lukevink/erikadress_jix | Run with an API on Replicate

lukevink / erikadress_jix

Cold

Public
4.2K runs
A100 (80GB)

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

photo of a woman wearing a jIX dress standing on a beach, half portrait, ((perfect face)), ((detailed face)), hyperrealism, hd quality, 8k resolution, Canon Eos 5Dphoto of a woman wearing a jIX dress standing on a beach, half portrait, ((perfect face)), ((detailed face)), hyperrealism, hd quality, 8k resolution, Canon Eos 5D

Input prompt

Default: "a cjw cat in a bucket"

negative_prompt

string

Shift + Return to add a new line

(((painting))), (((ugly))), (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck)))(((painting))), (((ugly))), (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck)))

The prompt NOT to guide the image generation. Ignored when not using guidance

width

integer

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

Default: 512

height

integer

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

Default: 512

num_outputs

integer

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

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=lukevink/erikadress_jix

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

const output = await replicate.run(
  "lukevink/erikadress_jix:8aac0c5751efacf1aeb556df676c875b3adaf09d48e7102ab52bbee775549c27",
  {
    input: {
      width: 512,
      height: 768,
      prompt: "photo of a woman wearing a jIX dress standing on a beach, half portrait, ((perfect face)), ((detailed face)), hyperrealism, hd quality, 8k resolution, Canon Eos 5D",
      num_outputs: 4,
      guidance_scale: 7.5,
      negative_prompt: "(((painting))), (((ugly))), (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck)))",
      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 lukevink/erikadress_jix using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lukevink/erikadress_jix:8aac0c5751efacf1aeb556df676c875b3adaf09d48e7102ab52bbee775549c27",
    input={
        "width": 512,
        "height": 768,
        "prompt": "photo of a woman wearing a jIX dress standing on a beach, half portrait, ((perfect face)), ((detailed face)), hyperrealism, hd quality, 8k resolution, Canon Eos 5D",
        "num_outputs": 4,
        "guidance_scale": 7.5,
        "negative_prompt": "(((painting))), (((ugly))), (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck)))",
        "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 lukevink/erikadress_jix 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": "lukevink/erikadress_jix:8aac0c5751efacf1aeb556df676c875b3adaf09d48e7102ab52bbee775549c27",
    "input": {
      "width": 512,
      "height": 768,
      "prompt": "photo of a woman wearing a jIX dress standing on a beach, half portrait, ((perfect face)), ((detailed face)), hyperrealism, hd quality, 8k resolution, Canon Eos 5D",
      "num_outputs": 4,
      "guidance_scale": 7.5,
      "negative_prompt": "(((painting))), (((ugly))), (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck)))",
      "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": "2022-12-24T08:30:13.647653Z",
  "created_at": "2022-12-24T08:28:07.918587Z",
  "data_removed": false,
  "error": null,
  "id": "dlsi3sfjprfdxaut3jncousauu",
  "input": {
    "width": 512,
    "height": "768",
    "prompt": "photo of a woman wearing a jIX dress standing on a beach, half portrait, ((perfect face)), ((detailed face)), hyperrealism, hd quality, 8k resolution, Canon Eos 5D",
    "num_outputs": "4",
    "guidance_scale": 7.5,
    "negative_prompt": "(((painting))), (((ugly))), (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck)))",
    "num_inference_steps": 50
  },
  "logs": "Loading pipeline...\nUsing seed: 6298\nGlobal seed set to 6298\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:02<02:08,  2.63s/it]\n  4%|▍         | 2/50 [00:02<00:59,  1.25s/it]\n  6%|▌         | 3/50 [00:03<00:37,  1.24it/s]\n  8%|▊         | 4/50 [00:03<00:27,  1.67it/s]\n 10%|█         | 5/50 [00:03<00:21,  2.07it/s]\n 12%|█▏        | 6/50 [00:04<00:18,  2.41it/s]\n 14%|█▍        | 7/50 [00:04<00:15,  2.70it/s]\n 16%|█▌        | 8/50 [00:04<00:14,  2.92it/s]\n 18%|█▊        | 9/50 [00:04<00:13,  3.10it/s]\n 20%|██        | 10/50 [00:05<00:12,  3.23it/s]\n 22%|██▏       | 11/50 [00:05<00:11,  3.33it/s]\n 24%|██▍       | 12/50 [00:05<00:11,  3.40it/s]\n 26%|██▌       | 13/50 [00:05<00:10,  3.45it/s]\n 28%|██▊       | 14/50 [00:06<00:10,  3.48it/s]\n 30%|███       | 15/50 [00:06<00:09,  3.51it/s]\n 32%|███▏      | 16/50 [00:06<00:09,  3.53it/s]\n 34%|███▍      | 17/50 [00:07<00:09,  3.54it/s]\n 36%|███▌      | 18/50 [00:07<00:09,  3.55it/s]\n 38%|███▊      | 19/50 [00:07<00:08,  3.56it/s]\n 40%|████      | 20/50 [00:07<00:08,  3.56it/s]\n 42%|████▏     | 21/50 [00:08<00:08,  3.56it/s]\n 44%|████▍     | 22/50 [00:08<00:07,  3.56it/s]\n 46%|████▌     | 23/50 [00:08<00:07,  3.56it/s]\n 48%|████▊     | 24/50 [00:09<00:07,  3.56it/s]\n 50%|█████     | 25/50 [00:09<00:07,  3.56it/s]\n 52%|█████▏    | 26/50 [00:09<00:06,  3.56it/s]\n 54%|█████▍    | 27/50 [00:09<00:06,  3.56it/s]\n 56%|█████▌    | 28/50 [00:10<00:06,  3.56it/s]\n 58%|█████▊    | 29/50 [00:10<00:05,  3.56it/s]\n 60%|██████    | 30/50 [00:10<00:05,  3.56it/s]\n 62%|██████▏   | 31/50 [00:11<00:05,  3.56it/s]\n 64%|██████▍   | 32/50 [00:11<00:05,  3.57it/s]\n 66%|██████▌   | 33/50 [00:11<00:04,  3.57it/s]\n 68%|██████▊   | 34/50 [00:11<00:04,  3.57it/s]\n 70%|███████   | 35/50 [00:12<00:04,  3.57it/s]\n 72%|███████▏  | 36/50 [00:12<00:03,  3.57it/s]\n 74%|███████▍  | 37/50 [00:12<00:03,  3.57it/s]\n 76%|███████▌  | 38/50 [00:13<00:03,  3.57it/s]\n 78%|███████▊  | 39/50 [00:13<00:03,  3.57it/s]\n 80%|████████  | 40/50 [00:13<00:02,  3.57it/s]\n 82%|████████▏ | 41/50 [00:13<00:02,  3.57it/s]\n 84%|████████▍ | 42/50 [00:14<00:02,  3.57it/s]\n 86%|████████▌ | 43/50 [00:14<00:01,  3.57it/s]\n 88%|████████▊ | 44/50 [00:14<00:01,  3.57it/s]\n 90%|█████████ | 45/50 [00:14<00:01,  3.57it/s]\n 92%|█████████▏| 46/50 [00:15<00:01,  3.57it/s]\n 94%|█████████▍| 47/50 [00:15<00:00,  3.57it/s]\n 96%|█████████▌| 48/50 [00:15<00:00,  3.57it/s]\n 98%|█████████▊| 49/50 [00:16<00:00,  3.57it/s]\n100%|██████████| 50/50 [00:16<00:00,  3.57it/s]\n100%|██████████| 50/50 [00:16<00:00,  3.05it/s]",
  "metrics": {
    "predict_time": 23.164648,
    "total_time": 125.729066
  },
  "output": [
    "https://replicate.delivery/pbxt/Tbh9HPbVIpIBEZfbzfWIHKiOHTeXWVwNSoZy5WGGMNxkUNagA/out-0.png",
    "https://replicate.delivery/pbxt/HFnIJjzm5o55IR3MZALBSRfhnwpB74S5wXHjkJlic8nJVjGIA/out-1.png",
    "https://replicate.delivery/pbxt/SBc0ATyFkj6HIJqcOZn3m8Y0EUOBxS2LKg9pEEasC8DlqRDE/out-2.png",
    "https://replicate.delivery/pbxt/4SV7SRI2WELHBRAj2Aj5thUsNBTm9ljY6sDkEsYoPAClqRDE/out-3.png"
  ],
  "started_at": "2022-12-24T08:29:50.483005Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/dlsi3sfjprfdxaut3jncousauu",
    "cancel": "https://api.replicate.com/v1/predictions/dlsi3sfjprfdxaut3jncousauu/cancel"
  },
  "version": "8aac0c5751efacf1aeb556df676c875b3adaf09d48e7102ab52bbee775549c27"
}

Generated in

23.2 seconds

Tweak it Report View full prediction

Loading pipeline...
Using seed: 6298
Global seed set to 6298
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:02<02:08,  2.63s/it]
  4%|▍         | 2/50 [00:02<00:59,  1.25s/it]
  6%|▌         | 3/50 [00:03<00:37,  1.24it/s]
  8%|▊         | 4/50 [00:03<00:27,  1.67it/s]
 10%|█         | 5/50 [00:03<00:21,  2.07it/s]
 12%|█▏        | 6/50 [00:04<00:18,  2.41it/s]
 14%|█▍        | 7/50 [00:04<00:15,  2.70it/s]
 16%|█▌        | 8/50 [00:04<00:14,  2.92it/s]
 18%|█▊        | 9/50 [00:04<00:13,  3.10it/s]
 20%|██        | 10/50 [00:05<00:12,  3.23it/s]
 22%|██▏       | 11/50 [00:05<00:11,  3.33it/s]
 24%|██▍       | 12/50 [00:05<00:11,  3.40it/s]
 26%|██▌       | 13/50 [00:05<00:10,  3.45it/s]
 28%|██▊       | 14/50 [00:06<00:10,  3.48it/s]
 30%|███       | 15/50 [00:06<00:09,  3.51it/s]
 32%|███▏      | 16/50 [00:06<00:09,  3.53it/s]
 34%|███▍      | 17/50 [00:07<00:09,  3.54it/s]
 36%|███▌      | 18/50 [00:07<00:09,  3.55it/s]
 38%|███▊      | 19/50 [00:07<00:08,  3.56it/s]
 40%|████      | 20/50 [00:07<00:08,  3.56it/s]
 42%|████▏     | 21/50 [00:08<00:08,  3.56it/s]
 44%|████▍     | 22/50 [00:08<00:07,  3.56it/s]
 46%|████▌     | 23/50 [00:08<00:07,  3.56it/s]
 48%|████▊     | 24/50 [00:09<00:07,  3.56it/s]
 50%|█████     | 25/50 [00:09<00:07,  3.56it/s]
 52%|█████▏    | 26/50 [00:09<00:06,  3.56it/s]
 54%|█████▍    | 27/50 [00:09<00:06,  3.56it/s]
 56%|█████▌    | 28/50 [00:10<00:06,  3.56it/s]
 58%|█████▊    | 29/50 [00:10<00:05,  3.56it/s]
 60%|██████    | 30/50 [00:10<00:05,  3.56it/s]
 62%|██████▏   | 31/50 [00:11<00:05,  3.56it/s]
 64%|██████▍   | 32/50 [00:11<00:05,  3.57it/s]
 66%|██████▌   | 33/50 [00:11<00:04,  3.57it/s]
 68%|██████▊   | 34/50 [00:11<00:04,  3.57it/s]
 70%|███████   | 35/50 [00:12<00:04,  3.57it/s]
 72%|███████▏  | 36/50 [00:12<00:03,  3.57it/s]
 74%|███████▍  | 37/50 [00:12<00:03,  3.57it/s]
 76%|███████▌  | 38/50 [00:13<00:03,  3.57it/s]
 78%|███████▊  | 39/50 [00:13<00:03,  3.57it/s]
 80%|████████  | 40/50 [00:13<00:02,  3.57it/s]
 82%|████████▏ | 41/50 [00:13<00:02,  3.57it/s]
 84%|████████▍ | 42/50 [00:14<00:02,  3.57it/s]
 86%|████████▌ | 43/50 [00:14<00:01,  3.57it/s]
 88%|████████▊ | 44/50 [00:14<00:01,  3.57it/s]
 90%|█████████ | 45/50 [00:14<00:01,  3.57it/s]
 92%|█████████▏| 46/50 [00:15<00:01,  3.57it/s]
 94%|█████████▍| 47/50 [00:15<00:00,  3.57it/s]
 96%|█████████▌| 48/50 [00:15<00:00,  3.57it/s]
 98%|█████████▊| 49/50 [00:16<00:00,  3.57it/s]
100%|██████████| 50/50 [00:16<00:00,  3.57it/s]
100%|██████████| 50/50 [00:16<00:00,  3.05it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.025 to run on Replicate, or 40 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 19 seconds. The predict time for this model varies significantly based on the inputs.

Readme

…

Model description

…

Intended use

…

Ethical considerations

…

Caveats and recommendations

…