replicategithubwc/dreamlike-photoreal – Run with an API on Replicate

replicategithubwc / dreamlike-photoreal

Dreamlike Photoreal Model for Splurge Art

Cold

Public
3.3K runs
A100 (80GB)

Iterate in the playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

aurora, girl with super long hair, hair becoming bright stars, in drip modern clothing, intricate, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, unreal engine 5, 8 k, art by artgerm and greg rutkowski and alphonse muchaaurora, girl with super long hair, hair becoming bright stars, in drip modern clothing, intricate, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, unreal engine 5, 8 k, art by artgerm and greg rutkowski and alphonse mucha

Input prompt

Default: "a photo of an astronaut riding a horse on mars"

negative_prompt

string

Shift + Return to add a new line

out of frame, duplicate, watermark, signature, textout of frame, duplicate, watermark, signature, text

Specify things to not see in the output

width

integer

Width of output image

Default: 786

height

integer

Height of output image

Default: 786

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

scheduler

string

Choose a scheduler.

Default: "DPMSolverMultistep"

seed

integer

Random seed. Leave blank to randomize the seed

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

npx create-replicate --model=replicategithubwc/dreamlike-photoreal

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 replicategithubwc/dreamlike-photoreal using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "replicategithubwc/dreamlike-photoreal:21e7e8c7a1476b06e1bbe94d4e08951ebfa478040fa26d4b10dc96abe6bf231d",
  {
    input: {
      width: 768,
      height: 1024,
      prompt: "aurora, girl with super long hair, hair becoming bright stars, in drip modern clothing, intricate, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, unreal engine 5, 8 k, art by artgerm and greg rutkowski and alphonse mucha",
      scheduler: "DPMSolverMultistep",
      num_outputs: 4,
      guidance_scale: 7.5,
      negative_prompt: "out of frame, duplicate, watermark, signature, text",
      num_inference_steps: 50
    }
  }
);

// 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 replicategithubwc/dreamlike-photoreal using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "replicategithubwc/dreamlike-photoreal:21e7e8c7a1476b06e1bbe94d4e08951ebfa478040fa26d4b10dc96abe6bf231d",
    input={
        "width": 768,
        "height": 1024,
        "prompt": "aurora, girl with super long hair, hair becoming bright stars, in drip modern clothing, intricate, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, unreal engine 5, 8 k, art by artgerm and greg rutkowski and alphonse mucha",
        "scheduler": "DPMSolverMultistep",
        "num_outputs": 4,
        "guidance_scale": 7.5,
        "negative_prompt": "out of frame, duplicate, watermark, signature, text",
        "num_inference_steps": 50
    }
)
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 replicategithubwc/dreamlike-photoreal 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": "replicategithubwc/dreamlike-photoreal:21e7e8c7a1476b06e1bbe94d4e08951ebfa478040fa26d4b10dc96abe6bf231d",
    "input": {
      "width": 768,
      "height": 1024,
      "prompt": "aurora, girl with super long hair, hair becoming bright stars, in drip modern clothing, intricate, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, unreal engine 5, 8 k, art by artgerm and greg rutkowski and alphonse mucha",
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 4,
      "guidance_scale": 7.5,
      "negative_prompt": "out of frame, duplicate, watermark, signature, text",
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-07-14T06:18:17.583070Z",
  "created_at": "2023-07-14T06:16:41.251680Z",
  "data_removed": false,
  "error": null,
  "id": "biy2jdtbfgtlw4txsb43knvp2y",
  "input": {
    "width": 768,
    "height": "1024",
    "prompt": "aurora, girl with super long hair, hair becoming bright stars, in drip modern clothing, intricate, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, unreal engine 5, 8 k, art by artgerm and greg rutkowski and alphonse mucha",
    "scheduler": "DPMSolverMultistep",
    "num_outputs": 4,
    "guidance_scale": 7.5,
    "negative_prompt": "out of frame, duplicate, watermark, signature, text",
    "num_inference_steps": 50
  },
  "logs": "Using seed: 17744\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:48,  1.01it/s]\n  4%|▍         | 2/50 [00:01<00:33,  1.43it/s]\n  6%|▌         | 3/50 [00:01<00:28,  1.65it/s]\n  8%|▊         | 4/50 [00:02<00:25,  1.77it/s]\n 10%|█         | 5/50 [00:02<00:24,  1.85it/s]\n 12%|█▏        | 6/50 [00:03<00:23,  1.90it/s]\n 14%|█▍        | 7/50 [00:03<00:22,  1.93it/s]\n 16%|█▌        | 8/50 [00:04<00:21,  1.96it/s]\n 18%|█▊        | 9/50 [00:04<00:20,  1.97it/s]\n 20%|██        | 10/50 [00:05<00:20,  1.98it/s]\n 22%|██▏       | 11/50 [00:05<00:19,  1.99it/s]\n 24%|██▍       | 12/50 [00:06<00:19,  1.99it/s]\n 26%|██▌       | 13/50 [00:06<00:18,  1.99it/s]\n 28%|██▊       | 14/50 [00:07<00:18,  2.00it/s]\n 30%|███       | 15/50 [00:07<00:17,  2.00it/s]\n 32%|███▏      | 16/50 [00:08<00:17,  2.00it/s]\n 34%|███▍      | 17/50 [00:08<00:16,  2.00it/s]\n 36%|███▌      | 18/50 [00:09<00:16,  2.00it/s]\n 38%|███▊      | 19/50 [00:09<00:15,  2.00it/s]\n 40%|████      | 20/50 [00:10<00:15,  2.00it/s]\n 42%|████▏     | 21/50 [00:10<00:14,  2.00it/s]\n 44%|████▍     | 22/50 [00:11<00:14,  2.00it/s]\n 46%|████▌     | 23/50 [00:11<00:13,  2.00it/s]\n 48%|████▊     | 24/50 [00:12<00:13,  2.00it/s]\n 50%|█████     | 25/50 [00:12<00:12,  2.00it/s]\n 52%|█████▏    | 26/50 [00:13<00:12,  2.00it/s]\n 54%|█████▍    | 27/50 [00:13<00:11,  2.00it/s]\n 56%|█████▌    | 28/50 [00:14<00:11,  2.00it/s]\n 58%|█████▊    | 29/50 [00:14<00:10,  2.00it/s]\n 60%|██████    | 30/50 [00:15<00:10,  2.00it/s]\n 62%|██████▏   | 31/50 [00:15<00:09,  2.00it/s]\n 64%|██████▍   | 32/50 [00:16<00:09,  2.00it/s]\n 66%|██████▌   | 33/50 [00:16<00:08,  2.00it/s]\n 68%|██████▊   | 34/50 [00:17<00:08,  2.00it/s]\n 70%|███████   | 35/50 [00:17<00:07,  2.00it/s]\n 72%|███████▏  | 36/50 [00:18<00:07,  2.00it/s]\n 74%|███████▍  | 37/50 [00:18<00:06,  2.00it/s]\n 76%|███████▌  | 38/50 [00:19<00:06,  2.00it/s]\n 78%|███████▊  | 39/50 [00:19<00:05,  2.00it/s]\n 80%|████████  | 40/50 [00:20<00:05,  2.00it/s]\n 82%|████████▏ | 41/50 [00:20<00:04,  2.00it/s]\n 84%|████████▍ | 42/50 [00:21<00:04,  2.00it/s]\n 86%|████████▌ | 43/50 [00:21<00:03,  2.00it/s]\n 88%|████████▊ | 44/50 [00:22<00:03,  2.00it/s]\n 90%|█████████ | 45/50 [00:22<00:02,  2.00it/s]\n 92%|█████████▏| 46/50 [00:23<00:02,  2.00it/s]\n 94%|█████████▍| 47/50 [00:23<00:01,  2.00it/s]\n 96%|█████████▌| 48/50 [00:24<00:01,  1.99it/s]\n 98%|█████████▊| 49/50 [00:24<00:00,  2.00it/s]\n100%|██████████| 50/50 [00:25<00:00,  1.99it/s]\n100%|██████████| 50/50 [00:25<00:00,  1.96it/s]",
  "metrics": {
    "predict_time": 29.125953,
    "total_time": 96.33139
  },
  "output": [
    "https://replicate.delivery/pbxt/TZmLfptOma0PPCLm3rcs19et0wM7rf5nXqDGWfCXyCeFVN9JC/out-0.png",
    "https://replicate.delivery/pbxt/iAHDSKf2VAT7IqNQ4I20uxg5eUgyjXgvMijKzeKZaufhqmeJC/out-1.png",
    "https://replicate.delivery/pbxt/uqmWufJ92fsjepI4SJvzezCQUejAdz1wZV5Fqsw6JUqMVN9JC/out-2.png",
    "https://replicate.delivery/pbxt/h0xudOBfnRRpYCBYv5MSag3IQmHRA6baFeB6gHxYT1mpqpPRA/out-3.png"
  ],
  "started_at": "2023-07-14T06:17:48.457117Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/biy2jdtbfgtlw4txsb43knvp2y",
    "cancel": "https://api.replicate.com/v1/predictions/biy2jdtbfgtlw4txsb43knvp2y/cancel"
  },
  "version": "9c8ae972b146516029b5ff2abc7b9c0fb4131c10b95c1339144b78b8472f3793"
}

Generated in

29.1 seconds

Tweak itReport

Using seed: 17744
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:48,  1.01it/s]
  4%|▍         | 2/50 [00:01<00:33,  1.43it/s]
  6%|▌         | 3/50 [00:01<00:28,  1.65it/s]
  8%|▊         | 4/50 [00:02<00:25,  1.77it/s]
 10%|█         | 5/50 [00:02<00:24,  1.85it/s]
 12%|█▏        | 6/50 [00:03<00:23,  1.90it/s]
 14%|█▍        | 7/50 [00:03<00:22,  1.93it/s]
 16%|█▌        | 8/50 [00:04<00:21,  1.96it/s]
 18%|█▊        | 9/50 [00:04<00:20,  1.97it/s]
 20%|██        | 10/50 [00:05<00:20,  1.98it/s]
 22%|██▏       | 11/50 [00:05<00:19,  1.99it/s]
 24%|██▍       | 12/50 [00:06<00:19,  1.99it/s]
 26%|██▌       | 13/50 [00:06<00:18,  1.99it/s]
 28%|██▊       | 14/50 [00:07<00:18,  2.00it/s]
 30%|███       | 15/50 [00:07<00:17,  2.00it/s]
 32%|███▏      | 16/50 [00:08<00:17,  2.00it/s]
 34%|███▍      | 17/50 [00:08<00:16,  2.00it/s]
 36%|███▌      | 18/50 [00:09<00:16,  2.00it/s]
 38%|███▊      | 19/50 [00:09<00:15,  2.00it/s]
 40%|████      | 20/50 [00:10<00:15,  2.00it/s]
 42%|████▏     | 21/50 [00:10<00:14,  2.00it/s]
 44%|████▍     | 22/50 [00:11<00:14,  2.00it/s]
 46%|████▌     | 23/50 [00:11<00:13,  2.00it/s]
 48%|████▊     | 24/50 [00:12<00:13,  2.00it/s]
 50%|█████     | 25/50 [00:12<00:12,  2.00it/s]
 52%|█████▏    | 26/50 [00:13<00:12,  2.00it/s]
 54%|█████▍    | 27/50 [00:13<00:11,  2.00it/s]
 56%|█████▌    | 28/50 [00:14<00:11,  2.00it/s]
 58%|█████▊    | 29/50 [00:14<00:10,  2.00it/s]
 60%|██████    | 30/50 [00:15<00:10,  2.00it/s]
 62%|██████▏   | 31/50 [00:15<00:09,  2.00it/s]
 64%|██████▍   | 32/50 [00:16<00:09,  2.00it/s]
 66%|██████▌   | 33/50 [00:16<00:08,  2.00it/s]
 68%|██████▊   | 34/50 [00:17<00:08,  2.00it/s]
 70%|███████   | 35/50 [00:17<00:07,  2.00it/s]
 72%|███████▏  | 36/50 [00:18<00:07,  2.00it/s]
 74%|███████▍  | 37/50 [00:18<00:06,  2.00it/s]
 76%|███████▌  | 38/50 [00:19<00:06,  2.00it/s]
 78%|███████▊  | 39/50 [00:19<00:05,  2.00it/s]
 80%|████████  | 40/50 [00:20<00:05,  2.00it/s]
 82%|████████▏ | 41/50 [00:20<00:04,  2.00it/s]
 84%|████████▍ | 42/50 [00:21<00:04,  2.00it/s]
 86%|████████▌ | 43/50 [00:21<00:03,  2.00it/s]
 88%|████████▊ | 44/50 [00:22<00:03,  2.00it/s]
 90%|█████████ | 45/50 [00:22<00:02,  2.00it/s]
 92%|█████████▏| 46/50 [00:23<00:02,  2.00it/s]
 94%|█████████▍| 47/50 [00:23<00:01,  2.00it/s]
 96%|█████████▌| 48/50 [00:24<00:01,  1.99it/s]
 98%|█████████▊| 49/50 [00:24<00:00,  2.00it/s]
100%|██████████| 50/50 [00:25<00:00,  1.99it/s]
100%|██████████| 50/50 [00:25<00:00,  1.96it/s]

This output was created using a different version of the model, replicategithubwc/dreamlike-photoreal:9c8ae972.

Examples

View more examples

Run time and cost

This model costs approximately $0.042 to run on Replicate, or 23 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 A100 (80GB) GPU hardware. Predictions typically complete within 31 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.