adirik / t2i-adapter-sdxl-depth-midas

Modify images using depth maps

Warm

Public
616.7K runs
L40S
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Prediction

adirik/t2i-adapter-sdxl-depth-midas:3263801326d7bf368327b89980371f634086e6bbbf734d9a2943cb516dd8209d

Model

adirik/t2i-adapter-sdxl-depth-midas:32638013

xxu6o73bni3qrucb7vh6ect4oi

Status

Succeeded

Source

Web

Hardware

A40

Total duration

2m 21s

Created

over 1 year ago by @adirik

Input

image
prompt: A photo of a room, 4k photo, highly detailed
scheduler: K_EULER_ANCESTRAL
num_samples: 1
guidance_scale: 7.5
negative_prompt: anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured
num_inference_steps: 30
adapter_conditioning_scale: 1
adapter_conditioning_factor: 1

{
  "image": "https://replicate.delivery/pbxt/JbnAzlvH84NR20HgqUdfnLlMMwwiU8Fv5N3FSjcRXPH6kmmu/org_mid.jpg",
  "prompt": "A photo of a room, 4k photo, highly detailed",
  "scheduler": "K_EULER_ANCESTRAL",
  "num_samples": 1,
  "guidance_scale": 7.5,
  "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
  "num_inference_steps": 30,
  "adapter_conditioning_scale": 1,
  "adapter_conditioning_factor": 1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

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

Run adirik/t2i-adapter-sdxl-depth-midas using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/t2i-adapter-sdxl-depth-midas:3263801326d7bf368327b89980371f634086e6bbbf734d9a2943cb516dd8209d",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JbnAzlvH84NR20HgqUdfnLlMMwwiU8Fv5N3FSjcRXPH6kmmu/org_mid.jpg",
      prompt: "A photo of a room, 4k photo, highly detailed",
      scheduler: "K_EULER_ANCESTRAL",
      num_samples: 1,
      guidance_scale: 7.5,
      negative_prompt: "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
      num_inference_steps: 30,
      adapter_conditioning_scale: 1,
      adapter_conditioning_factor: 1
    }
  }
);

// 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

Import the client:

import replicate

Run adirik/t2i-adapter-sdxl-depth-midas using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/t2i-adapter-sdxl-depth-midas:3263801326d7bf368327b89980371f634086e6bbbf734d9a2943cb516dd8209d",
    input={
        "image": "https://replicate.delivery/pbxt/JbnAzlvH84NR20HgqUdfnLlMMwwiU8Fv5N3FSjcRXPH6kmmu/org_mid.jpg",
        "prompt": "A photo of a room, 4k photo, highly detailed",
        "scheduler": "K_EULER_ANCESTRAL",
        "num_samples": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
        "num_inference_steps": 30,
        "adapter_conditioning_scale": 1,
        "adapter_conditioning_factor": 1
    }
)
print(output)

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

Run adirik/t2i-adapter-sdxl-depth-midas 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": "3263801326d7bf368327b89980371f634086e6bbbf734d9a2943cb516dd8209d",
    "input": {
      "image": "https://replicate.delivery/pbxt/JbnAzlvH84NR20HgqUdfnLlMMwwiU8Fv5N3FSjcRXPH6kmmu/org_mid.jpg",
      "prompt": "A photo of a room, 4k photo, highly detailed",
      "scheduler": "K_EULER_ANCESTRAL",
      "num_samples": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
      "num_inference_steps": 30,
      "adapter_conditioning_scale": 1,
      "adapter_conditioning_factor": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/adirik/t2i-adapter-sdxl-depth-midas@sha256:3263801326d7bf368327b89980371f634086e6bbbf734d9a2943cb516dd8209d \
  -i 'image="https://replicate.delivery/pbxt/JbnAzlvH84NR20HgqUdfnLlMMwwiU8Fv5N3FSjcRXPH6kmmu/org_mid.jpg"' \
  -i 'prompt="A photo of a room, 4k photo, highly detailed"' \
  -i 'scheduler="K_EULER_ANCESTRAL"' \
  -i 'num_samples=1' \
  -i 'guidance_scale=7.5' \
  -i 'negative_prompt="anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured"' \
  -i 'num_inference_steps=30' \
  -i 'adapter_conditioning_scale=1' \
  -i 'adapter_conditioning_factor=1'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/adirik/t2i-adapter-sdxl-depth-midas@sha256:3263801326d7bf368327b89980371f634086e6bbbf734d9a2943cb516dd8209d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "image": "https://replicate.delivery/pbxt/JbnAzlvH84NR20HgqUdfnLlMMwwiU8Fv5N3FSjcRXPH6kmmu/org_mid.jpg",
      "prompt": "A photo of a room, 4k photo, highly detailed",
      "scheduler": "K_EULER_ANCESTRAL",
      "num_samples": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
      "num_inference_steps": 30,
      "adapter_conditioning_scale": 1,
      "adapter_conditioning_factor": 1
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2023-10-03T18:23:59.395638Z",
  "created_at": "2023-10-03T18:21:38.642699Z",
  "data_removed": false,
  "error": null,
  "id": "xxu6o73bni3qrucb7vh6ect4oi",
  "input": {
    "image": "https://replicate.delivery/pbxt/JbnAzlvH84NR20HgqUdfnLlMMwwiU8Fv5N3FSjcRXPH6kmmu/org_mid.jpg",
    "prompt": "A photo of a room, 4k photo, highly detailed",
    "scheduler": "K_EULER_ANCESTRAL",
    "num_samples": 1,
    "guidance_scale": 7.5,
    "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
    "num_inference_steps": 30,
    "adapter_conditioning_scale": 1,
    "adapter_conditioning_factor": 1
  },
  "logs": "0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:05,  5.32it/s]\n  7%|▋         | 2/30 [00:00<00:07,  3.76it/s]\n 10%|█         | 3/30 [00:00<00:07,  3.43it/s]\n 13%|█▎        | 4/30 [00:01<00:07,  3.29it/s]\n 17%|█▋        | 5/30 [00:01<00:07,  3.21it/s]\n 20%|██        | 6/30 [00:01<00:07,  3.17it/s]\n 23%|██▎       | 7/30 [00:02<00:07,  3.14it/s]\n 27%|██▋       | 8/30 [00:02<00:07,  3.12it/s]\n 30%|███       | 9/30 [00:02<00:06,  3.11it/s]\n 33%|███▎      | 10/30 [00:03<00:06,  3.10it/s]\n 37%|███▋      | 11/30 [00:03<00:06,  3.09it/s]\n 40%|████      | 12/30 [00:03<00:05,  3.09it/s]\n 43%|████▎     | 13/30 [00:04<00:05,  3.09it/s]\n 47%|████▋     | 14/30 [00:04<00:05,  3.08it/s]\n 50%|█████     | 15/30 [00:04<00:04,  3.08it/s]\n 53%|█████▎    | 16/30 [00:05<00:04,  3.08it/s]\n 57%|█████▋    | 17/30 [00:05<00:04,  3.08it/s]\n 60%|██████    | 18/30 [00:05<00:03,  3.08it/s]\n 63%|██████▎   | 19/30 [00:06<00:03,  3.08it/s]\n 67%|██████▋   | 20/30 [00:06<00:03,  3.07it/s]\n 70%|███████   | 21/30 [00:06<00:02,  3.07it/s]\n 73%|███████▎  | 22/30 [00:07<00:02,  3.07it/s]\n 77%|███████▋  | 23/30 [00:07<00:02,  3.07it/s]\n 80%|████████  | 24/30 [00:07<00:01,  3.07it/s]\n 83%|████████▎ | 25/30 [00:07<00:01,  3.07it/s]\n 87%|████████▋ | 26/30 [00:08<00:01,  3.07it/s]\n 90%|█████████ | 27/30 [00:08<00:00,  3.07it/s]\n 93%|█████████▎| 28/30 [00:08<00:00,  3.07it/s]\n 97%|█████████▋| 29/30 [00:09<00:00,  3.07it/s]\n100%|██████████| 30/30 [00:09<00:00,  3.07it/s]\n100%|██████████| 30/30 [00:09<00:00,  3.12it/s]",
  "metrics": {
    "predict_time": 14.094359,
    "total_time": 140.752939
  },
  "output": [
    "https://pbxt.replicate.delivery/ZgXuoCSFdiYffUaQY06W2nrdaR0uw28el95sIgYffjbzHHUNC/out-preprocessed.png",
    "https://pbxt.replicate.delivery/jR6ZtGztysLkJxhSeGHWu25iu9GfopTWIAeb6GSdr5K8xBVjA/out-0.png"
  ],
  "started_at": "2023-10-03T18:23:45.301279Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/xxu6o73bni3qrucb7vh6ect4oi",
    "cancel": "https://api.replicate.com/v1/predictions/xxu6o73bni3qrucb7vh6ect4oi/cancel"
  },
  "version": "3263801326d7bf368327b89980371f634086e6bbbf734d9a2943cb516dd8209d"
}

Generated in

14.1 seconds

Tweak it ShareReport

Want to make some of these yourself?

Run this model