jackieyaung/sd-xl-interior-design
Redesign room photos while preserving spatial structure
Run jackieyaung/sd-xl-interior-design with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
Input schema
The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| image |
string
|
输入的室内照片
|
|
| prompt |
string
|
Professional photography of a mid-century modern living room, architectural digest style. Featuring wood, symmetry, Scandinavian design, mixed textures, vintage, reclaimed furniture, ergonomic layout. Cinematic lighting, atmospheric, photorealistic, sharp focus, 8k, highly detailed.
|
设计风格描述
|
| negative_prompt |
string
|
cartoon, illustration, 3d render, painting, drawing, anime, low quality, blurry, watermark, text, signature, people, humans, distorted perspective
|
负向提示词（不想出现的内容）
|
| steps |
integer
|
20
Min: 10 Max: 50 |
推理步数
|
| cfg |
number
|
6
Min: 1 Max: 15 |
CFG Scale（提示词引导强度）
|
| denoise |
number
|
0.75
Max: 1 |
去噪强度（越高变化越大）
|
| depth_strength |
number
|
0.35
Max: 1 |
Depth ControlNet 强度（保持空间结构）
|
| depth_start |
number
|
0.25
Max: 1 |
Depth ControlNet 开始比例
|
| depth_end |
number
|
0.8
Max: 1 |
Depth ControlNet 结束比例
|
| tile_strength |
number
|
0.15
Max: 1 |
Tile ControlNet 强度（保持细节纹理）
|
| tile_start |
number
|
0.6
Max: 1 |
Tile ControlNet 开始比例
|
| tile_end |
number
|
1
Max: 1 |
Tile ControlNet 结束比例
|
| seed |
integer
|
随机种子（留空则随机）
|
|
| output_format |
None
|
webp
|
Format of the output images
|
| output_quality |
integer
|
95
Max: 100 |
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
|
{
"type": "object",
"title": "Input",
"required": [
"image"
],
"properties": {
"cfg": {
"type": "number",
"title": "Cfg",
"default": 6,
"maximum": 15,
"minimum": 1,
"x-order": 4,
"description": "CFG Scale\uff08\u63d0\u793a\u8bcd\u5f15\u5bfc\u5f3a\u5ea6\uff09"
},
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 12,
"description": "\u968f\u673a\u79cd\u5b50\uff08\u7559\u7a7a\u5219\u968f\u673a\uff09"
},
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 0,
"description": "\u8f93\u5165\u7684\u5ba4\u5185\u7167\u7247"
},
"steps": {
"type": "integer",
"title": "Steps",
"default": 20,
"maximum": 50,
"minimum": 10,
"x-order": 3,
"description": "\u63a8\u7406\u6b65\u6570"
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "Professional photography of a mid-century modern living room, architectural digest style. Featuring wood, symmetry, Scandinavian design, mixed textures, vintage, reclaimed furniture, ergonomic layout. Cinematic lighting, atmospheric, photorealistic, sharp focus, 8k, highly detailed.",
"x-order": 1,
"description": "\u8bbe\u8ba1\u98ce\u683c\u63cf\u8ff0"
},
"denoise": {
"type": "number",
"title": "Denoise",
"default": 0.75,
"maximum": 1,
"minimum": 0,
"x-order": 5,
"description": "\u53bb\u566a\u5f3a\u5ea6\uff08\u8d8a\u9ad8\u53d8\u5316\u8d8a\u5927\uff09"
},
"tile_end": {
"type": "number",
"title": "Tile End",
"default": 1,
"maximum": 1,
"minimum": 0,
"x-order": 11,
"description": "Tile ControlNet \u7ed3\u675f\u6bd4\u4f8b"
},
"depth_end": {
"type": "number",
"title": "Depth End",
"default": 0.8,
"maximum": 1,
"minimum": 0,
"x-order": 8,
"description": "Depth ControlNet \u7ed3\u675f\u6bd4\u4f8b"
},
"tile_start": {
"type": "number",
"title": "Tile Start",
"default": 0.6,
"maximum": 1,
"minimum": 0,
"x-order": 10,
"description": "Tile ControlNet \u5f00\u59cb\u6bd4\u4f8b"
},
"depth_start": {
"type": "number",
"title": "Depth Start",
"default": 0.25,
"maximum": 1,
"minimum": 0,
"x-order": 7,
"description": "Depth ControlNet \u5f00\u59cb\u6bd4\u4f8b"
},
"output_format": {
"enum": [
"webp",
"jpg",
"png"
],
"type": "string",
"title": "output_format",
"description": "Format of the output images",
"default": "webp",
"x-order": 13
},
"tile_strength": {
"type": "number",
"title": "Tile Strength",
"default": 0.15,
"maximum": 1,
"minimum": 0,
"x-order": 9,
"description": "Tile ControlNet \u5f3a\u5ea6\uff08\u4fdd\u6301\u7ec6\u8282\u7eb9\u7406\uff09"
},
"depth_strength": {
"type": "number",
"title": "Depth Strength",
"default": 0.35,
"maximum": 1,
"minimum": 0,
"x-order": 6,
"description": "Depth ControlNet \u5f3a\u5ea6\uff08\u4fdd\u6301\u7a7a\u95f4\u7ed3\u6784\uff09"
},
"output_quality": {
"type": "integer",
"title": "Output Quality",
"default": 95,
"maximum": 100,
"minimum": 0,
"x-order": 14,
"description": "Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality."
},
"negative_prompt": {
"type": "string",
"title": "Negative Prompt",
"default": "cartoon, illustration, 3d render, painting, drawing, anime, low quality, blurry, watermark, text, signature, people, humans, distorted perspective",
"x-order": 2,
"description": "\u8d1f\u5411\u63d0\u793a\u8bcd\uff08\u4e0d\u60f3\u51fa\u73b0\u7684\u5185\u5bb9\uff09"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"title": "Output"
}