orbin-ahmed/360_pano – Run with an API on Replicate

orbin-ahmed / 360_pano

Generate panoramic image based on text prompts or image.

Cold

Public
407 runs
A100 (80GB)
GitHub
License

Run with an API

Playground API Examples README Versions

Input

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

npx create-replicate --model=orbin-ahmed/360_pano

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 orbin-ahmed/360_pano using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "orbin-ahmed/360_pano:dc653997df860cbabc5cc46b75b9fc77eef955ca7d1af9c00fc5ba3ada6ffe68",
  {
    input: {
      seed: 0,
      prompt: "A kids room",
      upscale: true,
      guidance_scale: 7.5,
      num_inference_steps: 20
    }
  }
);

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

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

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 orbin-ahmed/360_pano using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "orbin-ahmed/360_pano:dc653997df860cbabc5cc46b75b9fc77eef955ca7d1af9c00fc5ba3ada6ffe68",
    input={
        "seed": 0,
        "prompt": "A kids room",
        "upscale": True,
        "guidance_scale": 7.5,
        "num_inference_steps": 20
    }
)
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 orbin-ahmed/360_pano 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": "dc653997df860cbabc5cc46b75b9fc77eef955ca7d1af9c00fc5ba3ada6ffe68",
    "input": {
      "seed": 0,
      "prompt": "A kids room",
      "upscale": true,
      "guidance_scale": 7.5,
      "num_inference_steps": 20
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-07-28T23:30:02.609626Z",
  "created_at": "2024-07-28T23:26:01.382000Z",
  "data_removed": false,
  "error": null,
  "id": "5qvbz5tgmsrgm0cgzen8gx0sag",
  "input": {
    "seed": 0,
    "prompt": "A kids room",
    "upscale": true,
    "guidance_scale": 7.5,
    "num_inference_steps": 20
  },
  "logs": "Using seed: 15384\nTest with prompt: A kids room\nglobal seed: 15384\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:14,  1.33it/s]\n 15%|█▌        | 3/20 [00:00<00:04,  3.96it/s]\n 25%|██▌       | 5/20 [00:01<00:02,  6.16it/s]\n 35%|███▌      | 7/20 [00:01<00:01,  7.93it/s]\n 45%|████▌     | 9/20 [00:01<00:01,  9.29it/s]\n 55%|█████▌    | 11/20 [00:01<00:00, 10.32it/s]\n 65%|██████▌   | 13/20 [00:01<00:00, 11.08it/s]\n 75%|███████▌  | 15/20 [00:01<00:00, 11.64it/s]\n 85%|████████▌ | 17/20 [00:01<00:00, 12.03it/s]\n 95%|█████████▌| 19/20 [00:02<00:00, 12.30it/s]\n100%|██████████| 20/20 [00:02<00:00,  9.02it/s]\ninputs: upscale=True, running upscaler.\nrunning upscaler step1. Initial super-resolution\n  0%|          | 0/5 [00:00<?, ?it/s]\n 20%|██        | 1/5 [00:02<00:11,  2.98s/it]\n 40%|████      | 2/5 [00:05<00:08,  2.72s/it]\n 60%|██████    | 3/5 [00:08<00:05,  2.64s/it]\n 80%|████████  | 4/5 [00:10<00:02,  2.59s/it]\n100%|██████████| 5/5 [00:13<00:00,  2.57s/it]\n100%|██████████| 5/5 [00:13<00:00,  2.62s/it]\nrunning upscaler step2. Super-resolution with Real-ESRGAN\nTile 1/45\nTile 2/45\nTile 3/45\nTile 4/45\nTile 5/45\nTile 6/45\nTile 7/45\nTile 8/45\nTile 9/45\nTile 10/45\nTile 11/45\nTile 12/45\nTile 13/45\nTile 14/45\nTile 15/45\nTile 16/45\nTile 17/45\nTile 18/45\nTile 19/45\nTile 20/45\nTile 21/45\nTile 22/45\nTile 23/45\nTile 24/45\nTile 25/45\nTile 26/45\nTile 27/45\nTile 28/45\nTile 29/45\nTile 30/45\nTile 31/45\nTile 32/45\nTile 33/45\nTile 34/45\nTile 35/45\nTile 36/45\nTile 37/45\nTile 38/45\nTile 39/45\nTile 40/45\nTile 41/45\nTile 42/45\nTile 43/45\nTile 44/45\nTile 45/45\ninputs: refinement=True, running refinement. This is a bit time-consuming.\n  0%|          | 0/5 [00:00<?, ?it/s]\n 20%|██        | 1/5 [00:12<00:48, 12.08s/it]\n 40%|████      | 2/5 [00:23<00:35, 11.84s/it]\n 60%|██████    | 3/5 [00:35<00:23, 11.81s/it]\n 80%|████████  | 4/5 [00:47<00:11, 11.78s/it]\n100%|██████████| 5/5 [00:59<00:00, 11.78s/it]\n100%|██████████| 5/5 [00:59<00:00, 11.81s/it]\nfinished",
  "metrics": {
    "predict_time": 108.111475536,
    "total_time": 241.227626
  },
  "output": "https://replicate.delivery/pbxt/yf4PzoG74VySBiQ1ZxuC4YkDu53UepehXdjIsy9twBDwzQamA/result.png",
  "started_at": "2024-07-28T23:28:14.498150Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/5qvbz5tgmsrgm0cgzen8gx0sag",
    "cancel": "https://api.replicate.com/v1/predictions/5qvbz5tgmsrgm0cgzen8gx0sag/cancel"
  },
  "version": "bfd01bb5d6c5f9fb4a036049fb8ab770beb6a0d5872ef7ef1c04f4ca26781a36"
}

Generated in

1 minute 48 seconds

Tweak it ShareReport

Using seed: 15384
Test with prompt: A kids room
global seed: 15384
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:14,  1.33it/s]
 15%|█▌        | 3/20 [00:00<00:04,  3.96it/s]
 25%|██▌       | 5/20 [00:01<00:02,  6.16it/s]
 35%|███▌      | 7/20 [00:01<00:01,  7.93it/s]
 45%|████▌     | 9/20 [00:01<00:01,  9.29it/s]
 55%|█████▌    | 11/20 [00:01<00:00, 10.32it/s]
 65%|██████▌   | 13/20 [00:01<00:00, 11.08it/s]
 75%|███████▌  | 15/20 [00:01<00:00, 11.64it/s]
 85%|████████▌ | 17/20 [00:01<00:00, 12.03it/s]
 95%|█████████▌| 19/20 [00:02<00:00, 12.30it/s]
100%|██████████| 20/20 [00:02<00:00,  9.02it/s]
inputs: upscale=True, running upscaler.
running upscaler step1. Initial super-resolution
  0%|          | 0/5 [00:00<?, ?it/s]
 20%|██        | 1/5 [00:02<00:11,  2.98s/it]
 40%|████      | 2/5 [00:05<00:08,  2.72s/it]
 60%|██████    | 3/5 [00:08<00:05,  2.64s/it]
 80%|████████  | 4/5 [00:10<00:02,  2.59s/it]
100%|██████████| 5/5 [00:13<00:00,  2.57s/it]
100%|██████████| 5/5 [00:13<00:00,  2.62s/it]
running upscaler step2. Super-resolution with Real-ESRGAN
Tile 1/45
Tile 2/45
Tile 3/45
Tile 4/45
Tile 5/45
Tile 6/45
Tile 7/45
Tile 8/45
Tile 9/45
Tile 10/45
Tile 11/45
Tile 12/45
Tile 13/45
Tile 14/45
Tile 15/45
Tile 16/45
Tile 17/45
Tile 18/45
Tile 19/45
Tile 20/45
Tile 21/45
Tile 22/45
Tile 23/45
Tile 24/45
Tile 25/45
Tile 26/45
Tile 27/45
Tile 28/45
Tile 29/45
Tile 30/45
Tile 31/45
Tile 32/45
Tile 33/45
Tile 34/45
Tile 35/45
Tile 36/45
Tile 37/45
Tile 38/45
Tile 39/45
Tile 40/45
Tile 41/45
Tile 42/45
Tile 43/45
Tile 44/45
Tile 45/45
inputs: refinement=True, running refinement. This is a bit time-consuming.
  0%|          | 0/5 [00:00<?, ?it/s]
 20%|██        | 1/5 [00:12<00:48, 12.08s/it]
 40%|████      | 2/5 [00:23<00:35, 11.84s/it]
 60%|██████    | 3/5 [00:35<00:23, 11.81s/it]
 80%|████████  | 4/5 [00:47<00:11, 11.78s/it]
100%|██████████| 5/5 [00:59<00:00, 11.78s/it]
100%|██████████| 5/5 [00:59<00:00, 11.81s/it]
finished

This output was created using a different version of the model, orbin-ahmed/360_pano:bfd01bb5.

Examples

View more examples

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.