adirik/leditsplusplus:18916a95 – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

adirik /leditsplusplus:18916a95

Playground API

Input

image

*file

Input image to edit.

num_inversion_steps

integer

(minimum: 1, maximum: 200)

Number of image inversion steps.

Default: 50

source_prompt

string

Shift + Return to add a new line

Prompt describing the input image that will be used for guidance during inversion. Guidance is disabled if the `source_prompt` is ``.

Default: ""

source_guidance_scale

number

(minimum: 1, maximum: 25)

Strength of guidance during inversion.

Default: 3.5

skip

number

(minimum: 0, maximum: 1)

Portion of initial steps that will be ignored for inversion and subsequent generation. Lower values will lead to stronger changes to the input image.

Default: 0.15

negative_prompt

string

Shift + Return to add a new line

Negative prompt for the first text encoder to guide the image generation. *optional*, defaults to None.

negative_prompt2

string

Shift + Return to add a new line

Negative prompt for the second text encoder to guide the image generation. *optional*, defaults to None if *negative_prompt* is also left empty, alternatively defaults to *negative_prompt* otherwise.

editing_prompts

string

Shift + Return to add a new line

Comma separated objects to add, remove or edit. Defaults to None, which inverts and reconstructs the input image.

reverse_editing_directions

string

Shift + Return to add a new line

Comma separated True or False boolean values indicating whether the corresponding prompt in `editing_prompts` should be increased or decreased to add, remove or edit. *optional*, defaults to `False`

edit_guidance_scale

string

Shift + Return to add a new line

Comma separated float values for each change specified in editing prompts list. *optional*, defaults to 5 if left empty.

edit_warmup_steps

integer

(minimum: 0, maximum: 100)

Number of diffusion steps (for each prompt) for which guidance is not applied

Default: 0

edit_threshold

string

Shift + Return to add a new line

Comma separated edit threshold float values for each editing prompt, threshold values should be proportional to the image region that is modified. *optional*, defaults to 0.9 if left empty.

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

npx create-replicate --model=adirik/leditsplusplus

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

const output = await replicate.run(
  "adirik/leditsplusplus:18916a9500f503aa4aa92ec0b2dbf3cecfa1995ee2280b2033e80d50973af9f2",
  {
    input: {
      skip: 0.2,
      image: "https://replicate.delivery/pbxt/Kdrl0kuNYX3VCwJtdSfIoN8rzHBkcVuAhD9FLLzEI82ZywHT/tennis.jpg",
      source_prompt: "",
      edit_threshold: "0.9, 0.85",
      editing_prompts: "tennis ball, tomato",
      edit_warmup_steps: 0,
      edit_guidance_scale: "5.0, 10.0",
      num_inversion_steps: 50,
      source_guidance_scale: 3.5,
      reverse_editing_directions: "True, False"
    }
  }
);

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

output = replicate.run(
    "adirik/leditsplusplus:18916a9500f503aa4aa92ec0b2dbf3cecfa1995ee2280b2033e80d50973af9f2",
    input={
        "skip": 0.2,
        "image": "https://replicate.delivery/pbxt/Kdrl0kuNYX3VCwJtdSfIoN8rzHBkcVuAhD9FLLzEI82ZywHT/tennis.jpg",
        "source_prompt": "",
        "edit_threshold": "0.9, 0.85",
        "editing_prompts": "tennis ball, tomato",
        "edit_warmup_steps": 0,
        "edit_guidance_scale": "5.0, 10.0",
        "num_inversion_steps": 50,
        "source_guidance_scale": 3.5,
        "reverse_editing_directions": "True, False"
    }
)
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 adirik/leditsplusplus 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": "18916a9500f503aa4aa92ec0b2dbf3cecfa1995ee2280b2033e80d50973af9f2",
    "input": {
      "skip": 0.2,
      "image": "https://replicate.delivery/pbxt/Kdrl0kuNYX3VCwJtdSfIoN8rzHBkcVuAhD9FLLzEI82ZywHT/tennis.jpg",
      "source_prompt": "",
      "edit_threshold": "0.9, 0.85",
      "editing_prompts": "tennis ball, tomato",
      "edit_warmup_steps": 0,
      "edit_guidance_scale": "5.0, 10.0",
      "num_inversion_steps": 50,
      "source_guidance_scale": 3.5,
      "reverse_editing_directions": "True, False"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-03-27T09:47:28.583402Z",
  "created_at": "2024-03-27T09:46:08.567289Z",
  "data_removed": false,
  "error": null,
  "id": "hw6si63bv7m3amueh2qhvfcsou",
  "input": {
    "skip": 0.2,
    "image": "https://replicate.delivery/pbxt/Kdrl0kuNYX3VCwJtdSfIoN8rzHBkcVuAhD9FLLzEI82ZywHT/tennis.jpg",
    "source_prompt": "",
    "edit_threshold": "0.9, 0.85",
    "editing_prompts": "tennis ball, tomato",
    "edit_warmup_steps": 0,
    "edit_guidance_scale": "5.0, 10.0",
    "num_inversion_steps": 50,
    "source_guidance_scale": 3.5,
    "reverse_editing_directions": "True, False"
  },
  "logs": "Your input images far exceed the default resolution of the underlying diffusion model. The output images may contain severe artifacts! Consider down-sampling the input using the `height` and `width` parameters\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:08,  5.82it/s]\n  6%|▌         | 3/50 [00:00<00:04,  9.75it/s]\n 10%|█         | 5/50 [00:00<00:04, 10.71it/s]\n 14%|█▍        | 7/50 [00:00<00:03, 11.19it/s]\n 18%|█▊        | 9/50 [00:00<00:03, 11.51it/s]\n 22%|██▏       | 11/50 [00:00<00:03, 11.67it/s]\n 26%|██▌       | 13/50 [00:01<00:03, 11.75it/s]\n 30%|███       | 15/50 [00:01<00:02, 11.73it/s]\n 34%|███▍      | 17/50 [00:01<00:02, 11.86it/s]\n 38%|███▊      | 19/50 [00:01<00:02, 11.91it/s]\n 42%|████▏     | 21/50 [00:01<00:02, 11.90it/s]\n 46%|████▌     | 23/50 [00:02<00:02, 11.92it/s]\n 50%|█████     | 25/50 [00:02<00:02, 11.94it/s]\n 54%|█████▍    | 27/50 [00:02<00:01, 11.95it/s]\n 58%|█████▊    | 29/50 [00:02<00:01, 11.89it/s]\n 62%|██████▏   | 31/50 [00:02<00:01, 11.91it/s]\n 66%|██████▌   | 33/50 [00:02<00:01, 11.94it/s]\n 70%|███████   | 35/50 [00:03<00:01, 11.96it/s]\n 74%|███████▍  | 37/50 [00:03<00:01, 11.96it/s]\n 78%|███████▊  | 39/50 [00:03<00:00, 11.96it/s]\n 82%|████████▏ | 41/50 [00:03<00:00, 11.95it/s]\n 86%|████████▌ | 43/50 [00:03<00:00, 11.93it/s]\n 90%|█████████ | 45/50 [00:03<00:00, 11.92it/s]\n 94%|█████████▍| 47/50 [00:04<00:00, 11.95it/s]\n 98%|█████████▊| 49/50 [00:04<00:00, 11.96it/s]\n100%|██████████| 50/50 [00:04<00:00, 11.68it/s]\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:13,  3.65it/s]\n  4%|▍         | 2/50 [00:00<00:11,  4.24it/s]\n  6%|▌         | 3/50 [00:00<00:10,  4.47it/s]\n  8%|▊         | 4/50 [00:00<00:10,  4.58it/s]\n 10%|█         | 5/50 [00:01<00:09,  4.65it/s]\n 12%|█▏        | 6/50 [00:01<00:09,  4.69it/s]\n 14%|█▍        | 7/50 [00:01<00:09,  4.71it/s]\n 16%|█▌        | 8/50 [00:01<00:08,  4.73it/s]\n 18%|█▊        | 9/50 [00:01<00:08,  4.74it/s]\n 20%|██        | 10/50 [00:02<00:08,  4.74it/s]\n 22%|██▏       | 11/50 [00:02<00:08,  4.74it/s]\n 24%|██▍       | 12/50 [00:02<00:08,  4.75it/s]\n 26%|██▌       | 13/50 [00:02<00:07,  4.75it/s]\n 28%|██▊       | 14/50 [00:03<00:07,  4.75it/s]\n 30%|███       | 15/50 [00:03<00:07,  4.75it/s]\n 32%|███▏      | 16/50 [00:03<00:07,  4.75it/s]\n 34%|███▍      | 17/50 [00:03<00:06,  4.76it/s]\n 36%|███▌      | 18/50 [00:03<00:06,  4.76it/s]\n 38%|███▊      | 19/50 [00:04<00:06,  4.76it/s]\n 40%|████      | 20/50 [00:04<00:06,  4.76it/s]\n 42%|████▏     | 21/50 [00:04<00:06,  4.75it/s]\n 44%|████▍     | 22/50 [00:04<00:05,  4.76it/s]\n 46%|████▌     | 23/50 [00:04<00:05,  4.76it/s]\n 48%|████▊     | 24/50 [00:05<00:05,  4.76it/s]\n 50%|█████     | 25/50 [00:05<00:05,  4.75it/s]\n 52%|█████▏    | 26/50 [00:05<00:05,  4.75it/s]\n 54%|█████▍    | 27/50 [00:05<00:04,  4.75it/s]\n 56%|█████▌    | 28/50 [00:05<00:04,  4.75it/s]\n 58%|█████▊    | 29/50 [00:06<00:04,  4.75it/s]\n 60%|██████    | 30/50 [00:06<00:04,  4.75it/s]\n 62%|██████▏   | 31/50 [00:06<00:03,  4.75it/s]\n 64%|██████▍   | 32/50 [00:06<00:03,  4.75it/s]\n 66%|██████▌   | 33/50 [00:07<00:03,  4.75it/s]\n 68%|██████▊   | 34/50 [00:07<00:03,  4.75it/s]\n 70%|███████   | 35/50 [00:07<00:03,  4.69it/s]\n 72%|███████▏  | 36/50 [00:07<00:02,  4.71it/s]\n 74%|███████▍  | 37/50 [00:07<00:02,  4.72it/s]\n 76%|███████▌  | 38/50 [00:08<00:02,  4.73it/s]\n 78%|███████▊  | 39/50 [00:08<00:02,  4.73it/s]\n 80%|████████  | 40/50 [00:08<00:02,  4.74it/s]\n 82%|████████▏ | 41/50 [00:08<00:01,  4.74it/s]\n 84%|████████▍ | 42/50 [00:08<00:01,  4.71it/s]\n 86%|████████▌ | 43/50 [00:09<00:01,  4.72it/s]\n 88%|████████▊ | 44/50 [00:09<00:01,  4.72it/s]\n 90%|█████████ | 45/50 [00:09<00:01,  4.73it/s]\n 92%|█████████▏| 46/50 [00:09<00:00,  4.73it/s]\n 94%|█████████▍| 47/50 [00:09<00:00,  4.73it/s]\n 96%|█████████▌| 48/50 [00:10<00:00,  4.73it/s]\n 98%|█████████▊| 49/50 [00:10<00:00,  4.73it/s]\n100%|██████████| 50/50 [00:10<00:00,  4.73it/s]\n100%|██████████| 50/50 [00:10<00:00,  4.72it/s]",
  "metrics": {
    "predict_time": 19.052099,
    "total_time": 80.016113
  },
  "output": "https://replicate.delivery/pbxt/zwHbyMZQby5TDhyewKnOcIoVg6ZisivUxvJiL6DlMXrX6MSJA/output.png",
  "started_at": "2024-03-27T09:47:09.531303Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/hw6si63bv7m3amueh2qhvfcsou",
    "cancel": "https://api.replicate.com/v1/predictions/hw6si63bv7m3amueh2qhvfcsou/cancel"
  },
  "version": "18916a9500f503aa4aa92ec0b2dbf3cecfa1995ee2280b2033e80d50973af9f2"
}

Generated in

19.1 seconds

Tweak itReport

Your input images far exceed the default resolution of the underlying diffusion model. The output images may contain severe artifacts! Consider down-sampling the input using the `height` and `width` parameters
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:08,  5.82it/s]
  6%|▌         | 3/50 [00:00<00:04,  9.75it/s]
 10%|█         | 5/50 [00:00<00:04, 10.71it/s]
 14%|█▍        | 7/50 [00:00<00:03, 11.19it/s]
 18%|█▊        | 9/50 [00:00<00:03, 11.51it/s]
 22%|██▏       | 11/50 [00:00<00:03, 11.67it/s]
 26%|██▌       | 13/50 [00:01<00:03, 11.75it/s]
 30%|███       | 15/50 [00:01<00:02, 11.73it/s]
 34%|███▍      | 17/50 [00:01<00:02, 11.86it/s]
 38%|███▊      | 19/50 [00:01<00:02, 11.91it/s]
 42%|████▏     | 21/50 [00:01<00:02, 11.90it/s]
 46%|████▌     | 23/50 [00:02<00:02, 11.92it/s]
 50%|█████     | 25/50 [00:02<00:02, 11.94it/s]
 54%|█████▍    | 27/50 [00:02<00:01, 11.95it/s]
 58%|█████▊    | 29/50 [00:02<00:01, 11.89it/s]
 62%|██████▏   | 31/50 [00:02<00:01, 11.91it/s]
 66%|██████▌   | 33/50 [00:02<00:01, 11.94it/s]
 70%|███████   | 35/50 [00:03<00:01, 11.96it/s]
 74%|███████▍  | 37/50 [00:03<00:01, 11.96it/s]
 78%|███████▊  | 39/50 [00:03<00:00, 11.96it/s]
 82%|████████▏ | 41/50 [00:03<00:00, 11.95it/s]
 86%|████████▌ | 43/50 [00:03<00:00, 11.93it/s]
 90%|█████████ | 45/50 [00:03<00:00, 11.92it/s]
 94%|█████████▍| 47/50 [00:04<00:00, 11.95it/s]
 98%|█████████▊| 49/50 [00:04<00:00, 11.96it/s]
100%|██████████| 50/50 [00:04<00:00, 11.68it/s]
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:13,  3.65it/s]
  4%|▍         | 2/50 [00:00<00:11,  4.24it/s]
  6%|▌         | 3/50 [00:00<00:10,  4.47it/s]
  8%|▊         | 4/50 [00:00<00:10,  4.58it/s]
 10%|█         | 5/50 [00:01<00:09,  4.65it/s]
 12%|█▏        | 6/50 [00:01<00:09,  4.69it/s]
 14%|█▍        | 7/50 [00:01<00:09,  4.71it/s]
 16%|█▌        | 8/50 [00:01<00:08,  4.73it/s]
 18%|█▊        | 9/50 [00:01<00:08,  4.74it/s]
 20%|██        | 10/50 [00:02<00:08,  4.74it/s]
 22%|██▏       | 11/50 [00:02<00:08,  4.74it/s]
 24%|██▍       | 12/50 [00:02<00:08,  4.75it/s]
 26%|██▌       | 13/50 [00:02<00:07,  4.75it/s]
 28%|██▊       | 14/50 [00:03<00:07,  4.75it/s]
 30%|███       | 15/50 [00:03<00:07,  4.75it/s]
 32%|███▏      | 16/50 [00:03<00:07,  4.75it/s]
 34%|███▍      | 17/50 [00:03<00:06,  4.76it/s]
 36%|███▌      | 18/50 [00:03<00:06,  4.76it/s]
 38%|███▊      | 19/50 [00:04<00:06,  4.76it/s]
 40%|████      | 20/50 [00:04<00:06,  4.76it/s]
 42%|████▏     | 21/50 [00:04<00:06,  4.75it/s]
 44%|████▍     | 22/50 [00:04<00:05,  4.76it/s]
 46%|████▌     | 23/50 [00:04<00:05,  4.76it/s]
 48%|████▊     | 24/50 [00:05<00:05,  4.76it/s]
 50%|█████     | 25/50 [00:05<00:05,  4.75it/s]
 52%|█████▏    | 26/50 [00:05<00:05,  4.75it/s]
 54%|█████▍    | 27/50 [00:05<00:04,  4.75it/s]
 56%|█████▌    | 28/50 [00:05<00:04,  4.75it/s]
 58%|█████▊    | 29/50 [00:06<00:04,  4.75it/s]
 60%|██████    | 30/50 [00:06<00:04,  4.75it/s]
 62%|██████▏   | 31/50 [00:06<00:03,  4.75it/s]
 64%|██████▍   | 32/50 [00:06<00:03,  4.75it/s]
 66%|██████▌   | 33/50 [00:07<00:03,  4.75it/s]
 68%|██████▊   | 34/50 [00:07<00:03,  4.75it/s]
 70%|███████   | 35/50 [00:07<00:03,  4.69it/s]
 72%|███████▏  | 36/50 [00:07<00:02,  4.71it/s]
 74%|███████▍  | 37/50 [00:07<00:02,  4.72it/s]
 76%|███████▌  | 38/50 [00:08<00:02,  4.73it/s]
 78%|███████▊  | 39/50 [00:08<00:02,  4.73it/s]
 80%|████████  | 40/50 [00:08<00:02,  4.74it/s]
 82%|████████▏ | 41/50 [00:08<00:01,  4.74it/s]
 84%|████████▍ | 42/50 [00:08<00:01,  4.71it/s]
 86%|████████▌ | 43/50 [00:09<00:01,  4.72it/s]
 88%|████████▊ | 44/50 [00:09<00:01,  4.72it/s]
 90%|█████████ | 45/50 [00:09<00:01,  4.73it/s]
 92%|█████████▏| 46/50 [00:09<00:00,  4.73it/s]
 94%|█████████▍| 47/50 [00:09<00:00,  4.73it/s]
 96%|█████████▌| 48/50 [00:10<00:00,  4.73it/s]
 98%|█████████▊| 49/50 [00:10<00:00,  4.73it/s]
100%|██████████| 50/50 [00:10<00:00,  4.73it/s]
100%|██████████| 50/50 [00:10<00:00,  4.72it/s]