benjielysium/delib_realv | Run with an API on Replicate

This model is actually: prompthero / openjourney-v4

Cold

Public

281 runs

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

RAW photo, a close-up portrait shot of a corporate (man:1.4) CEO overlord looking at the viewer, (expensive haute couture:1.2), embroidered leather jacket embedded with advanced devices, velvet cape, gleaming technology, background is a ((dystopian)) perfect futuristic high-rise office, (high detailed skin:1.2), textured surfaces, ((intricate details, hyperdetailed)), earth tones, muted colors, 8k resolution, (((An extremely complex and advanced technology))), (((hdr)))RAW photo, a close-up portrait shot of a corporate (man:1.4) CEO overlord looking at the viewer, (expensive haute couture:1.2), embroidered leather jacket embedded with advanced devices, velvet cape, gleaming technology, background is a ((dystopian)) perfect futuristic high-rise office, (high detailed skin:1.2), textured surfaces, ((intricate details, hyperdetailed)), earth tones, muted colors, 8k resolution, (((An extremely complex and advanced technology))), (((hdr)))

Input prompt

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

negative_prompt

string

Shift + Return to add a new line

Specify things to not see in the output

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 768

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 768

prompt_strength

number

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

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=benjielysium/delib_realv

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";
import fs from "node:fs";

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

Run benjielysium/delib_realv using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "benjielysium/delib_realv:c581bb078c9f74e580960262a493d9ea186b2e76e2a71713b4daa4a900ccc9a5",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "RAW photo, a close-up portrait shot of a corporate (man:1.4) CEO overlord looking at the viewer, (expensive haute couture:1.2), embroidered leather jacket embedded with advanced devices, velvet cape, gleaming technology, background is a ((dystopian)) perfect futuristic high-rise office, (high detailed skin:1.2), textured surfaces, ((intricate details, hyperdetailed)), earth tones, muted colors, 8k resolution, (((An extremely complex and advanced technology))), (((hdr)))",
      scheduler: "DPMSolverMultistep",
      num_outputs: 1,
      guidance_scale: 7.5,
      prompt_strength: 0.8,
      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 benjielysium/delib_realv using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "benjielysium/delib_realv:c581bb078c9f74e580960262a493d9ea186b2e76e2a71713b4daa4a900ccc9a5",
    input={
        "width": 512,
        "height": 512,
        "prompt": "RAW photo, a close-up portrait shot of a corporate (man:1.4) CEO overlord looking at the viewer, (expensive haute couture:1.2), embroidered leather jacket embedded with advanced devices, velvet cape, gleaming technology, background is a ((dystopian)) perfect futuristic high-rise office, (high detailed skin:1.2), textured surfaces, ((intricate details, hyperdetailed)), earth tones, muted colors, 8k resolution, (((An extremely complex and advanced technology))), (((hdr)))",
        "scheduler": "DPMSolverMultistep",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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 benjielysium/delib_realv 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": "benjielysium/delib_realv:c581bb078c9f74e580960262a493d9ea186b2e76e2a71713b4daa4a900ccc9a5",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "RAW photo, a close-up portrait shot of a corporate (man:1.4) CEO overlord looking at the viewer, (expensive haute couture:1.2), embroidered leather jacket embedded with advanced devices, velvet cape, gleaming technology, background is a ((dystopian)) perfect futuristic high-rise office, (high detailed skin:1.2), textured surfaces, ((intricate details, hyperdetailed)), earth tones, muted colors, 8k resolution, (((An extremely complex and advanced technology))), (((hdr)))",
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "prompt_strength": 0.8,
      "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": "2023-05-27T00:08:29.695128Z",
  "created_at": "2023-05-27T00:07:59.747332Z",
  "data_removed": false,
  "error": null,
  "id": "vhiexiczy5bhzpfiyqe2664qoa",
  "input": {
    "width": "512",
    "height": "512",
    "prompt": "RAW photo, a close-up portrait shot of a corporate (man:1.4) CEO overlord looking at the viewer, (expensive haute couture:1.2), embroidered leather jacket embedded with advanced devices, velvet cape, gleaming technology, background is a ((dystopian)) perfect futuristic high-rise office, (high detailed skin:1.2), textured surfaces, ((intricate details, hyperdetailed)), earth tones, muted colors, 8k resolution, (((An extremely complex and advanced technology))), (((hdr)))",
    "scheduler": "DPMSolverMultistep",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 65429\nThe config attributes {'clip_sample_range': 1.0} were passed to PNDMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\nThe config attributes {'clip_sample_range': 1.0} were passed to LMSDiscreteScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\nThe config attributes {'clip_sample_range': 1.0} were passed to DDIMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\nThe config attributes {'clip_sample_range': 1.0} were passed to EulerDiscreteScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\nThe config attributes {'clip_sample_range': 1.0} were passed to EulerAncestralDiscreteScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\nThe config attributes {'clip_sample_range': 1.0} were passed to DPMSolverMultistepScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: [', (( intricate details, hyperdetailed )), earth tones, muted colors, 8 k resolution, ((( an extremely complex and advanced technology ))), ((( hdr )))']\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:29,  1.66it/s]\n  4%|▍         | 2/50 [00:01<00:27,  1.76it/s]\n  6%|▌         | 3/50 [00:01<00:26,  1.78it/s]\n  8%|▊         | 4/50 [00:02<00:25,  1.79it/s]\n 10%|█         | 5/50 [00:02<00:24,  1.80it/s]\n 12%|█▏        | 6/50 [00:03<00:24,  1.80it/s]\n 14%|█▍        | 7/50 [00:03<00:23,  1.81it/s]\n 16%|█▌        | 8/50 [00:04<00:23,  1.80it/s]\n 18%|█▊        | 9/50 [00:05<00:22,  1.81it/s]\n 20%|██        | 10/50 [00:05<00:22,  1.80it/s]\n 22%|██▏       | 11/50 [00:06<00:21,  1.80it/s]\n 24%|██▍       | 12/50 [00:06<00:21,  1.80it/s]\n 26%|██▌       | 13/50 [00:07<00:20,  1.79it/s]\n 28%|██▊       | 14/50 [00:07<00:20,  1.79it/s]\n 30%|███       | 15/50 [00:08<00:19,  1.79it/s]\n 32%|███▏      | 16/50 [00:08<00:19,  1.79it/s]\n 34%|███▍      | 17/50 [00:09<00:18,  1.78it/s]\n 36%|███▌      | 18/50 [00:10<00:17,  1.78it/s]\n 38%|███▊      | 19/50 [00:10<00:17,  1.78it/s]\n 40%|████      | 20/50 [00:11<00:16,  1.78it/s]\n 42%|████▏     | 21/50 [00:11<00:16,  1.77it/s]\n 44%|████▍     | 22/50 [00:12<00:15,  1.77it/s]\n 46%|████▌     | 23/50 [00:12<00:15,  1.77it/s]\n 48%|████▊     | 24/50 [00:13<00:14,  1.77it/s]\n 50%|█████     | 25/50 [00:14<00:14,  1.77it/s]\n 52%|█████▏    | 26/50 [00:14<00:13,  1.76it/s]\n 54%|█████▍    | 27/50 [00:15<00:13,  1.76it/s]\n 56%|█████▌    | 28/50 [00:15<00:12,  1.76it/s]\n 58%|█████▊    | 29/50 [00:16<00:11,  1.76it/s]\n 60%|██████    | 30/50 [00:16<00:11,  1.75it/s]\n 62%|██████▏   | 31/50 [00:17<00:10,  1.75it/s]\n 64%|██████▍   | 32/50 [00:18<00:10,  1.75it/s]\n 66%|██████▌   | 33/50 [00:18<00:09,  1.75it/s]\n 68%|██████▊   | 34/50 [00:19<00:09,  1.75it/s]\n 70%|███████   | 35/50 [00:19<00:08,  1.74it/s]\n 72%|███████▏  | 36/50 [00:20<00:08,  1.74it/s]\n 74%|███████▍  | 37/50 [00:20<00:07,  1.73it/s]\n 76%|███████▌  | 38/50 [00:21<00:06,  1.72it/s]\n 78%|███████▊  | 39/50 [00:22<00:06,  1.73it/s]\n 80%|████████  | 40/50 [00:22<00:05,  1.73it/s]\n 82%|████████▏ | 41/50 [00:23<00:05,  1.72it/s]\n 84%|████████▍ | 42/50 [00:23<00:04,  1.72it/s]\n 86%|████████▌ | 43/50 [00:24<00:04,  1.71it/s]\n 88%|████████▊ | 44/50 [00:24<00:03,  1.71it/s]\n 90%|█████████ | 45/50 [00:25<00:02,  1.71it/s]\n 92%|█████████▏| 46/50 [00:26<00:02,  1.71it/s]\n 94%|█████████▍| 47/50 [00:26<00:01,  1.71it/s]\n 96%|█████████▌| 48/50 [00:27<00:01,  1.70it/s]\n 98%|█████████▊| 49/50 [00:27<00:00,  1.70it/s]\n100%|██████████| 50/50 [00:28<00:00,  1.70it/s]\n100%|██████████| 50/50 [00:28<00:00,  1.75it/s]",
  "metrics": {
    "predict_time": 29.971745,
    "total_time": 29.947796
  },
  "output": [
    "https://replicate.delivery/pbxt/5vh3EKAyHdK7HJKV7SVXQVeBBRBZsoEFYjnUc9zTotTevvfhA/out-0.png"
  ],
  "started_at": "2023-05-27T00:07:59.723383Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/vhiexiczy5bhzpfiyqe2664qoa",
    "cancel": "https://api.replicate.com/v1/predictions/vhiexiczy5bhzpfiyqe2664qoa/cancel"
  },
  "version": "c581bb078c9f74e580960262a493d9ea186b2e76e2a71713b4daa4a900ccc9a5"
}

Generated in

30.0 seconds

Tweak it Iterate in playgroundReport View full prediction

Using seed: 65429
The config attributes {'clip_sample_range': 1.0} were passed to PNDMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
The config attributes {'clip_sample_range': 1.0} were passed to LMSDiscreteScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
The config attributes {'clip_sample_range': 1.0} were passed to DDIMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
The config attributes {'clip_sample_range': 1.0} were passed to EulerDiscreteScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
The config attributes {'clip_sample_range': 1.0} were passed to EulerAncestralDiscreteScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
The config attributes {'clip_sample_range': 1.0} were passed to DPMSolverMultistepScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: [', (( intricate details, hyperdetailed )), earth tones, muted colors, 8 k resolution, ((( an extremely complex and advanced technology ))), ((( hdr )))']
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:29,  1.66it/s]
  4%|▍         | 2/50 [00:01<00:27,  1.76it/s]
  6%|▌         | 3/50 [00:01<00:26,  1.78it/s]
  8%|▊         | 4/50 [00:02<00:25,  1.79it/s]
 10%|█         | 5/50 [00:02<00:24,  1.80it/s]
 12%|█▏        | 6/50 [00:03<00:24,  1.80it/s]
 14%|█▍        | 7/50 [00:03<00:23,  1.81it/s]
 16%|█▌        | 8/50 [00:04<00:23,  1.80it/s]
 18%|█▊        | 9/50 [00:05<00:22,  1.81it/s]
 20%|██        | 10/50 [00:05<00:22,  1.80it/s]
 22%|██▏       | 11/50 [00:06<00:21,  1.80it/s]
 24%|██▍       | 12/50 [00:06<00:21,  1.80it/s]
 26%|██▌       | 13/50 [00:07<00:20,  1.79it/s]
 28%|██▊       | 14/50 [00:07<00:20,  1.79it/s]
 30%|███       | 15/50 [00:08<00:19,  1.79it/s]
 32%|███▏      | 16/50 [00:08<00:19,  1.79it/s]
 34%|███▍      | 17/50 [00:09<00:18,  1.78it/s]
 36%|███▌      | 18/50 [00:10<00:17,  1.78it/s]
 38%|███▊      | 19/50 [00:10<00:17,  1.78it/s]
 40%|████      | 20/50 [00:11<00:16,  1.78it/s]
 42%|████▏     | 21/50 [00:11<00:16,  1.77it/s]
 44%|████▍     | 22/50 [00:12<00:15,  1.77it/s]
 46%|████▌     | 23/50 [00:12<00:15,  1.77it/s]
 48%|████▊     | 24/50 [00:13<00:14,  1.77it/s]
 50%|█████     | 25/50 [00:14<00:14,  1.77it/s]
 52%|█████▏    | 26/50 [00:14<00:13,  1.76it/s]
 54%|█████▍    | 27/50 [00:15<00:13,  1.76it/s]
 56%|█████▌    | 28/50 [00:15<00:12,  1.76it/s]
 58%|█████▊    | 29/50 [00:16<00:11,  1.76it/s]
 60%|██████    | 30/50 [00:16<00:11,  1.75it/s]
 62%|██████▏   | 31/50 [00:17<00:10,  1.75it/s]
 64%|██████▍   | 32/50 [00:18<00:10,  1.75it/s]
 66%|██████▌   | 33/50 [00:18<00:09,  1.75it/s]
 68%|██████▊   | 34/50 [00:19<00:09,  1.75it/s]
 70%|███████   | 35/50 [00:19<00:08,  1.74it/s]
 72%|███████▏  | 36/50 [00:20<00:08,  1.74it/s]
 74%|███████▍  | 37/50 [00:20<00:07,  1.73it/s]
 76%|███████▌  | 38/50 [00:21<00:06,  1.72it/s]
 78%|███████▊  | 39/50 [00:22<00:06,  1.73it/s]
 80%|████████  | 40/50 [00:22<00:05,  1.73it/s]
 82%|████████▏ | 41/50 [00:23<00:05,  1.72it/s]
 84%|████████▍ | 42/50 [00:23<00:04,  1.72it/s]
 86%|████████▌ | 43/50 [00:24<00:04,  1.71it/s]
 88%|████████▊ | 44/50 [00:24<00:03,  1.71it/s]
 90%|█████████ | 45/50 [00:25<00:02,  1.71it/s]
 92%|█████████▏| 46/50 [00:26<00:02,  1.71it/s]
 94%|█████████▍| 47/50 [00:26<00:01,  1.71it/s]
 96%|█████████▌| 48/50 [00:27<00:01,  1.70it/s]
 98%|█████████▊| 49/50 [00:27<00:00,  1.70it/s]
100%|██████████| 50/50 [00:28<00:00,  1.70it/s]
100%|██████████| 50/50 [00:28<00:00,  1.75it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.014 to run on Replicate, or 71 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 T4 GPU hardware. Predictions typically complete within 63 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.