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-baseQwen-Image-2512模型文本生成图片 请求示例curl-shttp://192.168.0.11:34185/v1/chat/completions\-HContent-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-doutput.png Qwen3-TTS-12Hz-1.7B-Base文本生成语音# 1. 获取 base64AUDIO_BASE64$(base64-w0/root/test.wav)# 2. 生成包含 ref_text 的 JSON 文件# 注意请把下面的 Hello, this is a reference audio. 替换成你 /root/asr_en.wav 里真实的文字内容cat/tmp/body.jsonEOF { input: 你好这是语音合成测试。, ref_text: Hello, this is a reference audio., ref_audio: data:audio/wav;base64,${AUDIO_BASE64}, response_format: wav } EOF# 3. 发送请求curl-XPOST http://192.168.0.11:41173/v1/audio/speech\-HContent-Type: application/json\-d/tmp/body.json\--outputoutput001.wav