GenerateModel 是非常自由的一个接口,本质是组装一个 http post 请求,并尝试解析响应内容。但仍然有大量的 ai 模型无法覆盖(花样太多了),可使用 HttpUtils 直接请求。
一般涉及图片、声音、视频的生成,都会比较慢。所以大多平台大多是异步的,生成结果一般会是个 taskUrl 拼装的地址(也会有 base64 输出)。
1、示例:输入文本,生成图片
import org.junit.jupiter.api.Test;
import org.noear.solon.ai.generate.GenerateModel;
import org.noear.solon.ai.generate.GenerateResponse;@Test
public void case1_text2image() throws IOException {//生成图片String apiUrl = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis";String taskUrl = "https://dashscope.aliyuncs.com/api/v1/tasks/";GenerateModel generateModel = GenerateModel.of(apiUrl).apiKey(apiKey).taskUrl(taskUrl).model("wanx2.1-t2i-turbo").headerSet("X-DashScope-Async", "enable").build();//一次性返回GenerateResponse resp = generateModel.prompt("a white siamese cat").options(o -> o.size("1024x1024")).call();//打印消息log.info("{}", resp.getContent());assert resp.getContent().getUrl() != null;assert resp.getContent().getUrl().startsWith("https://");
}
2、示例:输入图片,生成新图片(调整图片)
import org.junit.jupiter.api.Test;
import org.noear.solon.ai.generate.GenerateModel;
import org.noear.solon.ai.generate.GenerateResponse;@Test
public void case2_image2image() throws IOException {//编辑图片String apiUrl = "https://dashscope.aliyuncs.com/api/v1/services/aigc/image2image/image-synthesis";String taskUrl = "https://dashscope.aliyuncs.com/api/v1/tasks/";GenerateModel generateModel = GenerateModel.of(apiUrl).apiKey(apiKey).taskUrl(taskUrl).model("wanx2.1-imageedit").headerSet("X-DashScope-Async", "enable").build();GenerateResponse resp = generateModel.prompt(GeneratePrompt.ofKeyValues("function", "stylization_all","prompt", "转换成法国绘本风格","base_image_url", "http://wanx.alicdn.com/material/20250318/stylization_all_1.jpeg")).options(o -> o.optionAdd("n", 1)).call();log.warn("{}", resp.getData());assert resp.getContent().getUrl() != null;assert resp.getContent().getUrl().startsWith("https://");
}
3、示例:输入文本,输出声音(音乐)
import org.junit.jupiter.api.Test;
import org.noear.solon.ai.generate.GenerateModel;
import org.noear.solon.ai.generate.GenerateResponse;@Test
public void case3_music() throws IOException {String apiUrl = "https://ai.gitee.com/v1/async/music/generations";String taskUrl = "https://ai.gitee.com/v1/task/";GenerateModel generateModel = GenerateModel.of(apiUrl).apiKey(apiKey).taskUrl(taskUrl).model("ACE-Step-v1-3.5B").build();//一次性返回GenerateResponse resp = generateModel.prompt(GeneratePrompt.ofKeyValues("prompt", "大海的哥","task", "text2music")).call();log.warn("{}", resp.getData());assert resp.getContent().getUrl() != null;assert resp.getContent().getUrl().startsWith("https://");
}
4、示例:输入文本,生成视频
import org.junit.jupiter.api.Test;
import org.noear.solon.ai.generate.GenerateModel;
import org.noear.solon.ai.generate.GenerateResponse;@Test
public void case4_video() throws IOException {//生成动画String apiUrl = "https://dashscope.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis";String taskUrl = "https://dashscope.aliyuncs.com/api/v1/tasks/";GenerateModel generateModel = GenerateModel.of(apiUrl).apiKey(apiKey).taskUrl(taskUrl).model("wan2.2-i2v-plus").headerSet("X-DashScope-Async", "enable").build();GenerateResponse resp = generateModel.prompt(GeneratePrompt.ofKeyValues("prompt", "一只猫在草地上奔跑","img_url", "https://cdn.translate.alibaba.com/r/wanx-demo-1.png")).options(o -> o.optionAdd("resolution", "480P").optionAdd("prompt_extend", true)).call();log.warn("{}", resp.getData());assert resp.getContent().getUrl() != null;assert resp.getContent().getUrl().startsWith("https://");
}