Wan AI WAN 2.2 LoRA API | 定价与文档

wan-ai/wan-2-2/lora/text-to-video

根据文本生成视频，并设置 LoRA、分辨率、宽高比、帧数、FPS、推理步数和随机种子。

1. 快速开始

使用 RunComfy 的 API 运行 wan-ai/wan-2-2/lora/text-to-video。可接受的输入与输出请参阅模型的数据结构说明。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-2/lora/text-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "Edge light, low contrast, medium close-up, daylight, left-heavy composition, clean single shot, warm tone, soft light, sunny light, side light, daytime. A young girl sits in a field of tall grass with two fluffy donkeys behind her. She is about 11 or 12 years old, wearing a floral dress, with braided pigtails and a pure smile. She gently plays with wildflowers beside her. Sunlight casts a natural, warm tone across the field.",
    "loras": [
      {
        "path": "https://huggingface.co/neph1/80s_fantasy_movies_wan_2.2/blob/main/80s_fantasy_wan_high_20.safetensors",
        "transformer": "both",
        "scale": 1
      }
    ]
  }'

2. 身份验证

将 YOUR_API_TOKEN 环境变量设置为您的 API 密钥（在个人资料中管理密钥），并在每个请求的 Authorization 标头中以 Bearer 令牌形式携带： Authorization: Bearer $YOUR_API_TOKEN。

3. API 参考

提交请求

提交异步生成任务，将立即获得 request_id 以及用于查询状态、获取结果和取消的 URL。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-2/lora/text-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "Edge light, low contrast, medium close-up, daylight, left-heavy composition, clean single shot, warm tone, soft light, sunny light, side light, daytime. A young girl sits in a field of tall grass with two fluffy donkeys behind her. She is about 11 or 12 years old, wearing a floral dress, with braided pigtails and a pure smile. She gently plays with wildflowers beside her. Sunlight casts a natural, warm tone across the field.",
    "loras": [
      {
        "path": "https://huggingface.co/neph1/80s_fantasy_movies_wan_2.2/blob/main/80s_fantasy_wan_high_20.safetensors",
        "transformer": "both",
        "scale": 1
      }
    ]
  }'

查询请求状态

根据 request_id 获取当前状态（"in_queue"、"in_progress"、"completed" 或 "cancelled"）。

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/status \
  --header "Authorization: Bearer <token>"

获取请求结果

获取指定 request_id 的最终输出与元数据；若任务未完成，响应会返回当前状态，便于继续轮询。

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/result \
  --header "Authorization: Bearer <token>"

取消请求

通过 request_id 取消排队中的任务；进行中的任务无法取消。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/cancel \
  --header "Authorization: Bearer <token>"

4. 文件输入

托管文件（URL）

请提供可公网访问的 HTTPS 地址。确保目标主机允许服务端拉取（无需登录或 Cookie）、未被限流或拦截爬虫。建议：图片 ≤ 50 MB（约 4K），视频 ≤ 100 MB（约 720p 下 2–5 分钟）。私有资源请使用稳定或预签名 URL。

5. 数据结构

输入结构

{
  "type": "object",
  "title": "输入结构",
  "required": [
    "prompt",
    "loras"
  ],
  "properties": {
    "prompt": {
      "title": "提示词",
      "description": "描述主体、动作、环境、构图和所需的视觉方向。",
      "type": "string",
      "default": "Edge light, low contrast, medium close-up, daylight, left-heavy composition, clean single shot, warm tone, soft light, sunny light, side light, daytime. A young girl sits in a field of tall grass with two fluffy donkeys behind her. She is about 11 or 12 years old, wearing a floral dress, with braided pigtails and a pure smile. She gently plays with wildflowers beside her. Sunlight casts a natural, warm tone across the field."
    },
    "loras": {
      "title": "LoRA",
      "description": "必填的 LoRA 列表，最多 3 个；每个路径可使用 URL 或 Hugging Face 仓库 ID。",
      "type": "array",
      "default": [
        {
          "path": "https://huggingface.co/neph1/80s_fantasy_movies_wan_2.2/blob/main/80s_fantasy_wan_high_20.safetensors",
          "transformer": "both",
          "scale": 1
        }
      ],
      "items": {
        "path": {
          "title": "LoRA 路径",
          "description": "LoRA 权重的 URL 或 Hugging Face 仓库 ID（owner/repo）。",
          "type": "string",
          "format": "str",
          "default": ""
        },
        "transformer": {
          "title": "LoRA 应用目标",
          "description": "可选 `high`、`low` 或 `both`，默认为 `both`。",
          "type": "string",
          "format": "str_with_choice",
          "enum": [
            "high",
            "low",
            "both"
          ],
          "default": "both"
        },
        "scale": {
          "title": "LoRA 强度",
          "description": "应用强度范围为 0–4，默认值为 1。",
          "type": "float",
          "format": "float_slider_with_range",
          "minimum": 0,
          "maximum": 4,
          "default": 1
        }
      },
      "maxItems": 3,
      "minItems": 0
    },
    "resolution": {
      "title": "分辨率",
      "description": "可选 `480p`、`580p` 或 `720p`，默认为 `480p`。",
      "type": "string",
      "enum": [
        "480p",
        "580p",
        "720p"
      ],
      "default": "480p"
    },
    "aspect_ratio": {
      "title": "宽高比（宽:高）",
      "description": "可选 `16:9`、`9:16` 或 `1:1`，默认为 `16:9`。",
      "type": "string",
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ],
      "default": "16:9"
    },
    "num_frames": {
      "title": "帧数",
      "description": "可设置为 17–161，默认值为 81。",
      "type": "integer",
      "default": 81,
      "minimum": 17,
      "maximum": 161
    },
    "frames_per_second": {
      "title": "每秒帧数",
      "description": "可设置为 4–60，默认值为 16。",
      "type": "integer",
      "default": 16,
      "minimum": 4,
      "maximum": 60
    },
    "num_inference_steps": {
      "title": "推理步数",
      "description": "可设置为 2–40，默认值为 27。",
      "type": "integer",
      "default": 27,
      "minimum": 2,
      "maximum": 40
    },
    "negative_prompt": {
      "title": "负面提示词",
      "description": "选填，用于描述希望避免的元素。",
      "type": "string",
      "default": ""
    },
    "seed": {
      "title": "随机种子",
      "description": "范围为 10000–99999 的整数随机种子。",
      "type": "integer",
      "maximum": 99999,
      "minimum": 10000,
      "default": 66969
    }
  }
}

输出结构

{
  "output": {
    "type": "object",
    "properties": {
      "image": {
        "type": "string",
        "format": "uri",
        "description": "单张图片 URL"
      },
      "video": {
        "type": "string",
        "format": "uri",
        "description": "单个视频 URL"
      },
      "images": {
        "type": "array",
        "description": "多张图片 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      },
      "videos": {
        "type": "array",
        "description": "多个视频 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      }
    }
  }
}

RunComfy

RunComfy 是首选的 ComfyUI 平台，提供 ComfyUI 在线环境和服务，以及 ComfyUI 工作流具有惊艳的视觉效果。 RunComfy还提供 AI Models, 帮助艺术家利用最新的AI工具创作出令人惊叹的艺术作品。

1. 快速开始

使用 RunComfy 的 API 运行 wan-ai/wan-2-2/lora/text-to-video。可接受的输入与输出请参阅模型的数据结构说明。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-2/lora/text-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "Edge light, low contrast, medium close-up, daylight, left-heavy composition, clean single shot, warm tone, soft light, sunny light, side light, daytime. A young girl sits in a field of tall grass with two fluffy donkeys behind her. She is about 11 or 12 years old, wearing a floral dress, with braided pigtails and a pure smile. She gently plays with wildflowers beside her. Sunlight casts a natural, warm tone across the field.",
    "loras": [
      {
        "path": "https://huggingface.co/neph1/80s_fantasy_movies_wan_2.2/blob/main/80s_fantasy_wan_high_20.safetensors",
        "transformer": "both",
        "scale": 1
      }
    ]
  }'

3. API 参考

提交请求

提交异步生成任务，将立即获得 request_id 以及用于查询状态、获取结果和取消的 URL。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-2/lora/text-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "Edge light, low contrast, medium close-up, daylight, left-heavy composition, clean single shot, warm tone, soft light, sunny light, side light, daytime. A young girl sits in a field of tall grass with two fluffy donkeys behind her. She is about 11 or 12 years old, wearing a floral dress, with braided pigtails and a pure smile. She gently plays with wildflowers beside her. Sunlight casts a natural, warm tone across the field.",
    "loras": [
      {
        "path": "https://huggingface.co/neph1/80s_fantasy_movies_wan_2.2/blob/main/80s_fantasy_wan_high_20.safetensors",
        "transformer": "both",
        "scale": 1
      }
    ]
  }'

查询请求状态

根据 request_id 获取当前状态（"in_queue"、"in_progress"、"completed" 或 "cancelled"）。

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/status \
  --header "Authorization: Bearer <token>"

获取请求结果

获取指定 request_id 的最终输出与元数据；若任务未完成，响应会返回当前状态，便于继续轮询。

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/result \
  --header "Authorization: Bearer <token>"

取消请求

通过 request_id 取消排队中的任务；进行中的任务无法取消。

curl --request POST \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/cancel \
  --header "Authorization: Bearer <token>"

4. 文件输入

托管文件（URL）

5. 数据结构

输入结构

{
  "type": "object",
  "title": "输入结构",
  "required": [
    "prompt",
    "loras"
  ],
  "properties": {
    "prompt": {
      "title": "提示词",
      "description": "描述主体、动作、环境、构图和所需的视觉方向。",
      "type": "string",
      "default": "Edge light, low contrast, medium close-up, daylight, left-heavy composition, clean single shot, warm tone, soft light, sunny light, side light, daytime. A young girl sits in a field of tall grass with two fluffy donkeys behind her. She is about 11 or 12 years old, wearing a floral dress, with braided pigtails and a pure smile. She gently plays with wildflowers beside her. Sunlight casts a natural, warm tone across the field."
    },
    "loras": {
      "title": "LoRA",
      "description": "必填的 LoRA 列表，最多 3 个；每个路径可使用 URL 或 Hugging Face 仓库 ID。",
      "type": "array",
      "default": [
        {
          "path": "https://huggingface.co/neph1/80s_fantasy_movies_wan_2.2/blob/main/80s_fantasy_wan_high_20.safetensors",
          "transformer": "both",
          "scale": 1
        }
      ],
      "items": {
        "path": {
          "title": "LoRA 路径",
          "description": "LoRA 权重的 URL 或 Hugging Face 仓库 ID（owner/repo）。",
          "type": "string",
          "format": "str",
          "default": ""
        },
        "transformer": {
          "title": "LoRA 应用目标",
          "description": "可选 `high`、`low` 或 `both`，默认为 `both`。",
          "type": "string",
          "format": "str_with_choice",
          "enum": [
            "high",
            "low",
            "both"
          ],
          "default": "both"
        },
        "scale": {
          "title": "LoRA 强度",
          "description": "应用强度范围为 0–4，默认值为 1。",
          "type": "float",
          "format": "float_slider_with_range",
          "minimum": 0,
          "maximum": 4,
          "default": 1
        }
      },
      "maxItems": 3,
      "minItems": 0
    },
    "resolution": {
      "title": "分辨率",
      "description": "可选 `480p`、`580p` 或 `720p`，默认为 `480p`。",
      "type": "string",
      "enum": [
        "480p",
        "580p",
        "720p"
      ],
      "default": "480p"
    },
    "aspect_ratio": {
      "title": "宽高比（宽:高）",
      "description": "可选 `16:9`、`9:16` 或 `1:1`，默认为 `16:9`。",
      "type": "string",
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ],
      "default": "16:9"
    },
    "num_frames": {
      "title": "帧数",
      "description": "可设置为 17–161，默认值为 81。",
      "type": "integer",
      "default": 81,
      "minimum": 17,
      "maximum": 161
    },
    "frames_per_second": {
      "title": "每秒帧数",
      "description": "可设置为 4–60，默认值为 16。",
      "type": "integer",
      "default": 16,
      "minimum": 4,
      "maximum": 60
    },
    "num_inference_steps": {
      "title": "推理步数",
      "description": "可设置为 2–40，默认值为 27。",
      "type": "integer",
      "default": 27,
      "minimum": 2,
      "maximum": 40
    },
    "negative_prompt": {
      "title": "负面提示词",
      "description": "选填，用于描述希望避免的元素。",
      "type": "string",
      "default": ""
    },
    "seed": {
      "title": "随机种子",
      "description": "范围为 10000–99999 的整数随机种子。",
      "type": "integer",
      "maximum": 99999,
      "minimum": 10000,
      "default": 66969
    }
  }
}

输出结构

{
  "output": {
    "type": "object",
    "properties": {
      "image": {
        "type": "string",
        "format": "uri",
        "description": "单张图片 URL"
      },
      "video": {
        "type": "string",
        "format": "uri",
        "description": "单个视频 URL"
      },
      "images": {
        "type": "array",
        "description": "多张图片 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      },
      "videos": {
        "type": "array",
        "description": "多个视频 URL",
        "items": {
          "type": "string",
          "format": "uri"
        }
      }
    }
  }
}

根据文本生成视频，并设置 LoRA、分辨率、宽高比、帧数、FPS、推理步数和随机种子。

目录

1. 快速开始

2. 身份验证

3. API 参考

提交请求

查询请求状态

获取请求结果

取消请求

4. 文件输入

托管文件（URL）

5. 数据结构

输入结构

输出结构

根据文本生成视频，并设置 LoRA、分辨率、宽高比、帧数、FPS、推理步数和随机种子。

目录

1. 快速开始

2. 身份验证

3. API 参考

提交请求

查询请求状态

获取请求结果

取消请求

4. 文件输入

托管文件（URL）

5. 数据结构

输入结构

输出结构

WAN 2.2 LoRA 文本生成视频：LoRA 与帧数设置 | RunComfy

根据文本生成视频，并设置 LoRA、分辨率、宽高比、帧数、FPS、推理步数和随机种子。

目录

1. 快速开始

2. 身份验证

3. API 参考

提交请求

查询请求状态

获取请求结果

取消请求

4. 文件输入

托管文件（URL）

5. 数据结构

输入结构

输出结构

WAN 2.2 LoRA 文本生成视频：LoRA 与帧数设置 | RunComfy

根据文本生成视频，并设置 LoRA、分辨率、宽高比、帧数、FPS、推理步数和随机种子。

目录

1. 快速开始

2. 身份验证

3. API 参考

提交请求

查询请求状态

获取请求结果

取消请求

4. 文件输入

托管文件（URL）

5. 数据结构

输入结构

输出结构