企业官网建设流程全解析

示例主要是文本生成图片和语音克隆两个模型，如Qwen-Image-2512和Qwen3-TTS-1.7B-base

Qwen-Image-2512模型（文本生成图片） 请求示例curl-shttp://192.168.0.11:34185/v1/chat/completions\-H"Content-Type: application/json"\-d'{ "messages": [ {"role": "user", "content": "A beautiful landscape painting"} ], "extra_body": { "height": 1024, "width": 1024, "num_inference_steps": 50, "true_cfg_scale": 4.0, "seed": 42 } }'|jq-r'.choices[0].message.content[0].image_url.url'|cut-d','-f2-|base64-d>output.png Qwen3-TTS-12Hz-1.7B-Base（文本生成语音）# 1. 获取 base64AUDIO_BASE64=$(base64-w0/root/test.wav)# 2. 生成包含 ref_text 的 JSON 文件# 注意：请把下面的 "Hello, this is a reference audio." 替换成你 /root/asr_en.wav 里真实的文字内容cat>/tmp/body.json<<EOF { "input": "你好，这是语音合成测试。", "ref_text": "Hello, this is a reference audio.", "ref_audio": "data:audio/wav;base64,${AUDIO_BASE64}", "response_format": "wav" } EOF# 3. 发送请求curl-XPOST http://192.168.0.11:41173/v1/audio/speech\-H"Content-Type: application/json"\-d@/tmp/body.json\--outputoutput001.wav