负载模型

POSThttps://stablediffusionapi.com/api/v1/enterprise/load_model

该接口用于将模型加载到您的专用服务器。

POST向 https://stablediffusionapi.com/api/v1/enterprise/load_model 接口发送请求。

笔记

选择用于加载的模型必须是扩散器模型。

ControlNet 模型 url 和 model_id表

网址	型号_id
lllyasviel/control_v11p_sd15_inpaint	修复
lllyasviel/control_v11e_sd15_ip2p	ip2p
lllyasviel/control_v11f1e_sd15_tile	瓦
lllyasviel/control_v11e_sd15_shuffle	随机播放
lllyasviel/control_v11p_sd15_softedge	软边
lllyasviel/control_v11p_sd15_scribble	涂
lllyasviel/control_v11p_sd15_lineart	线条艺术
lllyasviel/control_v11p_sd15_normalbae	正常情况
lllyasviel/control_v11f1p_sd15_深度	深度
lllyasviel/control_v11p_sd15_mlsd	最小二乘法
lllyasviel/control_v11p_sd15_canny	精明的

示例

Load a .ckpt or .safetensors Model from Civita

{
  "key": "enterprise_api_key",
  "url": "https://civitai.com/api/download/models/94640",
  "model_id": "majicmix-realistic",
  "model_type": "custom_ckpt",
  "from_safetensors": "yes",
  "webhook": "https://stablediffusionapi.com",
  "revision": "fp32",
  "upcast_attention": "no"
}

Load a .ckpt Model from Civitai

var myHeaders = new Headers();
myHeaders.append("Content-Type", "application/json");

var raw = JSON.stringify({
  "key": "",
  "url": "https://civitai.com/api/download/models/94640",
  "model_id": "majicmix-realistic",
  "model_type": "custom_ckpt",
  "from_safetensors": "yes",
  "webhook": "https://stablediffusionapi.com",
  "revision": "fp32",
  "upcast_attention": "no"
});

var requestOptions = {
  method: 'POST',
  headers: myHeaders,
  body: raw,
  redirect: 'follow'
};

model_reload("https://stablediffusionapi.com/api/v1/enterprise/load_model", requestOptions)
  .then(response => response.text())
  .then(result => console.log(result))
  .catch(error => console.log('error', error));

Load a Huggingface Model

{
  "key": "enterprise_api_key",
  "url": "wavymulder/Analog-Diffusion",
  "model_id": "analog-diffusion",
  "model_type": "huggingface",
  "from_safetensors": "no",
  "webhook": "https://stablediffusionapi.com",
  "revision": "fp32",
  "upcast_attention": "no"
}

Request: Load a Huggingface Model

var myHeaders = new Headers();
myHeaders.append("Content-Type", "application/json");

var raw = JSON.stringify({
  "key": "enterprise_api_key",
  "url": "wavymulder/Analog-Diffusion",
  "model_id": "analog-diffusion",
  "model_type": "huggingface",
  "from_safetensors": "no",
  "webhook": "https://stablediffusionapi.com",
  "revision": "fp32",
  "upcast_attention": "no"
});

var requestOptions = {
  method: 'POST',
  headers: myHeaders,
  body: raw,
  redirect: 'follow'
};

model_reload("https://stablediffusionapi.com/api/v1/enterprise/load_model", requestOptions)
  .then(response => response.text())
  .then(result => console.log(result))
  .catch(error => console.log('error', error));

Request Body: Load a ControlNet Model

{
  "key": "enterprise_api_key",
  "url": "lllyasviel/control_v11p_sd15_canny",
  "model_id": "canny",
  "model_type": "controlnet",
  "webhook": "https://stablediffusionapi.com",
  "revision": "fp32",
  "upcast_attention": "no"
}

Request: Load a ControlNet Model

var myHeaders = new Headers();
myHeaders.append("Content-Type", "application/json");

var raw = JSON.stringify({
  "key": "enterprise_api_key",
  "url": "lllyasviel/control_v11p_sd15_canny",
  "model_id": "canny",
  "model_type": "controlnet",
  "webhook": "https://stablediffusionapi.com",
  "revision": "fp32",
  "upcast_attention": "no"
});

var requestOptions = {
  method: 'POST',
  headers: myHeaders,
  body: raw,
  redirect: 'follow'
};

model_reload("https://stablediffusionapi.com/api/v1/enterprise/load_model", requestOptions)
  .then(response => response.text())
  .then(result => console.log(result))
  .catch(error => console.log('error', error));

请求参数

key

string

必需

您的企业API Key用于请求授权。

url

string

必需

Huggingface模型的 URL 、.ckpt下载链接或来自我们的 Dreambooth API 的训练模型。

model_id

string

必需

为您的模型选择一个名称（ID）。加载的模型将保存在此ID下，以便您在生成图像时参考它。

model_type

string

必需

可用选项：“huggingface”、“api_trained”、“custom_ckpt”、“lora”、“embeddings”、“controlnet”。

from_safetensors

string

必需

如果您正在加载.safetensor文件，请将其设置为“yes” ；否则通过“否”。

webhook

string

必需

用于接收模型加载事件响应的 Webhook。

revision

string

必需

指定加载的模型是“fp16”还是“fp32”。

upcast_attention

string

必需

仅当您加载稳定扩散 2.1模型时才将其设置为“yes” ；否则保持“否”。

{
  "key": "enterprise_api_key",
  "url": "https://civitai.com/api/download/models/94640",
  "model_id": "majicmix-realistic",
  "model_type": "custom_ckpt",
  "from_safetensors": "yes",
  "webhook": "https://stablediffusionapi.com",
  "revision": "fp32",
  "upcast_attention": "no"
}

示例代码

返回响应

成功(200)

HTTP 状态码: 200

内容格式: JSONapplication/json

message

string

必需

status

string

必需

{
  "message": "model load started",
  "status": "success"
}

最后修改时间： 1 年前