/fal-ai/flux-pro/kontext/max/text-to-image
接口: POST https://4zapi.com/fal-ai/flux-pro/kontext/max/text-to-image
官方文档: https://fal.ai/models/fal-ai/flux-pro/kontext/max/text-to-image
请求体 (application/json)
prompt(string, 必填): 生成图像的提示。aspect_ratio(string): 生成图像的宽高比。默认值:"1:1" 支持:21:9、16:9、4:3、3:2、1:1、2:3、3:4、9:16、9:21guidance_scale(number): CFG(无分类器引导)量表用于衡量您希望模型在寻找相关图像时与提示的贴近程度。默认值:3.5 范围值1-20num_images(integer): 生成的图像数量。默认值:1 范围值1-4output_format(string): 生成图片的格式。默认值:"jpeg" 支持default、png、jpegsafety_tolerance(string): 生成图像的安全容差等级。1 表示最严格,5 表示最宽松。默认值:"2"
请求示例
{
"aspect_ratio": "1:1",
"guidance_scale": 3.5,
"num_images": 1,
"output_format": "jpeg",
"prompt": "Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture authentic eye shine and depth. The word \"FLUX\" is painted over it in big, white brush strokes with visible texture.",
"safety_tolerance": "2"
}