",
 								"https://xxx/1.jpg",
 								"https://xxx/2.jpg"], 
		costTime=0.5460958480834961, 
 		checkResults=[
 			AIGCImageCheckResult{
 				code=1, 
 				frontal=false, 
 				url='https://xxx/0.jpg',
 				message='success'}, 
 			AIGCImageCheckResult{
        code=1, 
          frontal=true, 
          url='https://xxx/1.jpg',
          message='success'}, 
      AIGCImageCheckResult{
        code=4,
        frontal=false, 
        url='https://xxx/2.jpg',
        message='Image detect error.'}
  		]
		}
}

Response parameters:

Parameter	Description	Type
requestId	Request ID	String
code	Request status code. Valid values: OK: Success error: Failure	String
message	Request status details. "success" indicates successful request	String
data	Returned data details	AIGCImageCheckData

Data field (AIGCImageCheckData)

Parameter	Description	Type
checkResults	Detection result for each image. Contains url (image URL), message (detection details), and frontal (whether image is frontal view)	List<AIGCImageCheckResult>
costTime	Server-side processing time in seconds	float
images	URLs of checked images	List<String>
requestId	Request ID (same as parent requestId)	String

Check result messages:

message	Status code	Description
success	1	Requirements met
Image decode error.	2	Image cannot be downloaded or decoded
Number of faces is not 1	3	Number of faces in image is not 1
Image detection error	4	Error occurred during face detection
Image encoding error	5	Error occurred when encoding face into feature vector. Indicates no face detected
Photo does not match other photos	6	Faces in multiple images do not belong to same person

Train model (aigcImagesTrain)

Sample request:

package com.aliyun.aisdk;

import com.aliyun.openservices.aiservice.api.AigcImagesApi;
import com.aliyun.openservices.aiservice.ApiClient;
import com.aliyun.openservices.aiservice.ApiException;
import com.aliyun.openservices.aiservice.model.*;

import java.util.Arrays;
import java.util.List;

import java.io.IOException;

public class AIGCImageTrain {
  public String host = 'HOST';
  public String appId = 'YOUR-APPID';
  public String token = 'YOUR-TOKEN';

  public ApiClient apiClient = new ApiClient(host, appId, token);
  public AigcImagesApi api = new AigcImagesApi(apiClient);

  public void aigcImagesTrainTest() throws Exception {
    List<String> images =Arrays.asList(
      "https://xxx/0.jpg",
      "https://xxx/1.jpg",
      "https://xxx/2.jpg"
    );
    AIGCImageTrainResponse response = api.aigcImagesTrain(images);
    int jobId = response.getData().getJobId();
    String modelId = response.getData().getModelId();
    String message = response.getMessage();
    InlineResponse200Data Data = response.getData();

    System.out.println(response);
    System.out.println(response.getMessage());

    System.out.println("jobId:" + jobId);
    System.out.println("modelId:" + modelId);
    System.out.println("Data:" + Data);
  }
}

Parameters:

Parameter Location	Description
images	A list of image URLs. Type: List<String>.
<HOST>	Server-side endpoint: `http://ai-service.ce8cc13b6421545749e7b4605f3d02607.cn-hangzhou.alicontainer.com`
<YOUR-APPID>	Obtain from the AI Portrait page after activation.
<YOUR-TOKEN>	Obtain from the AI Portrait page after activation.

Sample response:

Response type: AIGCImageTrainResponse

{
  requestId: 2bd438df-2358-4852-b6b0-bf7d39b6dde7
  code: OK
  message: success
  data: class InlineResponse200Data {
          	jobId: xxxx
            modelId: xxxx-xxxxxxxx-xxxxxx
          }
}

Response fields:

Parameter	Description	Type
requestId	Request ID.	String
code	Request status code. OK indicates success, error indicates failure.	String
message	Request status details. "success" indicates a successful request.	String
data	Returned data details.	InlineResponse200Data

Description of the data field

Parameter Name	Description	Type
jobId	task ID.	int
modelId	The ID of the model from this training task. It is a 36-character string.	String

Use the job_id to query the training result.
Provide the model_id to call the portrait creation service.

Query training status (getAsyncJob)

Sample request:

import com.aliyun.openservices.aiservice.api.AiServiceJobApi;
import com.aliyun.openservices.aiservice.api.AigcImagesApi;
import com.aliyun.openservices.aiservice.ApiClient;
import com.aliyun.openservices.aiservice.ApiException;
import com.aliyun.openservices.aiservice.model.*;


import java.util.Arrays;
import java.util.List;

import java.io.IOException;

public class AIGCJobCheck {
	public void aigcJobStateGet() throws Exception {
    Integer jobId = new Integer(xxxx); // Asynchronous task ID

    AiServiceJobApi jobApi = new AiServiceJobApi(apiClient);

    AsyncJobResponse jobResponse = jobApi.getAsyncJob(jobId);
    String request_id = jobResponse.getRequestId();
    String job_code = jobResponse.getCode();
    String job_message = jobResponse.getMessage();
    Map<String, AsyncJobData> job_data = jobResponse.getData();

    String Result_string = (String) job_data.get("job").getResult();
    JsonObject jsonObject = new JsonParser().parse(Result_string).getAsJsonObject();
    JsonArray result_states = jsonObject.get("states").getAsJsonArray();

    for (int result_idx=0; result_idx < result_states.size(); result_idx++){
      JsonObject result_one = result_states.get(result_idx).getAsJsonObject();
      String result_url = result_one.get("url").getAsString();
    }
  }
}

Parameters:

Parameter	Type	Description
jobId	Integer	Training task ID

Sample responses:

Model training in progress:

{
    requestId: 9a76c77d-c241-4691-8c93-fc6953fb668c
    code: OK
    message: success
    data: {
          job=AsyncJobData{
            id=12746, 
            appId='xxxxxxxxxx', 
            state=1, 
            message='model requesting', 
            result="", 
            requestId='111a6503-c2f7-4141-b17b-f8567e6a0a5f'
            }
    }
}

Model training complete:

{
      requestId: 0fc513d1-5a9e-48e1-9b6f-2eca7c0b62e9
      code: OK
      message: success
        data: {
          job=AsyncJobData{
            id=12744, 
            appId='xxxxxxxxxxx', 
            state=2, 
            message='success', 
            result={
              "cost_time":232.83351230621338,
              "model_id":"xxxxxxxxxxxx",
              "states":[{"code":1,
                         "frontal":true,
                         "message":"success",
                         "url":"https://xxxx/train/1.jpg"}]
            }, 
            requestId='83146ee3-68aa-40f7-b523-06f029e1db15'
          }
        }
}

Description of return values

Parameter name	Description	Type
requestId	Request ID.	String
code	Request status code. OK indicates success, error indicates failure.	String
message	Request status details. "success" indicates successful request	String
data	Returned data details.	Map<String, AsyncJobData>

Description of the job field in data

Parameter Name	Description	Type
id	Task ID (job_id)	int
appId	User AppId	String
state	Task status code: 0: Initializing. 1: Running. 2: Succeeded. 3: Failed.	int
message	Task execution information	String
Result	Model result	String

Description of the model result (type: String)

Parameter	Description
cost_time	Total time consumed by training task
states	Check result for each image detection result for each input image. Each image corresponds to a dictionary that contains three keys: url, message, and frontal. These keys represent the image URL, image detection details, and whether the image is a frontal view, respectively.
model_id	The LoRA model name. This is the same model_id obtained from the training request and is used as an input for portrait creation.

Related error codes

error codes for service requests are as follows:

HTTP status code	code	message	Description
400	PARAMETER_ERROR	not found appid	The AppId is incorrect.
401	PARAMETER_ERROR	sign error	token is incorrect.
404	PARAMETER_ERROR	model not found	corresponding model service is not deployed.

Query results can contain the following error codes:

HTTP status code	code	message	Description
462	error	Invalid input data	Failed to parse the input data.
462	error	Image not provided	No training images were provided.
462	error	Make dir in oss Error.	Failed to create a folder in OSS. Check if OSS is mounted.
462	error	Image process error.	An error occurred during image pre-processing.
469	error	Training - Not get best template image	training task exited unexpectedly and failed to generate a reference image.
469	error	Training - Not get lora weight	training task exited unexpectedly and failed to generate the LoRA weight.

Create portrait

Sample requests:

API for solo portrait creation (aigcImagesCreate)

Prediction with Stable Diffusion 1.5

import com.aliyun.openservices.aiservice.api.AiServiceJobApi;
import com.aliyun.openservices.aiservice.api.AigcImagesApi;
import com.aliyun.openservices.aiservice.ApiClient;
import com.aliyun.openservices.aiservice.ApiException;
import com.aliyun.openservices.aiservice.model.*;


import java.io.FileOutputStream;
import java.io.OutputStream;
import java.util.Arrays;
import java.util.List;

import java.io.IOException;

import sun.misc.BASE64Decoder;
import sun.misc.BASE64Encoder;

public class AIGCImageService {
  public String host = 'HOST';
  public String appId = 'YOUR-APPID';
  public String token = 'YOUR-TOKEN';

  public ApiClient apiClient = new ApiClient(host, appId, token);
  public AigcImagesApi api = new AigcImagesApi(apiClient);

  public void aigcImageCreateGet() throws Exception {
    String modelId = "xxx-xxxx";
    String templateImage = "https://xxxx.jpg";
    String model_name = "";
    Map<String, Object> configure = new TreeMap<String, Object>();

    AIGCImageCreateResponse createResponse = api.aigcImagesCreate(modelId, templateImage, model_name, configure);

    // Request ID.
    String request_id = createResponse.getRequestId();
    // Request status.
    String code = createResponse.getCode();
    // Details of the request status.
    String message = createResponse.getMessage();
    // Content of the response.
    AIGCImageCreateData data = createResponse.getData();

    // Base64-encoded generated image.
    String imgStr = createResponse.getData().getImage();

    BASE64Decoder decoder = new BASE64Decoder();
    byte[] imgBtyes = decoder.decodeBuffer(imgStr);
    for (int i = 0; i < imgBtyes.length; ++i) {
      // Adjust abnormal data.
      if (imgBtyes[i] < 0) {
        imgBtyes[i] += 256;
      }
    }

    String imgFilePath = "test_single.jpg";
    OutputStream out = new FileOutputStream(imgFilePath);

    out.write(imgBtyes);
    out.flush();
    out.close();
  }
}

Parameters:

Parameter	Type	Description
modelId	String	LoRA model name. Enter model_id from training Set to "" for ipa_control_only mode
templateImage	String	Template URL path
model_name	String	Model name. Default is empty string
configure	Map<String, Object>	Model return configuration. Default is None
<HOST>	String	Server-side endpoint: `http://ai-service.ce8cc13b6421545749e7b4605f3d02607.cn-hangzhou.alicontainer.com`
<YOUR-APPID>	String	After activation, obtain AppId from AI Portrait page
<YOUR-TOKEN>	String	After activation, obtain token from AI Portrait page

Parameters in configure

Configuring internal parameter names	Description	Type	Required	Default value	Value range
lora_weights	LoRA weight	float	No	0.90	0.5 to 1.0
first_denoising_strength	First image reconstruction intensity	float	No	0.45	0.0 to 1.0
second_denoising_strength	Second image reconstruction intensity	float	No	0.30	0.0 to 1.0
more_like_me	Individual likeness strength	float	No	0.50	0.0 to 1.0
crop_face_preprocess	Whether to crop image before reconstruction. Recommended for large images	bool	No	True	True, False
apply_face_fusion_before	Specifies whether to perform the first portrait merging.	bool	No	True	True, False
apply_face_fusion_after	Specifies whether to perform the second portrait merging.	bool	No	True	True, False
color_shift_middle	Specifies whether to perform the first color correction.	bool	No	True	True, False
color_shift_last	Specifies whether to perform the second color correction.	bool	No	True	True, False
background_restore	Specifies whether to reconstruct the background.	bool	No	False	True, False
skin_retouching_bool	Specifies whether to perform skin smoothing. If enabled, the skin is smoothed and brightened, which generally makes the image more appealing but may result in overly white skin. If disabled, the skin texture is enhanced.	bool	No	False	True, False
photo_enhancement_bool	Specifies whether to perform portrait enhancement. If enabled, portrait restoration or super resolution is performed to improve the quality of the generated image.	bool	No	True	True, False
photo_enhancement_method	portrait enhancement method. photo_fix performs image restoration. This may cause some distortion but fixes unreasonable parts and may reduce skin texture. super_resolution only performs image super resolution, which better preserves the original image.	String	No	photo_fix	photo_fix, super_resolution
makeup_transfer	Specifies whether to perform makeup transfer. If enabled, makeup is transferred to prevent the image from looking too plain. However, this may cause the image to look less like the user.	bool	No	False	True, False
makeup_transfer_ratio	intensity of the makeup transfer. A higher value results in a stronger makeup transfer effect, making the generated makeup look more like the template. However, this may also cause the image to look less like the user.	float	No	0.5	0.0 to 1.0
face_shape_match	Specifies whether to adapt the face shape. If enabled, the control intensity is reduced, and the face shape and skin texture will more closely match the user.	bool	No	False	True, False
ipa_control	Specifies whether to enable IPA control. If enabled, the portrait similarity is increased, but the result is more susceptible to the influence of the reference image.	bool	No	False	True, False
ipa_control_only	If enabled, perform prediction without training. If enabled, specify ipa_image_path.	bool	No	False	True, False
ipa_image_path	The URL of the reference portrait. This is required if ipa_control_only is enabled.	String	No	None	A downloadable URL
ipa_weight	The IPA control intensity. A higher value makes the output image look more like the user, but an excessively high value can cause image distortion.	float	No	0.5	0.0 to 1.0
style_name	Specifies the style for the generated output. Available in realistic or cartoon styles.	str	No	Realistic	Realistic, Anime
lcm_accelerate	Specifies whether to use LCM acceleration for the generation style.	bool	No	False	True, False
sharp_ratio	sharpening degree. An appropriate value can improve clarity. An excessively high value can cause image distortion.	float	No	0.15	0.0 to 1.0
t2i_prompt	If you want to use the text-to-image feature, set the prompt here. If you set t2i_prompt, you do not need to pass the URL path of the template.	String	No	None	N/A

Inference with Stable Diffusion XL

import com.aliyun.openservices.aiservice.api.AiServiceJobApi;
import com.aliyun.openservices.aiservice.api.AigcImagesApi;
import com.aliyun.openservices.aiservice.ApiClient;
import com.aliyun.openservices.aiservice.ApiException;
import com.aliyun.openservices.aiservice.model.*;


import java.io.FileOutputStream;
import java.io.OutputStream;
import java.util.Arrays;
import java.util.List;

import java.io.IOException;

import sun.misc.BASE64Decoder;
import sun.misc.BASE64Encoder;

public class AIGCImageService {
  public String host = 'HOST';
  public String appId = 'YOUR-APPID';
  public String token = 'YOUR-TOKEN';

  public ApiClient apiClient = new ApiClient(host, appId, token);
  public AigcImagesApi api = new AigcImagesApi(apiClient);

  public void aigcImageCreateGet() throws Exception {
    String modelId = "xxx-xxxx";
    String templateImage = "https://xxxx.jpg";
    String model_name = "create_xl";
    Map<String, Object> configure = new TreeMap<String, Object>();

    AIGCImageCreateResponse createResponse = api.aigcImagesCreate(modelId, templateImage, model_name, configure);

    // Request ID.
    String request_id = createResponse.getRequestId();
    // Request status.
    String code = createResponse.getCode();
    // Details of the request status.
    String message = createResponse.getMessage();
    // Content of the response.
    AIGCImageCreateData data = createResponse.getData();

    // Base64-encoded generated image.
    String imgStr = createResponse.getData().getImage();

    BASE64Decoder decoder = new BASE64Decoder();
    byte[] imgBtyes = decoder.decodeBuffer(imgStr);
    for (int i = 0; i < imgBtyes.length; ++i) {
      // Adjust abnormal data.
      if (imgBtyes[i] < 0) {
        imgBtyes[i] += 256;
      }
    }

    String imgFilePath = "test_single.jpg";
    OutputStream out = new FileOutputStream(imgFilePath);

    out.write(imgBtyes);
    out.flush();
    out.close();
  }
}

Parameters:

Parameter Location	Type	Description
modelId	string	LoRA model name. Enter model_id from training Set to "" for ipa_control_only mode
templateImage	string	Template URL path When generating with scene_lora or a prompt, set this to "t2i_generate".
model_name	string	model name. To use Stable Diffusion XL, set this to create_xl.
configure	Map<String, Object>	model returns the `configure` configuration, which is `None` by default.

Parameters in configure

Configuring internal parameter names	Description	Type	Required	Default value	Value range
lora_weights	application intensity of LoRA. A higher value makes the output image look more like the user, but an excessively high value can cause image distortion.	float	No	0.90	0.5 to 1.0
first_diffusion_steps	number of steps for the first diffusion. We do not recommend that you modify this parameter. A value that is too low can cause image distortion.	int	No	50	20-50
first_denoising_strength	First image reconstruction intensity reconstruction intensity for the face. A higher value results in more reconstruction. In theory, a higher value makes the output image look more like the user, but an excessively high value can make the image look unnatural.	float	No	0.45	0.0 to 1.0
second_diffusion_steps	number of steps for the second diffusion. We do not recommend that you modify this parameter. A value that is too low can cause image distortion.	int	No	30	20-50
second_denoising_strength	Second image reconstruction intensity reconstruction intensity for the edges of the face. An excessively high value can make the image look unnatural.	float	No	0.30	0.0 to 1.0
more_like_me	This is more my strong suit. portrait merging ratio. A higher value makes the image look more like the user, but an excessively high value reduces the realism of the image.	float	No	0.60	0.0 to 1.0
crop_face_preprocess	Whether to crop image before reconstruction. Recommended for large images We do not recommend that you adjust this parameter.	bool	No	True	True, False
apply_face_fusion_before	Specifies whether to perform the first portrait merging. If enabled, portrait merging is performed. If disabled, the similarity is reduced.	bool	No	True	True, False
apply_face_fusion_after	Specifies whether to perform the second portrait merging. If enabled, portrait merging is performed. If disabled, the similarity is reduced.	bool	No	True	True, False
color_shift_middle	Specifies whether to perform the first color correction. If enabled, color correction is performed to make the skin tone of the output image more like the template. If disabled, color correction is not performed, and color deviation may occur.	bool	No	True	True, False
color_shift_last	Specifies whether to perform the second color correction. If enabled, color correction is performed to make the skin tone of the output image more like the template. If disabled, color correction is not performed, and color deviation may occur.	bool	No	True	True, False
background_restore	Specifies whether to reconstruct the background. If enabled, the background is reconstructed. This can make the image look more natural but changes the background and increases the processing time.	bool	No	False	True, False
skin_retouching_bool	Specifies whether to perform skin smoothing. If enabled, the skin is smoothed and brightened, which generally makes the image more appealing but may result in overly white skin. If disabled, the skin texture is enhanced.	bool	No	False	True, False
photo_enhancement_bool	Specifies whether to perform portrait enhancement. If enabled, portrait restoration or super resolution is performed to improve the quality of the generated image.	bool	No	True	True, False
photo_enhancement_method	portrait enhancement method: photo_fix performs image restoration. This may cause some distortion but fixes unreasonable parts and may reduce skin texture. super_resolution only performs image super resolution, which better preserves the original image.	String	No	photo_fix	photo_fix, super_resolution
makeup_transfer	Specifies whether to perform makeup transfer. If enabled, makeup is transferred to prevent the image from looking too plain. However, this may cause the image to look less like the user.	bool	No	False	True, False
makeup_transfer_ratio	intensity of the makeup transfer. A higher value results in a stronger makeup transfer effect, making the generated makeup look more like the template. However, this may also cause the image to look less like the user.	float	No	0.5	0.0 to 1.0
ipa_control	Specifies whether to enable IPA control. If enabled, the portrait similarity is increased, but the result is more susceptible to the influence of the reference image.	bool	No	False	True, False
ipa_control_only	If enabled, perform prediction without training. If enabled, specify ipa_image_path.	bool	No	False	True, False
ipa_image_path	The URL of the reference portrait. This is required if ipa_control_only is enabled.	String	No	None	A downloadable URL
ipa_weight	The IPA control intensity. A higher value makes the output image look more like the user, but an excessively high value can cause image distortion.	float	No	0.5	0.0 to 1.0
lcm_accelerate	Specifies whether to use LCM acceleration for the generation style.	bool	No	False	True, False
sharp_ratio	sharpening degree. An appropriate value can improve clarity. An excessively high value can cause image distortion.	float	No	0.15	0.0 to 1.0
scene_id	If you want to use Scene LoRA, set the scene ID here. scene ID is obtained from training. The model ID returned when training a Stable Diffusion XL Scene LoRA is the scene ID.	String	No	None	N/A
t2i_prompt	If you want to use the text-to-image feature, set the prompt here. If you set t2i_prompt, you do not need to pass the URL path of the template.	String	No	None	N/A

API for multi-person portrait creation (api.aigcImagesCreateByMultiModelIds)

import com.aliyun.openservices.aiservice.api.AiServiceJobApi;
import com.aliyun.openservices.aiservice.api.AigcImagesApi;
import com.aliyun.openservices.aiservice.ApiClient;
import com.aliyun.openservices.aiservice.ApiException;
import com.aliyun.openservices.aiservice.model.*;


import java.io.FileOutputStream;
import java.io.OutputStream;
import java.util.Arrays;
import java.util.List;

import java.io.IOException;

import sun.misc.BASE64Decoder;
import sun.misc.BASE64Encoder;

public class AIGCImageService {
  public String host = 'HOST';
  public String appId = 'YOUR-APPID';
  public String token = 'YOUR-TOKEN';

  public ApiClient apiClient = new ApiClient(host, appId, token);
  public AigcImagesApi api = new AigcImagesApi(apiClient);

  public void aigcImageCreateMulti() throws Exception {
    String[] modelIds = new String[]{"model-id1","model-id2"};
    String templateImage = "https://xxxx.jpg";
    String model_name = "";
    Map<String, Object> configure = new TreeMap<String, Object>();

    AIGCImageCreateResponse createResponse = api.aigcImagesCreateByMultiModelIds(model_id, template_image, model_name, config);

    // Request ID.
    String request_id = createResponse.getRequestId();
    // Request status.
    String code = createResponse.getCode();
    // Details of the request status.
    String message = createResponse.getMessage();
    // Content of the response.
    AIGCImageCreateData data = createResponse.getData();

    // Base64-encoded generated image.
    String imgStr = createResponse.getData().getImage();

    BASE64Decoder decoder = new BASE64Decoder();
    byte[] imgBtyes = decoder.decodeBuffer(imgStr);
    for (int i = 0; i < imgBtyes.length; ++i) {
      // Adjust abnormal data.
      if (imgBtyes[i] < 0) {
        imgBtyes[i] += 256;
      }
    }

    String imgFilePath = "test_multi.jpg";
    OutputStream out = new FileOutputStream(imgFilePath);

    out.write(imgBtyes);
    out.flush();
    out.close();
  }
}

Parameter	Type	Description
modelId	String	model ID of the trained model.
templateImage	String	Template URL path
model_name	String	Model name. Default is empty string
configure	Map<String, Object>	Model return configuration. Default is None
<HOST>	String	Server-side endpoint: `http://ai-service.ce8cc13b6421545749e7b4605f3d02607.cn-hangzhou.alicontainer.com`
<YOUR-APPID>	String	After you activate AI Portrait, view the AppId on the AI Portrait page.
<YOUR-TOKEN>	String	After you activate AI Portrait, view the token on the AI Portrait page.

Sample response:

{
 requestId: 5eb7741b-540b-4a5c-9c98-fdd1d714e51f
 code: OK
 message: success
 data: com.aliyun.openservices.aiservice.model.AIGCImageCreateData@358c99f5
}

Description of the data field (type: AIGCImageCreateData)

Parameter	Description	Type
costTime	time taken for generation.	Float
image	The Base64-encoded image.	String

Error codes for portrait creation

Service request errors

HTTP status code	code	message	Description
400	PARAMETER_ERROR	not found appid	The AppId is incorrect.
401	PARAMETER_ERROR	sign error	token is incorrect.
404	PARAMETER_ERROR	model not found	corresponding model service is not deployed.

Result query errors

HTTP status code	code	message	Description
462	error	Invalid input data. Please check the input dict.	Failed to parse the input data.
462	error	Image not provided. Please check the template_image.	template image for portrait creation was not provided.
462	error	Prompts get error. Please check the model_id.	Check the format of the provided model_id.
462	error	Face id image decord error. Pleace check the user's lora is trained or not.	An error occurred when decoding the user-uploaded image. Check whether the model is trained.
462	error	Roop image decord error. Pleace check the user's lora is trained or not.	The Roop image does not exist. Check whether the model is trained.
462	error	Template image decode error. Please Give a new template.	An error occurred while decoding the template image. Provide a new template.
462	error	There is not face in template. Please Give a new template.	No face was found in the template image. Provide a new template.
462	error	Template image process error. Please Give a new template.	An error occurred during template image pre-processing. Provide a new template image.
469	error	First Face Fusion Error, Can't get face in template image.	An error occurred during the first portrait merging.
469	error	First Stable Diffusion Process error. Check the webui status.	An error occurred during the first Stable Diffusion process.
469	error	Second Face Fusion Error, Can't get face in template image.	An error occurred during the second portrait merging.
469	error	Second Stable Diffusion Process error. Check the webui status.	An error occurred during the second Stable Diffusion process.
469	error	Please confirm if the number of faces in the template corresponds to the user ID.	Check if the number of user IDs provided matches the number of faces.
469	error	Third Stable Diffusion Process error. Check the webui status.	An error occurred during background processing. Replace the template.

Complete workflow example

Complete example that generates an AI portrait image in the current directory:

Standard flow (Stable Diffusion 1.5)

package com.aliyun.aisdk;

import com.aliyun.openservices.aiservice.api.AiServiceJobApi;
import com.aliyun.openservices.aiservice.api.AigcImagesApi;
import com.aliyun.openservices.aiservice.ApiClient;
import com.aliyun.openservices.aiservice.ApiException;
import com.aliyun.openservices.aiservice.model.*;


import java.io.FileOutputStream;
import java.io.OutputStream;
import java.util.Arrays;
import java.util.List;

import java.io.IOException;

import sun.misc.BASE64Decoder;
import sun.misc.BASE64Encoder;

public class AIGCImageRunner {

  public String host = 'HOST';
  public String appId = 'YOUR-APPID';
  public String token = 'YOUR-TOKEN';

  public ApiClient apiClient = new ApiClient(host, appId, token);
  public AigcImagesApi api = new AigcImagesApi(apiClient);

  public byte[] base64ToBytes(String imgStr) throws IOException {
    BASE64Decoder decoder = new BASE64Decoder();
    byte[] imgBtyes = decoder.decodeBuffer(imgStr);
    for (int i = 0; i < imgBtyes.length; ++i) {
      // Adjust abnormal data.
      if (imgBtyes[i] < 0) {
        imgBtyes[i] += 256;
      }
    }

    return imgBtyes;
  }

  public void aigcImagesCheck(List<String> images) throws Exception{
    AIGCImageCheckResponse response = api.aigcImagesCheck(images);
  }

  public Object[] aigcImagesTrainRun(List<String> images) throws Exception {

    AIGCImageTrainResponse response = api.aigcImagesTrain(images);
    int jobId = response.getData().getJobId();

    Object[] trainOut = new Object[2];

    System.out.println(response);
    System.out.println(response.getMessage());

    System.out.println("jobId:" + jobId);
    System.out.println("modelId:" + response.getData().getModelId());
    System.out.println(response.getData());

    trainOut[0]=jobId;
    trainOut[1] = response.getData().getModelId();
    return trainOut;
  }

  public Integer aigcJobStateGet(AiServiceJobApi jobApi, int jobId_int) throws Exception {
    Integer jobId = new Integer(jobId_int); // Asynchronous task ID.

    AsyncJobResponse jobResponse = jobApi.getAsyncJob(jobId);

    System.out.println(jobResponse.getData().get("job").getResult());

    return jobResponse.getData().get("job").getState();
  }

  public void CreateSingle(String modelId, String templateImage) throws Exception {

    AIGCImageCreateResponse createResponse = api.aigcImagesCreate(modelId, templateImage);

    // Base64-encoded generated image.
    String imgStr = createResponse.getData().getImage();
    System.out.println(createResponse.getData());

    byte[] imgBtyes = base64ToBytes(imgStr);

    String imgFilePath = "test_single.jpg";
    OutputStream out = new FileOutputStream(imgFilePath);

    out.write(imgBtyes);
    out.flush();
    out.close();
  }
  
  public void CreateMulti(String[] model_ids, String template_image)throws ApiException, IOException {
        
    		String imgFilePath = "test_multi.jpg";
    		AIGCImageCreateResponse createResponse = api.aigcImagesCreateByMultiModelIds(model_ids, template_image, model_name, config);

        // Request ID.
        String request_id = createResponse.getRequestId();
        // Request status.
        String code = createResponse.getCode();
        // Request status details.
        String message = createResponse.getMessage();
        // Response content.
        AIGCImageCreateData data = createResponse.getData();

        if (!code.equals("OK")){
            System.out.printf("aigc_images_create failed, model_id is %s, request_id is %s\n",model_ids,request_id);
        }else {
            String imgStr = createResponse.getData().getImage();
            byte[] image = base64ToBytes(imgStr);

          	
            OutputStream out = new FileOutputStream(output_image);

            out.write(image);
            out.flush();
            out.close();

        }
    }


  public void aigcEndtoEndCreate() throws Exception {
    List<String> images =Arrays.asList(
      "https://xxx/0.jpg",
      "https://xxx/1.jpg",
      "https://xxx/2.jpg"
    );
    String templateImage = "https://xxx.jpg";
    String multiTemplateImage = "https://xxx.jpg";

    Object[] o = aigcImagesTrainRun(images);
    int jobId = (int)o[0];
    String modelId = (String)o[1];
    
    AiServiceJobApi jobApi = new AiServiceJobApi(apiClient);

    while(true){
      Integer jobState = aigcJobStateGet(jobApi, jobId);

      if (jobState == AsyncJobState.JOB_STATE_WAIT) { // Job is running.
        System.out.println("job running");
      } else if (jobState == AsyncJobState.JOB_STATE_SUCCESS) {
        System.out.println("job success");
        break;
      } else {
        System.out.println("job fail");
        throw new Exception("job fail");
      }

      try {
        Thread.sleep(30000);
      } catch (InterruptedException e) {
        throw new RuntimeException(e);
      }
    }
    
    

    CreateSingle(modelId,templateImage);


    String[] modelIds = new String[]{modelId,modelId};
    CreateMulti(model_ids, template_image)

  }

}

Parameters:

Parameter	Description
<HOST>	Server-side endpoint: `http://ai-service.ce8cc13b6421545749e7b4605f3d02607.cn-hangzhou.alicontainer.com`
<YOUR-APPID>	After you activate AI Portrait, view the AppId on the AI Portrait page.
<YOUR-TOKEN>	After you activate AI Portrait, view the token on the AI Portrait page.
images	The URLs of the images used to train the model. Separate multiple URLs with commas (,).
templateImage	The URL of the template image, which contains a single face. This is used for solo portrait creation.
multiTemplateImage	The URL of the template image, which contains multiple faces. The number of faces must match the number of model_id values provided. This is used for multi-person portrait creation.

Standard flow (Stable Diffusion XL)

To use Stable Diffusion XL model, contact PAI team to activate the service first. After activation, specify the model name.

package com.aliyun.aiservice.demo;

import com.aliyun.openservices.aiservice.ApiClient;
import com.aliyun.openservices.aiservice.ApiException;
import com.aliyun.openservices.aiservice.api.AiServiceJobApi;
import com.aliyun.openservices.aiservice.api.AigcImagesApi;
import com.aliyun.openservices.aiservice.model.*;
import com.google.gson.JsonArray;
import com.google.gson.JsonObject;
import com.google.gson.JsonParser;
import org.junit.Test;
import sun.misc.BASE64Decoder;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.util.*;


public class PhotoEndtoEndTest {

    public String host = 'HOST';
  	public String appId = 'YOUR-APPID';
  	public String token = 'YOUR-TOKEN';
  
    public ApiClient apiClient = new ApiClient(host, appId, token);
    public AigcImagesApi api = new AigcImagesApi(apiClient);
    public AiServiceJobApi jobApi = new AiServiceJobApi(apiClient);

    public byte[] base64ToBytes(String imgStr) throws IOException {
        BASE64Decoder decoder = new BASE64Decoder();
        byte[] imgBtyes = decoder.decodeBuffer(imgStr);
        for (int i = 0; i < imgBtyes.length; ++i) {
            // Adjust abnormal data.
            if (imgBtyes[i] < 0) {
                imgBtyes[i] += 256;
            }
        }

        return imgBtyes;
    }

    public boolean Check(List<String> images) throws ApiException {
        AIGCImageCheckResponse response = this.api.aigcImagesCheck(images);
        // Request ID.
        String request_id = response.getRequestId();
        // Request status.
        String code = response.getCode();
        // Request status details.
        String message = response.getMessage();
        // Response content.
        AIGCImageCheckData data = response.getData();

        // Print the returned result.
        boolean is_ok = false;
        if (!code.equals("OK")){
            System.out.printf("aigc_images_check failed,request id is %\n", request_id);
        }else{
            is_ok = true;
            System.out.printf("check images done, input %d images, return %d images, %d filtered by lvwang\n",
                    images.size(),(data.getCheckResults().size()),(images.size()-data.getCheckResults().size()));
            for (int check_result_idx=0; check_result_idx < data.getCheckResults().size();check_result_idx++ ){
                AIGCImageCheckResult checkResult = data.getCheckResults().get(check_result_idx);
                Integer checkResultCode = checkResult.getCode();
                if (checkResultCode.equals(1)){
                    System.out.printf("check %s success\n", checkResult.getUrl());
                }else {
                    is_ok = false;
                    System.out.printf("check %s failed, message is %s , request_id is %s\n",
                            checkResult.getUrl(),checkResult.getMessage(),request_id);
                }
            }
        }
        return is_ok;
    }

    public Object[] Train(List<String> images, String model_name, Map<String, Object> config) throws ApiException {
        Integer job_id = -1;
        String model_id = "";

        AIGCImageTrainResponse response = this.api.aigcImagesTrain(images,model_name,config);
        // Request ID.
        String request_id = response.getRequestId();
        // Request status.
        String code = response.getCode();
        // Request status details.
        String message = response.getMessage();
        // Response content.
        InlineResponse200Data Data = response.getData();

        // Print the returned result.
        if (!code.equals("OK")){
            System.out.printf("aigc_images_train failed, request id is %s\n", request_id);

        }else{
            job_id = response.getData().getJobId();
            model_id = response.getData().getModelId();

            System.out.printf("train job_id is %d, model id %s\n",job_id.intValue(),model_id);

        }
        Integer state = -1;
        while(true){
            AsyncJobResponse jobResponse = this.jobApi.getAsyncJob(job_id);
            String job_code = jobResponse.getCode();
            String job_message = jobResponse.getMessage();
            Map<String, AsyncJobData> job_data = jobResponse.getData();

            if (!job_code.equals("OK")){
                System.out.printf("get_async_job failed, request id is %s, message is %s\n",
                        request_id, job_message);
                job_id = new Integer(-1);
                model_id = "";

            }else{
                state = job_data.get("job").getState();
                if (state.equals(2)){
                    System.out.printf("model %s trained successfully\n",model_id);
                    break;
                }else if(!state.equals(3)){
                    System.out.printf("training model %s\n",model_id);

                    try {
                        Thread.sleep(10000);
                    } catch (InterruptedException e) {
                        e.printStackTrace();
                    }

                }else{
                    System.out.printf("model %s trained failed, message: %s\n",model_id,job_message);
                    break;
                }
            }

        }

        if (!state.equals(2)){
            model_id = "";
        }

        Object[] out = new Object[2];
        out[0] = job_id;
        out[1] = model_id;

        return out;

    }

    public String[] QueryValidImageUrlsByJob(Integer job_id) throws ApiException {
        String[] image_urls = null;

        AsyncJobResponse jobResponse = this.jobApi.getAsyncJob(job_id);
        String request_id = jobResponse.getRequestId();
        String job_code = jobResponse.getCode();
        String job_message = jobResponse.getMessage();
        Map<String, AsyncJobData> job_data = jobResponse.getData();

        if (!job_code.equals("OK")) {
            System.out.printf("get_async_job failed, request id is %s, message is %s\n",
                    request_id, job_message);
        }else {
            Integer state = job_data.get("job").getState();
            if (state == 2){
                System.out.printf("Job %s trained successfully\n", job_id);
                String Result_string = (String) job_data.get("job").getResult();
                JsonObject jsonObject = new JsonParser().parse(Result_string).getAsJsonObject();
                JsonArray result_states = jsonObject.get("states").getAsJsonArray();
                image_urls = new String[result_states.size()];
                for (int result_idx=0; result_idx < result_states.size(); result_idx++){
                    JsonObject result_one = result_states.get(result_idx).getAsJsonObject();
                    String result_url = result_one.get("url").getAsString();
                    image_urls[result_idx] = result_url;
                }

            }else{
                System.out.printf("job %s not ready\n",job_id);
            }
        }

        return image_urls;
    }

    public boolean Create(String model_id, String template_image, String output_image, String model_name, Map<String, Object> config) throws IOException {
        System.out.println("Create");
        AIGCImageCreateResponse createResponse = null;
        try{
            createResponse = api.aigcImagesCreate(model_id, template_image, model_name, config);
        }catch (ApiException e){
            System.out.println();
            System.out.println(e.getResponseBody());
        }
        System.out.println(createResponse);
        // Request ID.
        String request_id = createResponse.getRequestId();
        // Request status.
        String code = createResponse.getCode();
        // Request status details.
        String message = createResponse.getMessage();
        // Response content.
        AIGCImageCreateData data = createResponse.getData();

        if (!code.equals("OK")){
            System.out.printf("aigc_images_create failed, model_id is %s, request_id is %s\n",model_id,request_id);
        }else {
            String imgStr = createResponse.getData().getImage();
            byte[] image = base64ToBytes(imgStr);

            OutputStream out = new FileOutputStream(output_image);

            out.write(image);
            out.flush();
            out.close();

        }
        return true;
    }

    public boolean CreateMulti(String[] model_ids, String template_image, String output_image, String model_name, Map<String, Object> config) throws ApiException, IOException {
        AIGCImageCreateResponse createResponse = api.aigcImagesCreateByMultiModelIds(model_ids, template_image, model_name, config);

        // Request ID.
        String request_id = createResponse.getRequestId();
        // Request status.
        String code = createResponse.getCode();
        // Request status details.
        String message = createResponse.getMessage();
        // Response content.
        AIGCImageCreateData data = createResponse.getData();

        if (!code.equals("OK")){
            System.out.printf("aigc_images_create failed, model_id is %s, request_id is %s\n",model_ids,request_id);
        }else {
            String imgStr = createResponse.getData().getImage();
            byte[] image = base64ToBytes(imgStr);

            OutputStream out = new FileOutputStream(output_image);

            out.write(image);
            out.flush();
            out.close();

        }
        return true;
    }

    @Test
    public void aigcEndtoEndCreate() throws Exception {
        List<String> images = Arrays.asList(
                "https://xxx/0.jpg",
                "https://xxx/1.jpg",
                "https://xxx/2.jpg"
        );

        

        String template_image = "https://xxx.jpg";
        String multi_template_image = "https://xxx.jpg";
      
        String model_name = "train_xl";
        Map<String, Object> config = new HashMap<String, Object>();

        Object[] train_out = Train(images, model_name, config);

        Integer job_id= (Integer) train_out[0];
        String model_id =  (String) train_out[1];



        String[] model_ids = {model_id,model_id};
        model_name = "create_xl"; //""
        Map<String, Object> configure = new TreeMap<String, Object>();

        Create(model_id, template_image,"single_out.jpg", model_name,configure);

        CreateMulti(model_ids, multi_template_image,"multi_out.jpg", model_name,configure);


    }

}

Create an AI portrait using a single reference image (no model training required)

package com.aliyun.aiservice.demo;

import com.aliyun.openservices.aiservice.ApiClient;
import com.aliyun.openservices.aiservice.ApiException;
import com.aliyun.openservices.aiservice.api.AiServiceJobApi;
import com.aliyun.openservices.aiservice.api.AigcImagesApi;
import com.aliyun.openservices.aiservice.model.*;
import com.google.gson.JsonArray;
import com.google.gson.JsonObject;
import com.google.gson.JsonParser;
import org.junit.Test;
import sun.misc.BASE64Decoder;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.util.*;

public class PhotoReferCreateTest {
    public String host = 'HOST';
  	public String appId = 'YOUR-APPID';
  	public String token = 'YOUR-TOKEN';
  
    public ApiClient apiClient = new ApiClient(host, appId, token);
    public AigcImagesApi api = new AigcImagesApi(apiClient);
    public AiServiceJobApi jobApi = new AiServiceJobApi(apiClient);

    public byte[] base64ToBytes(String imgStr) throws IOException {
        BASE64Decoder decoder = new BASE64Decoder();
        byte[] imgBtyes = decoder.decodeBuffer(imgStr);
        for (int i = 0; i < imgBtyes.length; ++i) {
            // Adjust abnormal data.
            if (imgBtyes[i] < 0) {
                imgBtyes[i] += 256;
            }
        }

        return imgBtyes;
    }

    public boolean Check(List<String> images) throws ApiException {
        AIGCImageCheckResponse response = this.api.aigcImagesCheck(images);
        // Request ID.
        String request_id = response.getRequestId();
        // Request status.
        String code = response.getCode();
        // Request status details.
        String message = response.getMessage();
        // Response content.
        AIGCImageCheckData data = response.getData();

        // Print the returned result.
        boolean is_ok = false;
        if (!code.equals("OK")){
            System.out.printf("aigc_images_check failed,request id is %\n", request_id);
        }else{
            is_ok = true;
            System.out.printf("check images done, input %d images, return %d images, %d filtered by lvwang\n",
                    images.size(),(data.getCheckResults().size()),(images.size()-data.getCheckResults().size()));
            for (int check_result_idx=0; check_result_idx < data.getCheckResults().size();check_result_idx++ ){
                AIGCImageCheckResult checkResult = data.getCheckResults().get(check_result_idx);
                Integer checkResultCode = checkResult.getCode();
                if (checkResultCode.equals(1)){
                    System.out.printf("check %s success\n", checkResult.getUrl());
                }else {
                    is_ok = false;
                    System.out.printf("check %s failed, message is %s , request_id is %s\n",
                            checkResult.getUrl(),checkResult.getMessage(),request_id);
                }
            }
        }
        return is_ok;
    }



    public boolean Create(String template_image, String output_image, String ref_image) throws IOException {
        System.out.println("Create");
        AIGCImageCreateResponse createResponse = null;

        Map<String, Object> config = new TreeMap<String, Object>();

        config.put("ipa_control_only",true);
        config.put("ipa_weight",0.6);
        config.put("ipa_image_path",ref_image);
        try{
            createResponse = api.aigcImagesCreate("", template_image, "", config);
        }catch (ApiException e){
            System.out.println();
            System.out.println(e.getResponseBody());
        }
        System.out.println(createResponse);
        // Request ID.
        String request_id = createResponse.getRequestId();
        // Request status.
        String code = createResponse.getCode();
        // Request status details.
        String message = createResponse.getMessage();
        // Response content.
        AIGCImageCreateData data = createResponse.getData();

        if (!code.equals("OK")){
            System.out.printf("aigc_images_create failed, model_id is %s, request_id is %s\n",model_id,request_id);
        }else {
            String imgStr = createResponse.getData().getImage();
            byte[] image = base64ToBytes(imgStr);

            OutputStream out = new FileOutputStream(output_image);

            out.write(image);
            out.flush();
            out.close();

        }
        return true;
    }

    @Test
    public void aigcEndtoEndCreate() throws Exception {

        String template_image = "https://demo.jpg";
        String ref_image = "https://reference.jpg";
      
        Create(template_image,"ref_out.jpg", ref_image);


    }
}

Create an AI portrait by generating a template image from a prompt and a single reference image (no template image required)

package com.aliyun.aiservice.demo;

import com.aliyun.openservices.aiservice.ApiClient;
import com.aliyun.openservices.aiservice.ApiException;
import com.aliyun.openservices.aiservice.api.AiServiceJobApi;
import com.aliyun.openservices.aiservice.api.AigcImagesApi;
import com.aliyun.openservices.aiservice.model.*;
import com.google.gson.JsonArray;
import com.google.gson.JsonObject;
import com.google.gson.JsonParser;
import org.junit.Ignore;
import org.junit.Test;
import sun.misc.BASE64Decoder;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.util.*;

public class PhotoPtomptCreateTest {

    public String host = 'HOST';
  	public String appId = 'YOUR-APPID';
  	public String token = 'YOUR-TOKEN';
  
    public ApiClient apiClient = new ApiClient(host, appId, token);
    public AigcImagesApi api = new AigcImagesApi(apiClient);
    public AiServiceJobApi jobApi = new AiServiceJobApi(apiClient);

    public byte[] base64ToBytes(String imgStr) throws IOException {
        BASE64Decoder decoder = new BASE64Decoder();
        byte[] imgBtyes = decoder.decodeBuffer(imgStr);
        for (int i = 0; i < imgBtyes.length; ++i) {
            // Adjust abnormal data.
            if (imgBtyes[i] < 0) {
                imgBtyes[i] += 256;
            }
        }

        return imgBtyes;
    }

    public boolean Check(List<String> images) throws ApiException {
        AIGCImageCheckResponse response = this.api.aigcImagesCheck(images);
        // Request ID.
        String request_id = response.getRequestId();
        // Request status.
        String code = response.getCode();
        // Request status details.
        String message = response.getMessage();
        // Response content.
        AIGCImageCheckData data = response.getData();

        // Print the returned result.
        boolean is_ok = false;
        if (!code.equals("OK")){
            System.out.printf("aigc_images_check failed,request id is %\n", request_id);
        }else{
            is_ok = true;
            System.out.printf("check images done, input %d images, return %d images, %d filtered by lvwang\n",
                    images.size(),(data.getCheckResults().size()),(images.size()-data.getCheckResults().size()));
            for (int check_result_idx=0; check_result_idx < data.getCheckResults().size();check_result_idx++ ){
                AIGCImageCheckResult checkResult = data.getCheckResults().get(check_result_idx);
                Integer checkResultCode = checkResult.getCode();
                if (checkResultCode.equals(1)){
                    System.out.printf("check %s success\n", checkResult.getUrl());
                }else {
                    is_ok = false;
                    System.out.printf("check %s failed, message is %s , request_id is %s\n",
                            checkResult.getUrl(),checkResult.getMessage(),request_id);
                }
            }
        }
        return is_ok;
    }

    public Object[] Train(List<String> images, String model_name, Map<String, Object> config) throws ApiException {
        Integer job_id = -1;
        String model_id = "";

        AIGCImageTrainResponse response = this.api.aigcImagesTrain(images,model_name,config);
        // Request ID.
        String request_id = response.getRequestId();
        // Request status.
        String code = response.getCode();
        // Request status details.
        String message = response.getMessage();
        // Response content.
        InlineResponse200Data Data = response.getData();

        // Print the returned result.
        if (!code.equals("OK")){
            System.out.printf("aigc_images_train failed, request id is %s\n", request_id);

        }else{
            job_id = response.getData().getJobId();
            model_id = response.getData().getModelId();

            System.out.printf("train job_id is %d, model id %s\n",job_id.intValue(),model_id);

        }
        Integer state = -1;
        while(true){
            AsyncJobResponse jobResponse = this.jobApi.getAsyncJob(job_id);
            String job_code = jobResponse.getCode();
            String job_message = jobResponse.getMessage();
            Map<String, AsyncJobData> job_data = jobResponse.getData();

            if (!job_code.equals("OK")){
                System.out.printf("get_async_job failed, request id is %s, message is %s\n",
                        request_id, job_message);
                job_id = new Integer(-1);
                model_id = "";

            }else{
                state = job_data.get("job").getState();
                if (state.equals(2)){
                    System.out.printf("model %s trained successfully\n",model_id);
                    break;
                }else if(!state.equals(3)){
                    System.out.printf("training model %s\n",model_id);

                    try {
                        Thread.sleep(10000);
                    } catch (InterruptedException e) {
                        e.printStackTrace();
                    }

                }else{
                    System.out.printf("model %s trained failed, message: %s\n",model_id,job_message);
                    break;
                }
            }

        }

        if (!state.equals(2)){
            model_id = "";
        }

        Object[] out = new Object[2];
        out[0] = job_id;
        out[1] = model_id;

        return out;

    }

    public String[] QueryValidImageUrlsByJob(Integer job_id) throws ApiException {
        String[] image_urls = null;

        AsyncJobResponse jobResponse = this.jobApi.getAsyncJob(job_id);
        String request_id = jobResponse.getRequestId();
        String job_code = jobResponse.getCode();
        String job_message = jobResponse.getMessage();
        Map<String, AsyncJobData> job_data = jobResponse.getData();

        if (!job_code.equals("OK")) {
            System.out.printf("get_async_job failed, request id is %s, message is %s\n",
                    request_id, job_message);
        }else {
            Integer state = job_data.get("job").getState();
            if (state == 2){
                System.out.printf("Job %s trained successfully\n", job_id);
                String Result_string = (String) job_data.get("job").getResult();
                JsonObject jsonObject = new JsonParser().parse(Result_string).getAsJsonObject();
                JsonArray result_states = jsonObject.get("states").getAsJsonArray();
                image_urls = new String[result_states.size()];
                for (int result_idx=0; result_idx < result_states.size(); result_idx++){
                    JsonObject result_one = result_states.get(result_idx).getAsJsonObject();
                    String result_url = result_one.get("url").getAsString();
                    image_urls[result_idx] = result_url;
                }

            }else{
                System.out.printf("job %s not ready\n",job_id);
            }
        }

        return image_urls;
    }

    public boolean Create(String model_id, String t2i_prompt, String template_image) throws IOException {
        System.out.println("Create");
        AIGCImageCreateResponse createResponse = null;
        HashMap<String,Object> config = new HashMap<String, Object>();
        config.put("t2i_prompt", t2i_prompt);
        try{
            createResponse = api.aigcImagesCreate(model_id, template_image, "", config);
        }catch (ApiException e){
            System.out.println();
            System.out.println(e.getResponseBody());
        }
        System.out.println(createResponse);
        // Request ID.
        String request_id = createResponse.getRequestId();
        // Request status.
        String code = createResponse.getCode();
        // Request status details.
        String message = createResponse.getMessage();
        // Response content.
        AIGCImageCreateData data = createResponse.getData();

        if (!code.equals("OK")){
            System.out.printf("aigc_images_create failed, model_id is %s, request_id is %s\n",model_id,request_id);
        }else {
            String imgStr = createResponse.getData().getImage();
            byte[] image = base64ToBytes(imgStr);

            OutputStream out = new FileOutputStream("prompt_out.jpg");

            out.write(image);
            out.flush();
            out.close();

        }
        return true;
    }



    @Test
    public void aigcEndtoEndCreate() throws Exception {


        List<String> images =Arrays.asList(
      			"https://xxx/0.jpg",
      			"https://xxx/1.jpg",
      			"https://xxx/2.jpg"
    		);

        String template_image = "https://demo.jpg";

        String model_name = "";
        Map<String, Object> config = new HashMap<String, Object>();

        Object[] train_out = Train(images, model_name, config);

        Integer job_id= (Integer) train_out[0];
        String model_id =  (String) train_out[1];

        String t2i_prompt = "(portrait:1.5), 1girl, bokeh, bouquet, brown_hair, cloud, flower, hairband, hydrangea, lips, long_hair, outdoors, sunlight, white_flower, white_rose, green sweater, sweater, (cloth:1.0), (best quality), (realistic, photo-realistic:1.3), film photography, minor acne, (portrait:1.1), (indirect lighting), extremely detailed CG unity 8k wallpaper, enormous filesize, best quality, realistic, photo-realistic, ultra high res, raw photo, put on makeup";
        Create(model_id, t2i_prompt, template_image);

    }

}

Create an AI portrait by generating a template image from a prompt and a single reference image (no template image or model training required)

package com.aliyun.aiservice.demo;

import com.aliyun.openservices.aiservice.ApiClient;
import com.aliyun.openservices.aiservice.ApiException;
import com.aliyun.openservices.aiservice.api.AiServiceJobApi;
import com.aliyun.openservices.aiservice.api.AigcImagesApi;
import com.aliyun.openservices.aiservice.model.*;
import com.google.gson.JsonArray;
import com.google.gson.JsonObject;
import com.google.gson.JsonParser;
import org.junit.Ignore;
import org.junit.Test;
import sun.misc.BASE64Decoder;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.util.*;

public class PhotoPtomptCreateTest {

    public String host = 'HOST';
  	public String appId = 'YOUR-APPID';
  	public String token = 'YOUR-TOKEN';
  
    public ApiClient apiClient = new ApiClient(host, appId, token);
    public AigcImagesApi api = new AigcImagesApi(apiClient);
    public AiServiceJobApi jobApi = new AiServiceJobApi(apiClient);

    public byte[] base64ToBytes(String imgStr) throws IOException {
        BASE64Decoder decoder = new BASE64Decoder();
        byte[] imgBtyes = decoder.decodeBuffer(imgStr);
        for (int i = 0; i < imgBtyes.length; ++i) {
            // Adjust abnormal data.
            if (imgBtyes[i] < 0) {
                imgBtyes[i] += 256;
            }
        }

        return imgBtyes;
    }

    public boolean Check(List<String> images) throws ApiException {
        AIGCImageCheckResponse response = this.api.aigcImagesCheck(images);
        // Request ID.
        String request_id = response.getRequestId();
        // Request status.
        String code = response.getCode();
        // Request status details.
        String message = response.getMessage();
        // Response content.
        AIGCImageCheckData data = response.getData();

        // Print the returned result.
        boolean is_ok = false;
        if (!code.equals("OK")){
            System.out.printf("aigc_images_check failed,request id is %\n", request_id);
        }else{
            is_ok = true;
            System.out.printf("check images done, input %d images, return %d images, %d filtered by lvwang\n",
                    images.size(),(data.getCheckResults().size()),(images.size()-data.getCheckResults().size()));
            for (int check_result_idx=0; check_result_idx < data.getCheckResults().size();check_result_idx++ ){
                AIGCImageCheckResult checkResult = data.getCheckResults().get(check_result_idx);
                Integer checkResultCode = checkResult.getCode();
                if (checkResultCode.equals(1)){
                    System.out.printf("check %s success\n", checkResult.getUrl());
                }else {
                    is_ok = false;
                    System.out.printf("check %s failed, message is %s , request_id is %s\n",
                            checkResult.getUrl(),checkResult.getMessage(),request_id);
                }
            }
        }
        return is_ok;
    }

    public Object[] Train(List<String> images, String model_name, Map<String, Object> config) throws ApiException {
        Integer job_id = -1;
        String model_id = "";

        AIGCImageTrainResponse response = this.api.aigcImagesTrain(images,model_name,config);
        // Request ID.
        String request_id = response.getRequestId();
        // Request status.
        String code = response.getCode();
        // Request status details.
        String message = response.getMessage();
        // Response content.
        InlineResponse200Data Data = response.getData();

        // Print the returned result.
        if (!code.equals("OK")){
            System.out.printf("aigc_images_train failed, request id is %s\n", request_id);

        }else{
            job_id = response.getData().getJobId();
            model_id = response.getData().getModelId();

            System.out.printf("train job_id is %d, model id %s\n",job_id.intValue(),model_id);

        }
        Integer state = -1;
        while(true){
            AsyncJobResponse jobResponse = this.jobApi.getAsyncJob(job_id);
            String job_code = jobResponse.getCode();
            String job_message = jobResponse.getMessage();
            Map<String, AsyncJobData> job_data = jobResponse.getData();

            if (!job_code.equals("OK")){
                System.out.printf("get_async_job failed, request id is %s, message is %s\n",
                        request_id, job_message);
                job_id = new Integer(-1);
                model_id = "";

            }else{
                state = job_data.get("job").getState();
                if (state.equals(2)){
                    System.out.printf("model %s trained successfully\n",model_id);
                    break;
                }else if(!state.equals(3)){
                    System.out.printf("training model %s\n",model_id);

                    try {
                        Thread.sleep(10000);
                    } catch (InterruptedException e) {
                        e.printStackTrace();
                    }

                }else{
                    System.out.printf("model %s trained failed, message: %s\n",model_id,job_message);
                    break;
                }
            }

        }

        if (!state.equals(2)){
            model_id = "";
        }

        Object[] out = new Object[2];
        out[0] = job_id;
        out[1] = model_id;

        return out;

    }

    public String[] QueryValidImageUrlsByJob(Integer job_id) throws ApiException {
        String[] image_urls = null;

        AsyncJobResponse jobResponse = this.jobApi.getAsyncJob(job_id);
        String request_id = jobResponse.getRequestId();
        String job_code = jobResponse.getCode();
        String job_message = jobResponse.getMessage();
        Map<String, AsyncJobData> job_data = jobResponse.getData();

        if (!job_code.equals("OK")) {
            System.out.printf("get_async_job failed, request id is %s, message is %s\n",
                    request_id, job_message);
        }else {
            Integer state = job_data.get("job").getState();
            if (state == 2){
                System.out.printf("Job %s trained successfully\n", job_id);
                String Result_string = (String) job_data.get("job").getResult();
                JsonObject jsonObject = new JsonParser().parse(Result_string).getAsJsonObject();
                JsonArray result_states = jsonObject.get("states").getAsJsonArray();
                image_urls = new String[result_states.size()];
                for (int result_idx=0; result_idx < result_states.size(); result_idx++){
                    JsonObject result_one = result_states.get(result_idx).getAsJsonObject();
                    String result_url = result_one.get("url").getAsString();
                    image_urls[result_idx] = result_url;
                }

            }else{
                System.out.printf("job %s not ready\n",job_id);
            }
        }

        return image_urls;
    }

    public boolean Create(String t2i_prompt, String template_image, String ref_image) throws IOException {
        System.out.println("Create");
        AIGCImageCreateResponse createResponse = null;
        HashMap<String,Object> config = new HashMap<String, Object>();

        config.put("t2i_prompt", t2i_prompt);
        config.put("ipa_control_only", true);
        config.put("ipa_weight", 0.6);
        config.put("ipa_image_path", ref_image);

        try{
            createResponse = api.aigcImagesCreate("", template_image, "", config);
        }catch (ApiException e){
            System.out.println();
            System.out.println(e.getResponseBody());
        }
        System.out.println(createResponse);
        // Request ID.
        String request_id = createResponse.getRequestId();
        // Request status.
        String code = createResponse.getCode();
        // Request status details.
        String message = createResponse.getMessage();
        // Response content.
        AIGCImageCreateData data = createResponse.getData();

        if (!code.equals("OK")){
            System.out.printf("aigc_images_create failed, request_id is %s\n",request_id);
        }else {
            String imgStr = createResponse.getData().getImage();
            byte[] image = base64ToBytes(imgStr);

            OutputStream out = new FileOutputStream("ref_prompt_out.jpg");

            out.write(image);
            out.flush();
            out.close();

        }
        return true;
    }



    @Test
    public void aigcEndtoEndCreate() throws Exception {

        String template_image = "https://demo.jpg";
        String ref_image = "https://reference.jpg";


        String t2i_prompt = "(portrait:1.5), 1girl, bokeh, bouquet, brown_hair, cloud, flower, hairband, hydrangea, lips, long_hair, outdoors, sunlight, white_flower, white_rose, green sweater, sweater, (cloth:1.0), (best quality), (realistic, photo-realistic:1.3), film photography, minor acne, (portrait:1.1), (indirect lighting), extremely detailed CG unity 8k wallpaper, enormous filesize, best quality, realistic, photo-realistic, ultra high res, raw photo, put on makeup";
        Create(t2i_prompt, template_image, ref_image);

    }

}