jschoormans/interior-v2 – Run with an API on Replicate

jschoormans / interior-v2

Remodels interior

Cold

Public
2.3K runs
L40S

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

image

*file

Preview

Input image

prompt

string

Shift + Return to add a new line

Living room, scandinavian interior, photograph, clean, beautiful, high quality, 8kLiving room, scandinavian interior, photograph, clean, beautiful, high quality, 8k

Prompt for image generation

Default: "Living room, scandinavian interior, photograph, clean, beautiful, high quality, 8k"

strength

number

(minimum: 0, maximum: 1)

Strength of the inpainting

Default: 0.999999

max_resolution

integer

(minimum: 512, maximum: 2048)

Maximum resolution of the output image

Default: 1536

keep_furniture_structure

boolean

Keep the furniture structure

Default: false

controlnet_conditioning_scale

number

(minimum: 0, maximum: 1)

Controlnet conditioning scale

Default: 0.7

control_guidance_start

number

(minimum: 0, maximum: 1)

Control guidance start

Default: 0

control_guidance_end

number

(minimum: 0, maximum: 1)

Control guidance end

Default: 0.8

num_inference_steps

integer

(minimum: 1, maximum: 100)

Number of inference steps

Default: 30

guidance_scale

number

(minimum: 1, maximum: 20)

Guidance scale

Default: 7

control_image

file

Control image

inverted_mask_window

file

Inverted mask window

inverted_mask_ceiling

file

Inverted mask ceiling

mask_furniture

file

Mask furniture

negative_prompt

string

Shift + Return to add a new line

(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth

Negative prompt

Default: "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth"

mask_prompt_window

string

Shift + Return to add a new line

Mask prompt window

Default: "window, doorway"

mask_prompt_furniture

string

Shift + Return to add a new line

furniture, couch, table, chair, desk, bed, sofa, cupboard, shelf, cabinet, bookcase, dresser, nightstand, armchair, decoration, plant, flower, pillow, lamp, TVfurniture, couch, table, chair, desk, bed, sofa, cupboard, shelf, cabinet, bookcase, dresser, nightstand, armchair, decoration, plant, flower, pillow, lamp, TV

Mask prompt furniture

Default: "furniture, couch, table, chair, desk, bed, sofa, cupboard, shelf, cabinet, bookcase, dresser, nightstand, armchair, decoration, plant, flower, pillow, lamp, TV"

mask_prompt_ceiling

string

Shift + Return to add a new line

Mask prompt ceiling

Default: "ceiling"

ip_adapter_image

file

IP-Adapter image

empty_room_mode

boolean

Modify depth map for rooms that are originally empty

Default: false

Run this model in Node.js with one line of code:

npx create-replicate --model=jschoormans/interior-v2

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run jschoormans/interior-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jschoormans/interior-v2:8372bd24c6011ea957a0861f0146671eed615e375f038c13259c1882e3c8bac7",
  {
    input: {
      image: "https://replicate.delivery/pbxt/LscMB7dbg6KGk8OI5HbaPFLUukh15hFww9X9S5W5NF4u7OUm/149_1440.jpg",
      prompt: "Living room, scandinavian interior, photograph, clean, beautiful, high quality, 8k",
      strength: 0.999999,
      guidance_scale: 7,
      max_resolution: 1051,
      empty_room_mode: false,
      negative_prompt: "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
      mask_prompt_window: "window, doorway",
      mask_prompt_ceiling: "ceiling",
      num_inference_steps: 30,
      control_guidance_end: 0.8,
      mask_prompt_furniture: "furniture, couch, table, chair, desk, bed, sofa, cupboard, shelf, cabinet, bookcase, dresser, nightstand, armchair, decoration, plant, flower, pillow, lamp, TV",
      control_guidance_start: 0,
      keep_furniture_structure: false,
      controlnet_conditioning_scale: 0.03
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run jschoormans/interior-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jschoormans/interior-v2:8372bd24c6011ea957a0861f0146671eed615e375f038c13259c1882e3c8bac7",
    input={
        "image": "https://replicate.delivery/pbxt/LscMB7dbg6KGk8OI5HbaPFLUukh15hFww9X9S5W5NF4u7OUm/149_1440.jpg",
        "prompt": "Living room, scandinavian interior, photograph, clean, beautiful, high quality, 8k",
        "strength": 0.999999,
        "guidance_scale": 7,
        "max_resolution": 1051,
        "empty_room_mode": False,
        "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
        "mask_prompt_window": "window, doorway",
        "mask_prompt_ceiling": "ceiling",
        "num_inference_steps": 30,
        "control_guidance_end": 0.8,
        "mask_prompt_furniture": "furniture, couch, table, chair, desk, bed, sofa, cupboard, shelf, cabinet, bookcase, dresser, nightstand, armchair, decoration, plant, flower, pillow, lamp, TV",
        "control_guidance_start": 0,
        "keep_furniture_structure": False,
        "controlnet_conditioning_scale": 0.03
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run jschoormans/interior-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "jschoormans/interior-v2:8372bd24c6011ea957a0861f0146671eed615e375f038c13259c1882e3c8bac7",
    "input": {
      "image": "https://replicate.delivery/pbxt/LscMB7dbg6KGk8OI5HbaPFLUukh15hFww9X9S5W5NF4u7OUm/149_1440.jpg",
      "prompt": "Living room, scandinavian interior, photograph, clean, beautiful, high quality, 8k",
      "strength": 0.999999,
      "guidance_scale": 7,
      "max_resolution": 1051,
      "empty_room_mode": false,
      "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
      "mask_prompt_window": "window, doorway",
      "mask_prompt_ceiling": "ceiling",
      "num_inference_steps": 30,
      "control_guidance_end": 0.8,
      "mask_prompt_furniture": "furniture, couch, table, chair, desk, bed, sofa, cupboard, shelf, cabinet, bookcase, dresser, nightstand, armchair, decoration, plant, flower, pillow, lamp, TV",
      "control_guidance_start": 0,
      "keep_furniture_structure": false,
      "controlnet_conditioning_scale": 0.03
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-10-29T15:31:46.193799Z",
  "created_at": "2024-10-29T15:29:36.963000Z",
  "data_removed": false,
  "error": null,
  "id": "m14db5wjrdrgm0cjv3jrvhvx24",
  "input": {
    "image": "https://replicate.delivery/pbxt/LscMB7dbg6KGk8OI5HbaPFLUukh15hFww9X9S5W5NF4u7OUm/149_1440.jpg",
    "prompt": "Living room, scandinavian interior, photograph, clean, beautiful, high quality, 8k",
    "strength": 0.999999,
    "guidance_scale": 7,
    "max_resolution": 1051,
    "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
    "mask_prompt_window": "window, doorway",
    "mask_prompt_ceiling": "ceiling",
    "num_inference_steps": 30,
    "control_guidance_end": 0.8,
    "mask_prompt_furniture": "furniture, couch, table, chair, desk, bed, sofa, cupboard, shelf, cabinet, bookcase, dresser, nightstand, armchair, decoration, plant, flower, pillow, lamp, TV",
    "control_guidance_start": 0,
    "keep_furniture_structure": false,
    "controlnet_conditioning_scale": 0.03
  },
  "logs": "positive_prompt: window\nUserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.5 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.\nUserWarning: None of the inputs have requires_grad=True. Gradients will be None\npositive_prompt:  doorway\nDone!\npositive_prompt: ceiling\nDone!\npositive_prompt: furniture\npositive_prompt: couch\npositive_prompt:  table\npositive_prompt:  chair\npositive_prompt:  desk\npositive_prompt:  bed\npositive_prompt:  sofa\npositive_prompt:  cupboard\npositive_prompt:  shelf\npositive_prompt:  cabinet\npositive_prompt:  bookcase\npositive_prompt:  dresser\npositive_prompt:  nightstand\npositive_prompt:  armchair\npositive_prompt:  decoration\npositive_prompt:  plant\npositive_prompt:  flower\npositive_prompt:  pillow\npositive_prompt:  lamp\npositive_prompt:  TV\nDone!\n`last_sigmas_type='zero'` is not supported for `lower_order_final=False`. Changing scheduler {self.config} to have `lower_order_final` set to True.\n  0%|          | 0/29 [00:00<?, ?it/s]\n  3%|▎         | 1/29 [00:03<01:31,  3.27s/it]\n  7%|▋         | 2/29 [00:03<00:39,  1.48s/it]\n 10%|█         | 3/29 [00:03<00:24,  1.04it/s]\n 14%|█▍        | 4/29 [00:04<00:17,  1.40it/s]\n 17%|█▋        | 5/29 [00:04<00:13,  1.73it/s]\n 21%|██        | 6/29 [00:04<00:11,  2.02it/s]\n 24%|██▍       | 7/29 [00:05<00:09,  2.26it/s]\n 28%|██▊       | 8/29 [00:05<00:08,  2.44it/s]\n 31%|███       | 9/29 [00:05<00:07,  2.59it/s]\n 34%|███▍      | 10/29 [00:06<00:07,  2.70it/s]\n 38%|███▊      | 11/29 [00:06<00:06,  2.78it/s]\n 41%|████▏     | 12/29 [00:06<00:05,  2.84it/s]\n 45%|████▍     | 13/29 [00:07<00:05,  2.88it/s]\n 48%|████▊     | 14/29 [00:07<00:05,  2.91it/s]\n 52%|█████▏    | 15/29 [00:07<00:04,  2.93it/s]\n 55%|█████▌    | 16/29 [00:08<00:04,  2.94it/s]\n 59%|█████▊    | 17/29 [00:08<00:04,  2.95it/s]\n 62%|██████▏   | 18/29 [00:08<00:03,  2.96it/s]\n 66%|██████▌   | 19/29 [00:09<00:03,  2.96it/s]\n 69%|██████▉   | 20/29 [00:09<00:03,  2.96it/s]\n 72%|███████▏  | 21/29 [00:09<00:02,  2.96it/s]\n 76%|███████▌  | 22/29 [00:10<00:02,  2.97it/s]\n 79%|███████▉  | 23/29 [00:10<00:02,  2.96it/s]\n 83%|████████▎ | 24/29 [00:10<00:01,  2.96it/s]\n 86%|████████▌ | 25/29 [00:11<00:01,  2.96it/s]\n 90%|████████▉ | 26/29 [00:11<00:01,  2.96it/s]\n 93%|█████████▎| 27/29 [00:11<00:00,  2.96it/s]\n 97%|█████████▋| 28/29 [00:12<00:00,  2.96it/s]\n100%|██████████| 29/29 [00:12<00:00,  2.96it/s]\n100%|██████████| 29/29 [00:12<00:00,  2.30it/s]\nTime taken: 36.87832283973694 seconds",
  "metrics": {
    "predict_time": 40.255916079,
    "total_time": 129.230799
  },
  "output": [
    "https://replicate.delivery/pbxt/Qy2teTcZNx2lESNXLJ7QGJeKwzdBXm2u0NW54wEb2J0fOWXnA/output.png",
    "https://replicate.delivery/pbxt/WYP8JcfoINRDGan2PxHECkZia3fX51LgzMKmbsrJPjNhHrrTA/control.png",
    "https://replicate.delivery/pbxt/icX4CIkNTo5JOtpzaYzfM6Qc4w29V36pTergijq53qbhHrrTA/inverted_mask_window.png",
    "https://replicate.delivery/pbxt/fQEbrbQm5L3gUqH9v6sPTSKeBem8LXoRsalv8u64rpICPWXnA/inverted_mask_ceiling.png",
    "https://replicate.delivery/pbxt/i6HXINgKqGIlHtFmf2OYe83ahNISNvhblReseJuHcSyEeYddC/mask_furniture.png"
  ],
  "started_at": "2024-10-29T15:31:05.937883Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/m14db5wjrdrgm0cjv3jrvhvx24",
    "cancel": "https://api.replicate.com/v1/predictions/m14db5wjrdrgm0cjv3jrvhvx24/cancel"
  },
  "version": "db5c430268e1bb117f2f0547decafeed3252868cf051ab28f5e1e317b645d743"
}

Generated in

40.3 seconds

Tweak it Share Report

positive_prompt: window
UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.5 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.
UserWarning: None of the inputs have requires_grad=True. Gradients will be None
positive_prompt:  doorway
Done!
positive_prompt: ceiling
Done!
positive_prompt: furniture
positive_prompt: couch
positive_prompt:  table
positive_prompt:  chair
positive_prompt:  desk
positive_prompt:  bed
positive_prompt:  sofa
positive_prompt:  cupboard
positive_prompt:  shelf
positive_prompt:  cabinet
positive_prompt:  bookcase
positive_prompt:  dresser
positive_prompt:  nightstand
positive_prompt:  armchair
positive_prompt:  decoration
positive_prompt:  plant
positive_prompt:  flower
positive_prompt:  pillow
positive_prompt:  lamp
positive_prompt:  TV
Done!
`last_sigmas_type='zero'` is not supported for `lower_order_final=False`. Changing scheduler {self.config} to have `lower_order_final` set to True.
  0%|          | 0/29 [00:00<?, ?it/s]
  3%|▎         | 1/29 [00:03<01:31,  3.27s/it]
  7%|▋         | 2/29 [00:03<00:39,  1.48s/it]
 10%|█         | 3/29 [00:03<00:24,  1.04it/s]
 14%|█▍        | 4/29 [00:04<00:17,  1.40it/s]
 17%|█▋        | 5/29 [00:04<00:13,  1.73it/s]
 21%|██        | 6/29 [00:04<00:11,  2.02it/s]
 24%|██▍       | 7/29 [00:05<00:09,  2.26it/s]
 28%|██▊       | 8/29 [00:05<00:08,  2.44it/s]
 31%|███       | 9/29 [00:05<00:07,  2.59it/s]
 34%|███▍      | 10/29 [00:06<00:07,  2.70it/s]
 38%|███▊      | 11/29 [00:06<00:06,  2.78it/s]
 41%|████▏     | 12/29 [00:06<00:05,  2.84it/s]
 45%|████▍     | 13/29 [00:07<00:05,  2.88it/s]
 48%|████▊     | 14/29 [00:07<00:05,  2.91it/s]
 52%|█████▏    | 15/29 [00:07<00:04,  2.93it/s]
 55%|█████▌    | 16/29 [00:08<00:04,  2.94it/s]
 59%|█████▊    | 17/29 [00:08<00:04,  2.95it/s]
 62%|██████▏   | 18/29 [00:08<00:03,  2.96it/s]
 66%|██████▌   | 19/29 [00:09<00:03,  2.96it/s]
 69%|██████▉   | 20/29 [00:09<00:03,  2.96it/s]
 72%|███████▏  | 21/29 [00:09<00:02,  2.96it/s]
 76%|███████▌  | 22/29 [00:10<00:02,  2.97it/s]
 79%|███████▉  | 23/29 [00:10<00:02,  2.96it/s]
 83%|████████▎ | 24/29 [00:10<00:01,  2.96it/s]
 86%|████████▌ | 25/29 [00:11<00:01,  2.96it/s]
 90%|████████▉ | 26/29 [00:11<00:01,  2.96it/s]
 93%|█████████▎| 27/29 [00:11<00:00,  2.96it/s]
 97%|█████████▋| 28/29 [00:12<00:00,  2.96it/s]
100%|██████████| 29/29 [00:12<00:00,  2.96it/s]
100%|██████████| 29/29 [00:12<00:00,  2.30it/s]
Time taken: 36.87832283973694 seconds

This output was created using a different version of the model, jschoormans/interior-v2:db5c4302.

Examples

View more examples

Run time and cost

This model costs approximately $0.019 to run on Replicate, or 52 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 20 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.