Microsoft的MAI-Image-2.5——通用文本生成图像模型,照片级真实感强,贴合提示词,并能在图像中渲染文字。单次请求最多4张图像,支持七种宽高比。
~8s
curl https://www.flixly.ai/api/v1/generate \
-H "Authorization: Bearer flx_live_..." \
-H "Content-Type: application/json" \
-d '{
"model": "mai-image-2-5",
"prompt": "A beautiful sunset over the ocean",
"type": "TEXT_TO_IMAGE"
}'在开发者门户获取你的API密钥。