FLUX.1 Kontext Dev on SiliconFlow：重新定义超快、上下文感知的 Image 编辑

2025年6月27日

关键能力

由SiliconFlow的高性能推理引擎提供动力，FLUX.1 Kontext Dev提供显著更快的推理速度和更低的内存消耗，同时保持高质量、精准的Image编辑性能。

迭代编辑：支持迭代编辑，在多次修改中保持一致性。
字符保留：在各种场景和环境中擅长字符保留。
精确编辑控制：允许进行精确的局部和全局编辑。

快速开始

在SiliconFlow 模型广场试用FLUX.1 Kontext Dev。

快速访问API

以下Python示例演示如何调用SiliconFlow的API来执行使用FLUX.1 Kontext Dev模型的上下文感知Image编辑。

import requests

url = "https://api.siliconflow.com/v1/images/generations"

payload = {
    "model": "black-forest-labs/FLUX.1-Kontext-dev",
    "prompt": "an island near sea, with seagulls, moon shining over the sea, light house, boats int he background, fish flying over the sea",
    "image": "data:image/png;base64, XXX",
    "seed": 4999999999,
    "prompt_enhancement": False
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.request("POST", url, json=payload, headers=headers)

print(response.text)

import requests

url = "https://api.siliconflow.com/v1/images/generations"

payload = {
    "model": "black-forest-labs/FLUX.1-Kontext-dev",
    "prompt": "an island near sea, with seagulls, moon shining over the sea, light house, boats int he background, fish flying over the sea",
    "image": "data:image/png;base64, XXX",
    "seed": 4999999999,
    "prompt_enhancement": False
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.request("POST", url, json=payload, headers=headers)

print(response.text)

import requests

url = "https://api.siliconflow.com/v1/images/generations"

payload = {
    "model": "black-forest-labs/FLUX.1-Kontext-dev",
    "prompt": "an island near sea, with seagulls, moon shining over the sea, light house, boats int he background, fish flying over the sea",
    "image": "data:image/png;base64, XXX",
    "seed": 4999999999,
    "prompt_enhancement": False
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.request("POST", url, json=payload, headers=headers)

print(response.text)