adirik/local-prompt-mixing | Run with an API on Replicate

adirik / local-prompt-mixing

Generating object-level shape variations with Stable Diffusion (Updated 1 year, 6 months ago)

Cold

Public
86 runs
L40S
GitHub
Paper

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

image

*file

Input image

prompt

*string

Shift + Return to add a new line

A simple description of the image

object_of_interest

*string

Shift + Return to add a new line

Object of interest which is desired to be modified

proxy_words

string

Shift + Return to add a new line

Your own proxy words, if you leave empty then auto-generated proxy words will be used

Default: ""

objects_to_preserve

string

Shift + Return to add a new line

Objects to preserve, please use comma separated values. If you leave empty then no objects will be preserved

Default: ""

number_of_variations

integer

(minimum: 1, maximum: 5)

Number of auto variations to generate

Default: 1

steps

integer

(minimum: 1, maximum: 100)

Number of denoising steps

Default: 50

start_prompt_range

integer

Nth step where prompt-mixing begins

Default: 7

end_prompt_range

integer

Nth step where prompt-mixing ends

Default: 17

guidance_scale

number

(minimum: 0, maximum: 20)

Guidance scale

Default: 7.5

seed

integer

(minimum: 0, maximum: 100)

Random seed

Default: 10

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

npx create-replicate --model=adirik/local-prompt-mixing

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

const output = await replicate.run(
  "adirik/local-prompt-mixing:1f22992c5bf09b7b228dd390a9bacdc6edb5f2fc1e1fe75a5a141db18be764e6",
  {
    input: {
      seed: 10,
      image: "https://replicate.delivery/pbxt/K2CCi8IiDes9u7OWn2tQsZTtjatbfXsEapZMwWISUrtTMaOo/real.jpg",
      steps: 50,
      prompt: "A vase with flowers on the table",
      proxy_words: "",
      guidance_scale: 7.5,
      end_prompt_range: 17,
      object_of_interest: "vase",
      start_prompt_range: 7,
      objects_to_preserve: "flowers",
      number_of_variations: 2
    }
  }
);

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

output = replicate.run(
    "adirik/local-prompt-mixing:1f22992c5bf09b7b228dd390a9bacdc6edb5f2fc1e1fe75a5a141db18be764e6",
    input={
        "seed": 10,
        "image": "https://replicate.delivery/pbxt/K2CCi8IiDes9u7OWn2tQsZTtjatbfXsEapZMwWISUrtTMaOo/real.jpg",
        "steps": 50,
        "prompt": "A vase with flowers on the table",
        "proxy_words": "",
        "guidance_scale": 7.5,
        "end_prompt_range": 17,
        "object_of_interest": "vase",
        "start_prompt_range": 7,
        "objects_to_preserve": "flowers",
        "number_of_variations": 2
    }
)
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/local-prompt-mixing 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": "adirik/local-prompt-mixing:1f22992c5bf09b7b228dd390a9bacdc6edb5f2fc1e1fe75a5a141db18be764e6",
    "input": {
      "seed": 10,
      "image": "https://replicate.delivery/pbxt/K2CCi8IiDes9u7OWn2tQsZTtjatbfXsEapZMwWISUrtTMaOo/real.jpg",
      "steps": 50,
      "prompt": "A vase with flowers on the table",
      "proxy_words": "",
      "guidance_scale": 7.5,
      "end_prompt_range": 17,
      "object_of_interest": "vase",
      "start_prompt_range": 7,
      "objects_to_preserve": "flowers",
      "number_of_variations": 2
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-12-12T06:46:42.089061Z",
  "created_at": "2023-12-12T06:43:44.461587Z",
  "data_removed": false,
  "error": null,
  "id": "56rfuylbpukbee4wmu5oi5j3ye",
  "input": {
    "seed": 10,
    "image": "https://replicate.delivery/pbxt/K2CCi8IiDes9u7OWn2tQsZTtjatbfXsEapZMwWISUrtTMaOo/real.jpg",
    "steps": 50,
    "prompt": "A vase with flowers on the table",
    "proxy_words": "",
    "guidance_scale": 7.5,
    "end_prompt_range": 17,
    "object_of_interest": "vase",
    "start_prompt_range": 7,
    "objects_to_preserve": "flowers",
    "number_of_variations": 2
  },
  "logs": "0%|          | 0/15 [00:00<?, ?it/s]\n  7%|▋         | 1/15 [00:00<00:01,  7.23it/s]\n 13%|█▎        | 2/15 [00:01<00:08,  1.62it/s]\n 20%|██        | 3/15 [00:02<00:09,  1.31it/s]\n 27%|██▋       | 4/15 [00:02<00:09,  1.20it/s]\n 33%|███▎      | 5/15 [00:03<00:08,  1.14it/s]\n 40%|████      | 6/15 [00:04<00:08,  1.11it/s]\n 47%|████▋     | 7/15 [00:05<00:07,  1.09it/s]\n 53%|█████▎    | 8/15 [00:06<00:06,  1.08it/s]\n 60%|██████    | 9/15 [00:07<00:05,  1.07it/s]\n 67%|██████▋   | 10/15 [00:08<00:04,  1.07it/s]\n 73%|███████▎  | 11/15 [00:09<00:03,  1.06it/s]\n 80%|████████  | 12/15 [00:10<00:02,  1.06it/s]\n 87%|████████▋ | 13/15 [00:11<00:01,  1.05it/s]\n 93%|█████████▎| 14/15 [00:12<00:00,  1.05it/s]\n100%|██████████| 15/15 [00:13<00:00,  1.05it/s]\n100%|██████████| 15/15 [00:13<00:00,  1.12it/s]\nprompt: a photo of a {word}\ninitial word: vase\nTOP 50 SIMILAR WORDS:\n['jar', 'pot', 'plant', 'cup', 'flower', 'bottle', 'bowl', 'lamp', 'glass', 'mug', 'rose', 'trophy', 'decor', 'candle', 'acup', 'bucket', 'something', 'water', 'drink', 'table', 'grass', 'pipe', 'one', 'bloom', 'gift', 'scent', 'bone', 'globe', 'bell', 'stone', 'abstract', 'clock', 'rock', 'drum', 'present', 'ÅŁ', 'ÄŁ', 'âł', 'Ãł', 'phone', 've', 'milk', 'vege', 'wine', 'landscape', 'head', 'can', 'garden', 'grave', 'ðŁ']\n  0%|          | 0/1 [00:00<?, ?it/s]\n100%|██████████| 1/1 [00:00<00:00, 62.06it/s]\nprompt: a {word} with flowers on the table\ninitial word: vase\nTOP 3 SIMILAR WORDS:\n['pot', 'jar', 'cup']\nThe config attributes {'scaling_factor': 0.18215} were passed to AutoencoderKL, but are not expected and will be ignored. Please verify your config.json configuration file.\n/root/.pyenv/versions/3.10.8/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py:101: FutureWarning: The configuration file of this scheduler: DDIMScheduler {\n\"_class_name\": \"DDIMScheduler\",\n\"_diffusers_version\": \"0.10.2\",\n\"beta_end\": 0.012,\n\"beta_schedule\": \"scaled_linear\",\n\"beta_start\": 0.00085,\n\"clip_sample\": false,\n\"num_train_timesteps\": 1000,\n\"prediction_type\": \"epsilon\",\n\"set_alpha_to_one\": false,\n\"steps_offset\": 0,\n\"trained_betas\": null\n}\nis outdated. `steps_offset` should be set to 1 instead of 0. Please make sure to update the config accordingly as leaving `steps_offset` might led to incorrect results in future versions. If you have downloaded this checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for the `scheduler/scheduler_config.json` file\ndeprecate(\"steps_offset!=1\", \"1.0.0\", deprecation_message, standard_warn=False)\nStart null text inversion\nDDIM inversion...\n  0%|          | 0/50 [00:00<?, ?it/s]\n  4%|▍         | 2/50 [00:00<00:02, 16.13it/s]\n  8%|▊         | 4/50 [00:00<00:03, 12.51it/s]\n 12%|█▏        | 6/50 [00:00<00:03, 11.72it/s]\n 16%|█▌        | 8/50 [00:00<00:03, 11.37it/s]\n 20%|██        | 10/50 [00:00<00:03, 11.14it/s]\n 24%|██▍       | 12/50 [00:01<00:03, 11.04it/s]\n 28%|██▊       | 14/50 [00:01<00:03, 10.97it/s]\n 32%|███▏      | 16/50 [00:01<00:03, 10.92it/s]\n 36%|███▌      | 18/50 [00:01<00:02, 10.88it/s]\n 40%|████      | 20/50 [00:01<00:02, 10.88it/s]\n 44%|████▍     | 22/50 [00:01<00:02, 10.88it/s]\n 48%|████▊     | 24/50 [00:02<00:02, 10.87it/s]\n 52%|█████▏    | 26/50 [00:02<00:02, 10.85it/s]\n 56%|█████▌    | 28/50 [00:02<00:02, 10.85it/s]\n 60%|██████    | 30/50 [00:02<00:01, 10.82it/s]\n 64%|██████▍   | 32/50 [00:02<00:01, 10.73it/s]\n 68%|██████▊   | 34/50 [00:03<00:01, 10.85it/s]\n 72%|███████▏  | 36/50 [00:03<00:01, 10.84it/s]\n 76%|███████▌  | 38/50 [00:03<00:01, 10.84it/s]\n 80%|████████  | 40/50 [00:03<00:00, 10.84it/s]\n 84%|████████▍ | 42/50 [00:03<00:00, 10.83it/s]\n 88%|████████▊ | 44/50 [00:04<00:00, 10.82it/s]\n 92%|█████████▏| 46/50 [00:04<00:00, 10.83it/s]\n 96%|█████████▌| 48/50 [00:04<00:00, 10.83it/s]\n100%|██████████| 50/50 [00:04<00:00, 10.83it/s]\n100%|██████████| 50/50 [00:04<00:00, 10.97it/s]\nNull-text optimization...\n  0%|          | 0/500 [00:00<?, ?it/s]\n  0%|          | 1/500 [00:00<03:22,  2.47it/s]\n  0%|          | 2/500 [00:00<02:40,  3.09it/s]\n  1%|          | 3/500 [00:00<02:27,  3.37it/s]\n  1%|          | 4/500 [00:01<02:21,  3.51it/s]\n  1%|          | 5/500 [00:01<02:17,  3.60it/s]\n  1%|          | 6/500 [00:01<02:15,  3.65it/s]\n  1%|▏         | 7/500 [00:02<02:13,  3.69it/s]\n  2%|▏         | 8/500 [00:02<02:12,  3.71it/s]\n  2%|▏         | 9/500 [00:02<02:11,  3.72it/s]\n  2%|▏         | 10/500 [00:02<02:11,  3.73it/s]\n  2%|▏         | 11/500 [00:03<02:46,  2.94it/s]\n  2%|▏         | 12/500 [00:03<02:35,  3.15it/s]\n  3%|▎         | 13/500 [00:03<02:27,  3.31it/s]\n  3%|▎         | 14/500 [00:04<02:21,  3.44it/s]\n  3%|▎         | 15/500 [00:04<02:17,  3.53it/s]\n  3%|▎         | 16/500 [00:04<02:14,  3.59it/s]\n  3%|▎         | 17/500 [00:04<02:12,  3.64it/s]\n  4%|▎         | 18/500 [00:05<02:11,  3.68it/s]\n  4%|▍         | 19/500 [00:05<02:09,  3.70it/s]\n  4%|▍         | 20/500 [00:05<02:09,  3.72it/s]\n  4%|▍         | 21/500 [00:06<02:42,  2.94it/s]\n  4%|▍         | 22/500 [00:06<02:31,  3.15it/s]\n  5%|▍         | 23/500 [00:06<02:24,  3.31it/s]\n  5%|▍         | 24/500 [00:07<02:18,  3.43it/s]\n  6%|▌         | 31/500 [00:07<00:59,  7.87it/s]\n  6%|▋         | 32/500 [00:07<01:08,  6.87it/s]\n  7%|▋         | 33/500 [00:08<01:16,  6.07it/s]\n  8%|▊         | 41/500 [00:08<00:45, 10.09it/s]\n  8%|▊         | 42/500 [00:08<00:53,  8.60it/s]\n 10%|█         | 51/500 [00:09<00:36, 12.20it/s]\n 12%|█▏        | 61/500 [00:09<00:29, 14.93it/s]\n 13%|█▎        | 63/500 [00:10<00:39, 11.01it/s]\n 14%|█▍        | 71/500 [00:10<00:34, 12.57it/s]\n 16%|█▌        | 80/500 [00:11<00:25, 16.71it/s]\n 16%|█▋        | 82/500 [00:11<00:40, 10.40it/s]\n 18%|█▊        | 91/500 [00:12<00:32, 12.59it/s]\n 20%|██        | 100/500 [00:12<00:24, 16.44it/s]\n 21%|██        | 103/500 [00:13<00:41,  9.64it/s]\n 22%|██▏       | 110/500 [00:13<00:31, 12.23it/s]\n 22%|██▏       | 112/500 [00:14<00:45,  8.45it/s]\n 24%|██▍       | 120/500 [00:15<00:31, 11.94it/s]\n 24%|██▍       | 122/500 [00:15<00:46,  8.19it/s]\n 26%|██▌       | 130/500 [00:16<00:31, 11.80it/s]\n 26%|██▋       | 132/500 [00:16<00:45,  8.06it/s]\n 28%|██▊       | 141/500 [00:17<00:33, 10.74it/s]\n 29%|██▊       | 143/500 [00:17<00:41,  8.70it/s]\n 30%|███       | 151/500 [00:18<00:32, 10.72it/s]\n 32%|███▏      | 161/500 [00:18<00:25, 13.34it/s]\n 33%|███▎      | 163/500 [00:19<00:32, 10.43it/s]\n 34%|███▍      | 170/500 [00:19<00:24, 13.24it/s]\n 34%|███▍      | 172/500 [00:20<00:37,  8.73it/s]\n 36%|███▌      | 180/500 [00:20<00:25, 12.41it/s]\n 36%|███▋      | 182/500 [00:21<00:38,  8.31it/s]\n 37%|███▋      | 184/500 [00:22<00:45,  6.99it/s]\n 38%|███▊      | 191/500 [00:22<00:34,  8.93it/s]\n 39%|███▊      | 193/500 [00:23<00:41,  7.38it/s]\n 40%|████      | 201/500 [00:23<00:30,  9.82it/s]\n 41%|████      | 203/500 [00:24<00:37,  7.98it/s]\n 41%|████      | 204/500 [00:24<00:40,  7.23it/s]\n 42%|████▏     | 211/500 [00:24<00:30,  9.38it/s]\n 42%|████▏     | 212/500 [00:25<00:34,  8.27it/s]\n 43%|████▎     | 213/500 [00:25<00:39,  7.28it/s]\n 43%|████▎     | 214/500 [00:25<00:44,  6.44it/s]\n 44%|████▍     | 221/500 [00:26<00:29,  9.35it/s]\n 44%|████▍     | 222/500 [00:26<00:34,  8.07it/s]\n 45%|████▍     | 223/500 [00:26<00:39,  7.01it/s]\n 45%|████▍     | 224/500 [00:26<00:44,  6.17it/s]\n 45%|████▌     | 225/500 [00:27<00:49,  5.51it/s]\n 46%|████▌     | 231/500 [00:27<00:32,  8.20it/s]\n 46%|████▋     | 232/500 [00:28<00:37,  7.12it/s]\n 47%|████▋     | 233/500 [00:28<00:42,  6.25it/s]\n 47%|████▋     | 234/500 [00:28<00:47,  5.58it/s]\n 47%|████▋     | 235/500 [00:28<00:52,  5.08it/s]\n 48%|████▊     | 241/500 [00:29<00:32,  7.98it/s]\n 48%|████▊     | 242/500 [00:29<00:37,  6.95it/s]\n 49%|████▊     | 243/500 [00:29<00:41,  6.12it/s]\n 49%|████▉     | 244/500 [00:30<00:46,  5.48it/s]\n 49%|████▉     | 245/500 [00:30<00:51,  5.00it/s]\n 49%|████▉     | 246/500 [00:30<00:54,  4.64it/s]\n 49%|████▉     | 247/500 [00:30<00:57,  4.38it/s]\n 50%|█████     | 251/500 [00:31<00:41,  5.94it/s]\n 50%|█████     | 252/500 [00:31<00:45,  5.39it/s]\n 51%|█████     | 253/500 [00:31<00:49,  4.96it/s]\n 51%|█████     | 254/500 [00:32<00:53,  4.63it/s]\n 51%|█████     | 255/500 [00:32<00:55,  4.38it/s]\n 51%|█████     | 256/500 [00:32<00:58,  4.20it/s]\n 52%|█████▏    | 261/500 [00:33<00:35,  6.68it/s]\n 52%|█████▏    | 262/500 [00:33<00:39,  5.96it/s]\n 53%|█████▎    | 263/500 [00:33<00:44,  5.38it/s]\n 53%|█████▎    | 264/500 [00:34<00:47,  4.94it/s]\n 53%|█████▎    | 265/500 [00:34<00:51,  4.60it/s]\n 54%|█████▍    | 271/500 [00:34<00:29,  7.73it/s]\n 54%|█████▍    | 272/500 [00:35<00:33,  6.75it/s]\n 55%|█████▍    | 273/500 [00:35<00:38,  5.97it/s]\n 55%|█████▍    | 274/500 [00:35<00:42,  5.37it/s]\n 55%|█████▌    | 275/500 [00:35<00:45,  4.91it/s]\n 55%|█████▌    | 276/500 [00:36<00:48,  4.58it/s]\n 55%|█████▌    | 277/500 [00:36<00:51,  4.34it/s]\n 56%|█████▌    | 281/500 [00:36<00:37,  5.91it/s]\n 56%|█████▋    | 282/500 [00:37<00:40,  5.37it/s]\n 57%|█████▋    | 283/500 [00:37<00:43,  4.95it/s]\n 57%|█████▋    | 284/500 [00:37<00:46,  4.62it/s]\n 57%|█████▋    | 285/500 [00:38<00:49,  4.38it/s]\n 58%|█████▊    | 291/500 [00:38<00:27,  7.61it/s]\n 58%|█████▊    | 292/500 [00:38<00:31,  6.66it/s]\n 59%|█████▊    | 293/500 [00:39<00:35,  5.90it/s]\n 59%|█████▉    | 294/500 [00:39<00:38,  5.32it/s]\n 59%|█████▉    | 295/500 [00:39<00:42,  4.88it/s]\n 59%|█████▉    | 296/500 [00:39<00:44,  4.56it/s]\n 60%|██████    | 301/500 [00:40<00:28,  6.87it/s]\n 60%|██████    | 302/500 [00:40<00:32,  6.10it/s]\n 61%|██████    | 303/500 [00:40<00:35,  5.48it/s]\n 61%|██████    | 304/500 [00:41<00:39,  5.01it/s]\n 61%|██████    | 305/500 [00:41<00:41,  4.66it/s]\n 61%|██████    | 306/500 [00:41<00:44,  4.40it/s]\n 62%|██████▏   | 311/500 [00:42<00:27,  6.79it/s]\n 62%|██████▏   | 312/500 [00:42<00:31,  6.03it/s]\n 63%|██████▎   | 313/500 [00:42<00:34,  5.43it/s]\n 63%|██████▎   | 314/500 [00:42<00:37,  4.98it/s]\n 63%|██████▎   | 315/500 [00:43<00:39,  4.63it/s]\n 64%|██████▍   | 321/500 [00:43<00:23,  7.75it/s]\n 64%|██████▍   | 322/500 [00:44<00:26,  6.77it/s]\n 65%|██████▍   | 323/500 [00:44<00:29,  5.98it/s]\n 65%|██████▍   | 324/500 [00:44<00:32,  5.38it/s]\n 65%|██████▌   | 325/500 [00:44<00:35,  4.92it/s]\n 65%|██████▌   | 326/500 [00:45<00:37,  4.59it/s]\n 65%|██████▌   | 327/500 [00:45<00:39,  4.35it/s]\n 66%|██████▌   | 331/500 [00:45<00:28,  5.91it/s]\n 66%|██████▋   | 332/500 [00:46<00:31,  5.37it/s]\n 67%|██████▋   | 333/500 [00:46<00:33,  4.95it/s]\n 67%|██████▋   | 334/500 [00:46<00:35,  4.62it/s]\n 67%|██████▋   | 335/500 [00:46<00:37,  4.38it/s]\n 67%|██████▋   | 336/500 [00:47<00:39,  4.19it/s]\n 67%|██████▋   | 337/500 [00:47<00:40,  4.06it/s]\n 68%|██████▊   | 341/500 [00:47<00:27,  5.75it/s]\n 68%|██████▊   | 342/500 [00:48<00:30,  5.25it/s]\n 69%|██████▊   | 343/500 [00:48<00:32,  4.86it/s]\n 69%|██████▉   | 344/500 [00:48<00:34,  4.55it/s]\n 69%|██████▉   | 345/500 [00:49<00:35,  4.32it/s]\n 69%|██████▉   | 346/500 [00:49<00:37,  4.16it/s]\n 69%|██████▉   | 347/500 [00:49<00:37,  4.04it/s]\n 70%|███████   | 351/500 [00:50<00:25,  5.73it/s]\n 70%|███████   | 352/500 [00:50<00:28,  5.24it/s]\n 71%|███████   | 353/500 [00:50<00:30,  4.85it/s]\n 71%|███████   | 354/500 [00:50<00:32,  4.55it/s]\n 71%|███████   | 355/500 [00:51<00:33,  4.32it/s]\n 71%|███████   | 356/500 [00:51<00:34,  4.16it/s]\n 72%|███████▏  | 361/500 [00:51<00:20,  6.65it/s]\n 72%|███████▏  | 362/500 [00:52<00:23,  5.94it/s]\n 73%|███████▎  | 363/500 [00:52<00:25,  5.36it/s]\n 73%|███████▎  | 364/500 [00:52<00:27,  4.92it/s]\n 73%|███████▎  | 365/500 [00:52<00:29,  4.59it/s]\n 73%|███████▎  | 366/500 [00:53<00:30,  4.35it/s]\n 73%|███████▎  | 367/500 [00:53<00:31,  4.17it/s]\n 74%|███████▎  | 368/500 [00:53<00:32,  4.05it/s]\n 74%|███████▍  | 371/500 [00:54<00:26,  4.87it/s]\n 74%|███████▍  | 372/500 [00:54<00:27,  4.59it/s]\n 75%|███████▍  | 373/500 [00:54<00:29,  4.37it/s]\n 75%|███████▍  | 374/500 [00:55<00:30,  4.19it/s]\n 75%|███████▌  | 375/500 [00:55<00:30,  4.07it/s]\n 75%|███████▌  | 376/500 [00:55<00:31,  3.98it/s]\n 76%|███████▌  | 381/500 [00:56<00:18,  6.55it/s]\n 76%|███████▋  | 382/500 [00:56<00:20,  5.85it/s]\n 77%|███████▋  | 383/500 [00:56<00:22,  5.30it/s]\n 77%|███████▋  | 384/500 [00:56<00:23,  4.88it/s]\n 77%|███████▋  | 385/500 [00:57<00:25,  4.56it/s]\n 77%|███████▋  | 386/500 [00:57<00:26,  4.33it/s]\n 78%|███████▊  | 391/500 [00:57<00:16,  6.74it/s]\n 78%|███████▊  | 392/500 [00:58<00:17,  6.00it/s]\n 79%|███████▊  | 393/500 [00:58<00:19,  5.41it/s]\n 79%|███████▉  | 394/500 [00:58<00:21,  4.96it/s]\n 79%|███████▉  | 395/500 [00:59<00:22,  4.62it/s]\n 79%|███████▉  | 396/500 [00:59<00:23,  4.37it/s]\n 79%|███████▉  | 397/500 [00:59<00:24,  4.18it/s]\n 80%|████████  | 401/500 [01:00<00:17,  5.82it/s]\n 80%|████████  | 402/500 [01:00<00:18,  5.30it/s]\n 81%|████████  | 403/500 [01:00<00:19,  4.89it/s]\n 81%|████████  | 404/500 [01:00<00:20,  4.58it/s]\n 81%|████████  | 405/500 [01:01<00:21,  4.34it/s]\n 81%|████████  | 406/500 [01:01<00:22,  4.17it/s]\n 81%|████████▏ | 407/500 [01:01<00:22,  4.05it/s]\n 82%|████████▏ | 408/500 [01:01<00:23,  3.96it/s]\n 82%|████████▏ | 411/500 [01:02<00:18,  4.83it/s]\n 82%|████████▏ | 412/500 [01:02<00:19,  4.56it/s]\n 83%|████████▎ | 413/500 [01:03<00:20,  4.34it/s]\n 83%|████████▎ | 414/500 [01:03<00:20,  4.18it/s]\n 83%|████████▎ | 415/500 [01:03<00:20,  4.05it/s]\n 83%|████████▎ | 416/500 [01:03<00:21,  3.97it/s]\n 83%|████████▎ | 417/500 [01:04<00:21,  3.90it/s]\n 84%|████████▎ | 418/500 [01:04<00:21,  3.85it/s]\n 84%|████████▍ | 419/500 [01:04<00:21,  3.82it/s]\n 84%|████████▍ | 420/500 [01:04<00:21,  3.80it/s]\n 84%|████████▍ | 421/500 [01:05<00:26,  2.99it/s]\n 84%|████████▍ | 422/500 [01:05<00:24,  3.18it/s]\n 85%|████████▍ | 423/500 [01:05<00:23,  3.32it/s]\n 85%|████████▍ | 424/500 [01:06<00:22,  3.44it/s]\n 85%|████████▌ | 425/500 [01:06<00:21,  3.52it/s]\n 85%|████████▌ | 426/500 [01:06<00:20,  3.58it/s]\n 85%|████████▌ | 427/500 [01:06<00:20,  3.63it/s]\n 86%|████████▌ | 428/500 [01:07<00:19,  3.66it/s]\n 86%|████████▌ | 429/500 [01:07<00:19,  3.68it/s]\n 86%|████████▌ | 430/500 [01:07<00:18,  3.70it/s]\n 86%|████████▌ | 431/500 [01:08<00:23,  2.90it/s]\n 86%|████████▋ | 432/500 [01:08<00:21,  3.10it/s]\n 87%|████████▋ | 433/500 [01:08<00:20,  3.27it/s]\n 87%|████████▋ | 434/500 [01:09<00:19,  3.40it/s]\n 87%|████████▋ | 435/500 [01:09<00:18,  3.49it/s]\n 87%|████████▋ | 436/500 [01:09<00:17,  3.56it/s]\n 87%|████████▋ | 437/500 [01:09<00:17,  3.61it/s]\n 88%|████████▊ | 438/500 [01:10<00:16,  3.65it/s]\n 88%|████████▊ | 439/500 [01:10<00:16,  3.68it/s]\n 88%|████████▊ | 440/500 [01:10<00:16,  3.69it/s]\n 88%|████████▊ | 441/500 [01:11<00:20,  2.93it/s]\n 88%|████████▊ | 442/500 [01:11<00:18,  3.13it/s]\n 89%|████████▊ | 443/500 [01:11<00:17,  3.29it/s]\n 89%|████████▉ | 444/500 [01:12<00:16,  3.41it/s]\n 89%|████████▉ | 445/500 [01:12<00:15,  3.50it/s]\n 89%|████████▉ | 446/500 [01:12<00:15,  3.57it/s]\n 89%|████████▉ | 447/500 [01:12<00:14,  3.62it/s]\n 90%|████████▉ | 448/500 [01:13<00:14,  3.66it/s]\n 90%|████████▉ | 449/500 [01:13<00:13,  3.68it/s]\n 90%|█████████ | 450/500 [01:13<00:13,  3.70it/s]\n 90%|█████████ | 451/500 [01:14<00:16,  2.93it/s]\n 90%|█████████ | 452/500 [01:14<00:15,  3.13it/s]\n 91%|█████████ | 453/500 [01:14<00:14,  3.29it/s]\n 91%|█████████ | 454/500 [01:14<00:13,  3.42it/s]\n 91%|█████████ | 455/500 [01:15<00:12,  3.51it/s]\n 91%|█████████ | 456/500 [01:15<00:12,  3.58it/s]\n 91%|█████████▏| 457/500 [01:15<00:11,  3.63it/s]\n 92%|█████████▏| 458/500 [01:16<00:11,  3.66it/s]\n 92%|█████████▏| 459/500 [01:16<00:11,  3.69it/s]\n 92%|█████████▏| 460/500 [01:16<00:10,  3.70it/s]\n 92%|█████████▏| 461/500 [01:17<00:13,  2.93it/s]\n 92%|█████████▏| 462/500 [01:17<00:12,  3.13it/s]\n 93%|█████████▎| 463/500 [01:17<00:11,  3.29it/s]\n 93%|█████████▎| 464/500 [01:17<00:10,  3.42it/s]\n 93%|█████████▎| 465/500 [01:18<00:09,  3.51it/s]\n 93%|█████████▎| 466/500 [01:18<00:09,  3.57it/s]\n 93%|█████████▎| 467/500 [01:18<00:09,  3.62it/s]\n 94%|█████████▎| 468/500 [01:18<00:08,  3.66it/s]\n 94%|█████████▍| 469/500 [01:19<00:08,  3.68it/s]\n 94%|█████████▍| 470/500 [01:19<00:08,  3.70it/s]\n 94%|█████████▍| 471/500 [01:19<00:09,  2.93it/s]\n 94%|█████████▍| 472/500 [01:20<00:08,  3.13it/s]\n 95%|█████████▍| 473/500 [01:20<00:08,  3.29it/s]\n 95%|█████████▍| 474/500 [01:20<00:07,  3.42it/s]\n 95%|█████████▌| 475/500 [01:21<00:07,  3.51it/s]\n 95%|█████████▌| 476/500 [01:21<00:06,  3.57it/s]\n 95%|█████████▌| 477/500 [01:21<00:06,  3.62it/s]\n 96%|█████████▌| 478/500 [01:21<00:06,  3.66it/s]\n 96%|█████████▌| 479/500 [01:22<00:05,  3.68it/s]\n 96%|█████████▌| 480/500 [01:22<00:05,  3.69it/s]\n 96%|█████████▌| 481/500 [01:22<00:06,  2.93it/s]\n 96%|█████████▋| 482/500 [01:23<00:05,  3.13it/s]\n 97%|█████████▋| 483/500 [01:23<00:05,  3.29it/s]\n 97%|█████████▋| 484/500 [01:23<00:04,  3.41it/s]\n 97%|█████████▋| 485/500 [01:23<00:04,  3.50it/s]\n 97%|█████████▋| 486/500 [01:24<00:03,  3.57it/s]\n 97%|█████████▋| 487/500 [01:24<00:03,  3.62it/s]\n 98%|█████████▊| 488/500 [01:24<00:03,  3.65it/s]\n 98%|█████████▊| 489/500 [01:25<00:02,  3.68it/s]\n 98%|█████████▊| 490/500 [01:25<00:02,  3.70it/s]\n 98%|█████████▊| 491/500 [01:25<00:03,  2.93it/s]\n 98%|█████████▊| 492/500 [01:26<00:02,  3.13it/s]\n 99%|█████████▊| 493/500 [01:26<00:02,  3.29it/s]\n 99%|█████████▉| 494/500 [01:26<00:01,  3.41it/s]\n 99%|█████████▉| 495/500 [01:26<00:01,  3.51it/s]\n 99%|█████████▉| 496/500 [01:27<00:01,  3.57it/s]\n 99%|█████████▉| 497/500 [01:27<00:00,  3.62it/s]\n100%|█████████▉| 498/500 [01:27<00:00,  3.65it/s]\n100%|█████████▉| 499/500 [01:27<00:00,  3.68it/s]\n100%|██████████| 500/500 [01:28<00:00,  3.70it/s]\n100%|██████████| 500/500 [01:28<00:00,  5.67it/s]\nEnd null text inversion\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:06,  7.48it/s]\n  4%|▍         | 2/50 [00:00<00:08,  5.71it/s]\n  6%|▌         | 3/50 [00:00<00:08,  5.31it/s]\n  8%|▊         | 4/50 [00:00<00:08,  5.15it/s]\n 10%|█         | 5/50 [00:00<00:08,  5.05it/s]\n 12%|█▏        | 6/50 [00:01<00:08,  5.00it/s]\n 14%|█▍        | 7/50 [00:01<00:08,  4.97it/s]\n 16%|█▌        | 8/50 [00:01<00:08,  4.95it/s]\n 18%|█▊        | 9/50 [00:01<00:08,  4.94it/s]\n 20%|██        | 10/50 [00:01<00:08,  4.87it/s]\n 22%|██▏       | 11/50 [00:02<00:07,  4.94it/s]\n 24%|██▍       | 12/50 [00:02<00:07,  4.93it/s]\n 26%|██▌       | 13/50 [00:02<00:07,  4.90it/s]\n 28%|██▊       | 14/50 [00:02<00:07,  4.91it/s]\n 30%|███       | 15/50 [00:02<00:07,  4.90it/s]\n 32%|███▏      | 16/50 [00:03<00:06,  4.93it/s]\n 34%|███▍      | 17/50 [00:03<00:06,  4.92it/s]\n 36%|███▌      | 18/50 [00:03<00:06,  4.91it/s]\n 38%|███▊      | 19/50 [00:03<00:06,  4.91it/s]\n 40%|████      | 20/50 [00:04<00:06,  4.90it/s]\n 42%|████▏     | 21/50 [00:04<00:05,  4.90it/s]\n 44%|████▍     | 22/50 [00:04<00:05,  4.90it/s]\n 46%|████▌     | 23/50 [00:04<00:05,  4.90it/s]\n 48%|████▊     | 24/50 [00:04<00:05,  4.90it/s]\n 50%|█████     | 25/50 [00:05<00:05,  4.89it/s]\n 52%|█████▏    | 26/50 [00:05<00:04,  4.89it/s]\n 54%|█████▍    | 27/50 [00:05<00:04,  4.91it/s]\n 56%|█████▌    | 28/50 [00:05<00:04,  4.91it/s]\n 58%|█████▊    | 29/50 [00:05<00:04,  4.91it/s]\n 60%|██████    | 30/50 [00:06<00:04,  4.90it/s]\n 62%|██████▏   | 31/50 [00:06<00:03,  4.90it/s]\n 64%|██████▍   | 32/50 [00:06<00:03,  4.91it/s]\n 66%|██████▌   | 33/50 [00:06<00:03,  4.91it/s]\n 68%|██████▊   | 34/50 [00:06<00:03,  4.90it/s]\n 70%|███████   | 35/50 [00:07<00:03,  4.90it/s]\n 72%|███████▏  | 36/50 [00:07<00:02,  4.91it/s]\n 74%|███████▍  | 37/50 [00:07<00:02,  4.90it/s]\n 76%|███████▌  | 38/50 [00:07<00:02,  4.91it/s]\n 78%|███████▊  | 39/50 [00:07<00:02,  4.91it/s]\n 80%|████████  | 40/50 [00:08<00:02,  4.89it/s]\n 82%|████████▏ | 41/50 [00:08<00:01,  4.90it/s]\n 84%|████████▍ | 42/50 [00:08<00:01,  4.90it/s]\n 86%|████████▌ | 43/50 [00:08<00:01,  4.91it/s]\n 88%|████████▊ | 44/50 [00:08<00:01,  4.91it/s]\n 90%|█████████ | 45/50 [00:09<00:01,  4.91it/s]\n 92%|█████████▏| 46/50 [00:09<00:00,  4.91it/s]\n 94%|█████████▍| 47/50 [00:09<00:00,  4.91it/s]\n 96%|█████████▌| 48/50 [00:09<00:00,  4.91it/s]\n 98%|█████████▊| 49/50 [00:09<00:00,  4.90it/s]\n100%|██████████| 50/50 [00:10<00:00,  4.91it/s]\n100%|██████████| 50/50 [00:10<00:00,  4.94it/s]\nDo self attn other obj masking\n  0%|          | 0/3 [00:00<?, ?it/s]\n  0%|          | 0/50 [00:00<?, ?it/s]\u001b[A\n  2%|▏         | 1/50 [00:00<00:13,  3.57it/s]\u001b[A\n  4%|▍         | 2/50 [00:00<00:14,  3.21it/s]\u001b[A\n  6%|▌         | 3/50 [00:00<00:15,  3.10it/s]\u001b[A\n  8%|▊         | 4/50 [00:01<00:15,  3.05it/s]\u001b[A\n 10%|█         | 5/50 [00:01<00:14,  3.03it/s]\u001b[A\n 12%|█▏        | 6/50 [00:01<00:14,  3.01it/s]\u001b[A\n 14%|█▍        | 7/50 [00:02<00:14,  3.00it/s]\u001b[A\n 16%|█▌        | 8/50 [00:02<00:14,  2.99it/s]\u001b[A\n 18%|█▊        | 9/50 [00:02<00:13,  2.99it/s]\u001b[A\n 20%|██        | 10/50 [00:03<00:13,  2.99it/s]\u001b[A\n 22%|██▏       | 11/50 [00:03<00:13,  2.99it/s]\u001b[A\n 24%|██▍       | 12/50 [00:03<00:12,  2.99it/s]\u001b[A\n 26%|██▌       | 13/50 [00:04<00:12,  2.98it/s]\u001b[A\n 28%|██▊       | 14/50 [00:04<00:12,  2.98it/s]\u001b[A\n 30%|███       | 15/50 [00:04<00:11,  2.98it/s]\u001b[A\n 32%|███▏      | 16/50 [00:05<00:11,  2.98it/s]\u001b[A\n 34%|███▍      | 17/50 [00:05<00:11,  2.98it/s]\u001b[A\n 36%|███▌      | 18/50 [00:05<00:10,  2.98it/s]\u001b[A\n 38%|███▊      | 19/50 [00:06<00:10,  2.98it/s]\u001b[A\n 40%|████      | 20/50 [00:06<00:10,  2.98it/s]\u001b[A\n 42%|████▏     | 21/50 [00:06<00:09,  2.98it/s]\u001b[A\n 44%|████▍     | 22/50 [00:07<00:09,  2.98it/s]\u001b[A\n 46%|████▌     | 23/50 [00:07<00:09,  2.98it/s]\u001b[A\n 48%|████▊     | 24/50 [00:07<00:08,  2.98it/s]\u001b[A\n 50%|█████     | 25/50 [00:08<00:08,  2.98it/s]\u001b[A\n 52%|█████▏    | 26/50 [00:08<00:08,  2.98it/s]\u001b[A\n 54%|█████▍    | 27/50 [00:09<00:07,  2.98it/s]\u001b[A\n 56%|█████▌    | 28/50 [00:09<00:07,  2.98it/s]\u001b[A\n 58%|█████▊    | 29/50 [00:09<00:07,  2.98it/s]\u001b[A\n 60%|██████    | 30/50 [00:10<00:06,  2.97it/s]\u001b[A\n 62%|██████▏   | 31/50 [00:10<00:06,  2.97it/s]\u001b[A\n 64%|██████▍   | 32/50 [00:10<00:06,  2.97it/s]\u001b[A\n 66%|██████▌   | 33/50 [00:11<00:05,  2.98it/s]\u001b[A\n 68%|██████▊   | 34/50 [00:11<00:05,  2.97it/s]\u001b[A\n 70%|███████   | 35/50 [00:11<00:05,  2.98it/s]\u001b[A\n 72%|███████▏  | 36/50 [00:13<00:10,  1.38it/s]\u001b[A\n 74%|███████▍  | 37/50 [00:13<00:07,  1.69it/s]\u001b[A\n 76%|███████▌  | 38/50 [00:13<00:06,  1.95it/s]\u001b[A\n 78%|███████▊  | 39/50 [00:14<00:05,  2.18it/s]\u001b[A\n 80%|████████  | 40/50 [00:14<00:04,  2.37it/s]\u001b[A\n 82%|████████▏ | 41/50 [00:14<00:03,  2.67it/s]\u001b[A\n 84%|████████▍ | 42/50 [00:15<00:02,  2.78it/s]\u001b[A\n 86%|████████▌ | 43/50 [00:15<00:02,  2.86it/s]\u001b[A\n 88%|████████▊ | 44/50 [00:15<00:02,  2.92it/s]\u001b[A\n 90%|█████████ | 45/50 [00:16<00:01,  2.96it/s]\u001b[A\n 92%|█████████▏| 46/50 [00:16<00:01,  2.99it/s]\u001b[A\n 94%|█████████▍| 47/50 [00:16<00:00,  3.01it/s]\u001b[A\n 96%|█████████▌| 48/50 [00:17<00:00,  3.03it/s]\u001b[A\n 98%|█████████▊| 49/50 [00:17<00:00,  3.04it/s]\u001b[A\n100%|██████████| 50/50 [00:17<00:00,  3.05it/s]\u001b[A\n100%|██████████| 50/50 [00:17<00:00,  2.81it/s]\n 33%|███▎      | 1/3 [00:18<00:36, 18.18s/it]\n  0%|          | 0/50 [00:00<?, ?it/s]\u001b[A\n  2%|▏         | 1/50 [00:00<00:13,  3.56it/s]\u001b[A\n  4%|▍         | 2/50 [00:00<00:14,  3.20it/s]\u001b[A\n  6%|▌         | 3/50 [00:00<00:15,  3.11it/s]\u001b[A\n  8%|▊         | 4/50 [00:01<00:15,  3.05it/s]\u001b[A\n 10%|█         | 5/50 [00:01<00:14,  3.03it/s]\u001b[A\n 12%|█▏        | 6/50 [00:01<00:14,  3.01it/s]\u001b[A\n 14%|█▍        | 7/50 [00:02<00:14,  3.01it/s]\u001b[A\n 16%|█▌        | 8/50 [00:02<00:13,  3.00it/s]\u001b[A\n 18%|█▊        | 9/50 [00:02<00:13,  2.99it/s]\u001b[A\n 20%|██        | 10/50 [00:03<00:13,  2.99it/s]\u001b[A\n 22%|██▏       | 11/50 [00:03<00:13,  2.98it/s]\u001b[A\n 24%|██▍       | 12/50 [00:03<00:12,  2.98it/s]\u001b[A\n 26%|██▌       | 13/50 [00:04<00:12,  2.98it/s]\u001b[A\n 28%|██▊       | 14/50 [00:04<00:12,  2.98it/s]\u001b[A\n 30%|███       | 15/50 [00:04<00:11,  2.98it/s]\u001b[A\n 32%|███▏      | 16/50 [00:05<00:11,  2.98it/s]\u001b[A\n 34%|███▍      | 17/50 [00:05<00:11,  2.98it/s]\u001b[A\n 36%|███▌      | 18/50 [00:05<00:10,  2.98it/s]\u001b[A\n 38%|███▊      | 19/50 [00:06<00:10,  2.98it/s]\u001b[A\n 40%|████      | 20/50 [00:06<00:10,  2.98it/s]\u001b[A\n 42%|████▏     | 21/50 [00:06<00:09,  2.98it/s]\u001b[A\n 44%|████▍     | 22/50 [00:07<00:09,  2.98it/s]\u001b[A\n 46%|████▌     | 23/50 [00:07<00:09,  2.98it/s]\u001b[A\n 48%|████▊     | 24/50 [00:07<00:08,  2.98it/s]\u001b[A\n 50%|█████     | 25/50 [00:08<00:08,  2.98it/s]\u001b[A\n 52%|█████▏    | 26/50 [00:08<00:08,  2.98it/s]\u001b[A\n 54%|█████▍    | 27/50 [00:09<00:07,  2.98it/s]\u001b[A\n 56%|█████▌    | 28/50 [00:09<00:07,  2.98it/s]\u001b[A\n 58%|█████▊    | 29/50 [00:09<00:07,  2.98it/s]\u001b[A\n 60%|██████    | 30/50 [00:10<00:06,  2.98it/s]\u001b[A\n 62%|██████▏   | 31/50 [00:10<00:06,  2.98it/s]\u001b[A\n 64%|██████▍   | 32/50 [00:10<00:06,  2.98it/s]\u001b[A\n 66%|██████▌   | 33/50 [00:11<00:05,  2.98it/s]\u001b[A\n 68%|██████▊   | 34/50 [00:11<00:05,  2.98it/s]\u001b[A\n 70%|███████   | 35/50 [00:11<00:05,  2.98it/s]\u001b[A\n 72%|███████▏  | 36/50 [00:13<00:10,  1.36it/s]\u001b[A\n 74%|███████▍  | 37/50 [00:13<00:07,  1.67it/s]\u001b[A\n 76%|███████▌  | 38/50 [00:13<00:06,  1.93it/s]\u001b[A\n 78%|███████▊  | 39/50 [00:14<00:05,  2.16it/s]\u001b[A\n 80%|████████  | 40/50 [00:14<00:04,  2.35it/s]\u001b[A\n 82%|████████▏ | 41/50 [00:14<00:03,  2.65it/s]\u001b[A\n 84%|████████▍ | 42/50 [00:15<00:02,  2.76it/s]\u001b[A\n 86%|████████▌ | 43/50 [00:15<00:02,  2.85it/s]\u001b[A\n 88%|████████▊ | 44/50 [00:15<00:02,  2.91it/s]\u001b[A\n 90%|█████████ | 45/50 [00:16<00:01,  2.95it/s]\u001b[A\n 92%|█████████▏| 46/50 [00:16<00:01,  2.98it/s]\u001b[A\n 94%|█████████▍| 47/50 [00:16<00:00,  3.01it/s]\u001b[A\n 96%|█████████▌| 48/50 [00:17<00:00,  3.02it/s]\u001b[A\n 98%|█████████▊| 49/50 [00:17<00:00,  3.03it/s]\u001b[A\n100%|██████████| 50/50 [00:17<00:00,  3.04it/s]\u001b[A\n100%|██████████| 50/50 [00:17<00:00,  2.80it/s]\n 67%|██████▋   | 2/3 [00:36<00:18, 18.20s/it]\n  0%|          | 0/50 [00:00<?, ?it/s]\u001b[A\n  2%|▏         | 1/50 [00:00<00:13,  3.56it/s]\u001b[A\n  4%|▍         | 2/50 [00:00<00:14,  3.20it/s]\u001b[A\n  6%|▌         | 3/50 [00:00<00:15,  3.09it/s]\u001b[A\n  8%|▊         | 4/50 [00:01<00:15,  3.05it/s]\u001b[A\n 10%|█         | 5/50 [00:01<00:14,  3.02it/s]\u001b[A\n 12%|█▏        | 6/50 [00:01<00:14,  3.01it/s]\u001b[A\n 14%|█▍        | 7/50 [00:02<00:14,  2.99it/s]\u001b[A\n 16%|█▌        | 8/50 [00:02<00:14,  2.99it/s]\u001b[A\n 18%|█▊        | 9/50 [00:02<00:13,  2.99it/s]\u001b[A\n 20%|██        | 10/50 [00:03<00:13,  2.98it/s]\u001b[A\n 22%|██▏       | 11/50 [00:03<00:13,  2.98it/s]\u001b[A\n 24%|██▍       | 12/50 [00:03<00:12,  2.98it/s]\u001b[A\n 26%|██▌       | 13/50 [00:04<00:12,  2.98it/s]\u001b[A\n 28%|██▊       | 14/50 [00:04<00:12,  2.98it/s]\u001b[A\n 30%|███       | 15/50 [00:04<00:11,  2.97it/s]\u001b[A\n 32%|███▏      | 16/50 [00:05<00:11,  2.98it/s]\u001b[A\n 34%|███▍      | 17/50 [00:05<00:11,  2.98it/s]\u001b[A\n 36%|███▌      | 18/50 [00:05<00:10,  2.98it/s]\u001b[A\n 38%|███▊      | 19/50 [00:06<00:10,  2.98it/s]\u001b[A\n 40%|████      | 20/50 [00:06<00:10,  2.97it/s]\u001b[A\n 42%|████▏     | 21/50 [00:06<00:09,  2.97it/s]\u001b[A\n 44%|████▍     | 22/50 [00:07<00:09,  2.98it/s]\u001b[A\n 46%|████▌     | 23/50 [00:07<00:09,  2.98it/s]\u001b[A\n 48%|████▊     | 24/50 [00:08<00:08,  2.97it/s]\u001b[A\n 50%|█████     | 25/50 [00:08<00:08,  2.97it/s]\u001b[A\n 52%|█████▏    | 26/50 [00:08<00:08,  2.97it/s]\u001b[A\n 54%|█████▍    | 27/50 [00:09<00:07,  2.97it/s]\u001b[A\n 56%|█████▌    | 28/50 [00:09<00:07,  2.97it/s]\u001b[A\n 58%|█████▊    | 29/50 [00:09<00:07,  2.98it/s]\u001b[A\n 60%|██████    | 30/50 [00:10<00:06,  2.97it/s]\u001b[A\n 62%|██████▏   | 31/50 [00:10<00:06,  2.98it/s]\u001b[A\n 64%|██████▍   | 32/50 [00:10<00:06,  2.98it/s]\u001b[A\n 66%|██████▌   | 33/50 [00:11<00:05,  2.97it/s]\u001b[A\n 68%|██████▊   | 34/50 [00:11<00:05,  2.97it/s]\u001b[A\n 70%|███████   | 35/50 [00:11<00:05,  2.97it/s]\u001b[A\n 72%|███████▏  | 36/50 [00:13<00:10,  1.39it/s]\u001b[A\n 74%|███████▍  | 37/50 [00:13<00:07,  1.70it/s]\u001b[A\n 76%|███████▌  | 38/50 [00:13<00:06,  1.96it/s]\u001b[A\n 78%|███████▊  | 39/50 [00:14<00:05,  2.18it/s]\u001b[A\n 80%|████████  | 40/50 [00:14<00:04,  2.38it/s]\u001b[A\n 82%|████████▏ | 41/50 [00:14<00:03,  2.67it/s]\u001b[A\n 84%|████████▍ | 42/50 [00:15<00:02,  2.78it/s]\u001b[A\n 86%|████████▌ | 43/50 [00:15<00:02,  2.86it/s]\u001b[A\n 88%|████████▊ | 44/50 [00:15<00:02,  2.92it/s]\u001b[A\n 90%|█████████ | 45/50 [00:16<00:01,  2.96it/s]\u001b[A\n 92%|█████████▏| 46/50 [00:16<00:01,  2.99it/s]\u001b[A\n 94%|█████████▍| 47/50 [00:16<00:00,  3.01it/s]\u001b[A\n 96%|█████████▌| 48/50 [00:17<00:00,  3.02it/s]\u001b[A\n 98%|█████████▊| 49/50 [00:17<00:00,  3.03it/s]\u001b[A\n100%|██████████| 50/50 [00:17<00:00,  3.04it/s]\u001b[A\n100%|██████████| 50/50 [00:17<00:00,  2.81it/s]\n100%|██████████| 3/3 [00:54<00:00, 18.19s/it]\n100%|██████████| 3/3 [00:54<00:00, 18.19s/it]",
  "metrics": {
    "predict_time": 177.593375,
    "total_time": 177.627474
  },
  "output": [
    "https://replicate.delivery/pbxt/tsoTLnv5VkZULFXeiP8fUXdaKfC6y3nRqb1D36cRjNThesFIB/pot.jpg",
    "https://replicate.delivery/pbxt/1yefI0hblIqbZE03OZUmVbM9N8j983qXeV4JLPUeelfS0zWgE/jar.jpg",
    "https://replicate.delivery/pbxt/tBAx4boguErsO5TqcpjipCUA8I6iwMVTaDIB13VaG2S0zWgE/cup.jpg"
  ],
  "started_at": "2023-12-12T06:43:44.495686Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/56rfuylbpukbee4wmu5oi5j3ye",
    "cancel": "https://api.replicate.com/v1/predictions/56rfuylbpukbee4wmu5oi5j3ye/cancel"
  },
  "version": "66a8d7d7a76192ef7957a9230e379188564020ee2e3c2d6976ef9e088fa24e6f"
}

Generated in

2 minutes 58 seconds

Tweak itReport View full prediction

0%|          | 0/15 [00:00<?, ?it/s]
  7%|▋         | 1/15 [00:00<00:01,  7.23it/s]
 13%|█▎        | 2/15 [00:01<00:08,  1.62it/s]
 20%|██        | 3/15 [00:02<00:09,  1.31it/s]
 27%|██▋       | 4/15 [00:02<00:09,  1.20it/s]
 33%|███▎      | 5/15 [00:03<00:08,  1.14it/s]
 40%|████      | 6/15 [00:04<00:08,  1.11it/s]
 47%|████▋     | 7/15 [00:05<00:07,  1.09it/s]
 53%|█████▎    | 8/15 [00:06<00:06,  1.08it/s]
 60%|██████    | 9/15 [00:07<00:05,  1.07it/s]
 67%|██████▋   | 10/15 [00:08<00:04,  1.07it/s]
 73%|███████▎  | 11/15 [00:09<00:03,  1.06it/s]
 80%|████████  | 12/15 [00:10<00:02,  1.06it/s]
 87%|████████▋ | 13/15 [00:11<00:01,  1.05it/s]
 93%|█████████▎| 14/15 [00:12<00:00,  1.05it/s]
100%|██████████| 15/15 [00:13<00:00,  1.05it/s]
100%|██████████| 15/15 [00:13<00:00,  1.12it/s]
prompt: a photo of a {word}
initial word: vase
TOP 50 SIMILAR WORDS:
['jar', 'pot', 'plant', 'cup', 'flower', 'bottle', 'bowl', 'lamp', 'glass', 'mug', 'rose', 'trophy', 'decor', 'candle', 'acup', 'bucket', 'something', 'water', 'drink', 'table', 'grass', 'pipe', 'one', 'bloom', 'gift', 'scent', 'bone', 'globe', 'bell', 'stone', 'abstract', 'clock', 'rock', 'drum', 'present', 'ÅŁ', 'ÄŁ', 'âł', 'Ãł', 'phone', 've', 'milk', 'vege', 'wine', 'landscape', 'head', 'can', 'garden', 'grave', 'ðŁ']
  0%|          | 0/1 [00:00<?, ?it/s]
100%|██████████| 1/1 [00:00<00:00, 62.06it/s]
prompt: a {word} with flowers on the table
initial word: vase
TOP 3 SIMILAR WORDS:
['pot', 'jar', 'cup']
The config attributes {'scaling_factor': 0.18215} were passed to AutoencoderKL, but are not expected and will be ignored. Please verify your config.json configuration file.
/root/.pyenv/versions/3.10.8/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py:101: FutureWarning: The configuration file of this scheduler: DDIMScheduler {
"_class_name": "DDIMScheduler",
"_diffusers_version": "0.10.2",
"beta_end": 0.012,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"num_train_timesteps": 1000,
"prediction_type": "epsilon",
"set_alpha_to_one": false,
"steps_offset": 0,
"trained_betas": null
}
is outdated. `steps_offset` should be set to 1 instead of 0. Please make sure to update the config accordingly as leaving `steps_offset` might led to incorrect results in future versions. If you have downloaded this checkpoint from the Hugging Face Hub, it would be very nice if you could open a Pull request for the `scheduler/scheduler_config.json` file
deprecate("steps_offset!=1", "1.0.0", deprecation_message, standard_warn=False)
Start null text inversion
DDIM inversion...
  0%|          | 0/50 [00:00<?, ?it/s]
  4%|▍         | 2/50 [00:00<00:02, 16.13it/s]
  8%|▊         | 4/50 [00:00<00:03, 12.51it/s]
 12%|█▏        | 6/50 [00:00<00:03, 11.72it/s]
 16%|█▌        | 8/50 [00:00<00:03, 11.37it/s]
 20%|██        | 10/50 [00:00<00:03, 11.14it/s]
 24%|██▍       | 12/50 [00:01<00:03, 11.04it/s]
 28%|██▊       | 14/50 [00:01<00:03, 10.97it/s]
 32%|███▏      | 16/50 [00:01<00:03, 10.92it/s]
 36%|███▌      | 18/50 [00:01<00:02, 10.88it/s]
 40%|████      | 20/50 [00:01<00:02, 10.88it/s]
 44%|████▍     | 22/50 [00:01<00:02, 10.88it/s]
 48%|████▊     | 24/50 [00:02<00:02, 10.87it/s]
 52%|█████▏    | 26/50 [00:02<00:02, 10.85it/s]
 56%|█████▌    | 28/50 [00:02<00:02, 10.85it/s]
 60%|██████    | 30/50 [00:02<00:01, 10.82it/s]
 64%|██████▍   | 32/50 [00:02<00:01, 10.73it/s]
 68%|██████▊   | 34/50 [00:03<00:01, 10.85it/s]
 72%|███████▏  | 36/50 [00:03<00:01, 10.84it/s]
 76%|███████▌  | 38/50 [00:03<00:01, 10.84it/s]
 80%|████████  | 40/50 [00:03<00:00, 10.84it/s]
 84%|████████▍ | 42/50 [00:03<00:00, 10.83it/s]
 88%|████████▊ | 44/50 [00:04<00:00, 10.82it/s]
 92%|█████████▏| 46/50 [00:04<00:00, 10.83it/s]
 96%|█████████▌| 48/50 [00:04<00:00, 10.83it/s]
100%|██████████| 50/50 [00:04<00:00, 10.83it/s]
100%|██████████| 50/50 [00:04<00:00, 10.97it/s]
Null-text optimization...
  0%|          | 0/500 [00:00<?, ?it/s]
  0%|          | 1/500 [00:00<03:22,  2.47it/s]
  0%|          | 2/500 [00:00<02:40,  3.09it/s]
  1%|          | 3/500 [00:00<02:27,  3.37it/s]
  1%|          | 4/500 [00:01<02:21,  3.51it/s]
  1%|          | 5/500 [00:01<02:17,  3.60it/s]
  1%|          | 6/500 [00:01<02:15,  3.65it/s]
  1%|▏         | 7/500 [00:02<02:13,  3.69it/s]
  2%|▏         | 8/500 [00:02<02:12,  3.71it/s]
  2%|▏         | 9/500 [00:02<02:11,  3.72it/s]
  2%|▏         | 10/500 [00:02<02:11,  3.73it/s]
  2%|▏         | 11/500 [00:03<02:46,  2.94it/s]
  2%|▏         | 12/500 [00:03<02:35,  3.15it/s]
  3%|▎         | 13/500 [00:03<02:27,  3.31it/s]
  3%|▎         | 14/500 [00:04<02:21,  3.44it/s]
  3%|▎         | 15/500 [00:04<02:17,  3.53it/s]
  3%|▎         | 16/500 [00:04<02:14,  3.59it/s]
  3%|▎         | 17/500 [00:04<02:12,  3.64it/s]
  4%|▎         | 18/500 [00:05<02:11,  3.68it/s]
  4%|▍         | 19/500 [00:05<02:09,  3.70it/s]
  4%|▍         | 20/500 [00:05<02:09,  3.72it/s]
  4%|▍         | 21/500 [00:06<02:42,  2.94it/s]
  4%|▍         | 22/500 [00:06<02:31,  3.15it/s]
  5%|▍         | 23/500 [00:06<02:24,  3.31it/s]
  5%|▍         | 24/500 [00:07<02:18,  3.43it/s]
  6%|▌         | 31/500 [00:07<00:59,  7.87it/s]
  6%|▋         | 32/500 [00:07<01:08,  6.87it/s]
  7%|▋         | 33/500 [00:08<01:16,  6.07it/s]
  8%|▊         | 41/500 [00:08<00:45, 10.09it/s]
  8%|▊         | 42/500 [00:08<00:53,  8.60it/s]
 10%|█         | 51/500 [00:09<00:36, 12.20it/s]
 12%|█▏        | 61/500 [00:09<00:29, 14.93it/s]
 13%|█▎        | 63/500 [00:10<00:39, 11.01it/s]
 14%|█▍        | 71/500 [00:10<00:34, 12.57it/s]
 16%|█▌        | 80/500 [00:11<00:25, 16.71it/s]
 16%|█▋        | 82/500 [00:11<00:40, 10.40it/s]
 18%|█▊        | 91/500 [00:12<00:32, 12.59it/s]
 20%|██        | 100/500 [00:12<00:24, 16.44it/s]
 21%|██        | 103/500 [00:13<00:41,  9.64it/s]
 22%|██▏       | 110/500 [00:13<00:31, 12.23it/s]
 22%|██▏       | 112/500 [00:14<00:45,  8.45it/s]
 24%|██▍       | 120/500 [00:15<00:31, 11.94it/s]
 24%|██▍       | 122/500 [00:15<00:46,  8.19it/s]
 26%|██▌       | 130/500 [00:16<00:31, 11.80it/s]
 26%|██▋       | 132/500 [00:16<00:45,  8.06it/s]
 28%|██▊       | 141/500 [00:17<00:33, 10.74it/s]
 29%|██▊       | 143/500 [00:17<00:41,  8.70it/s]
 30%|███       | 151/500 [00:18<00:32, 10.72it/s]
 32%|███▏      | 161/500 [00:18<00:25, 13.34it/s]
 33%|███▎      | 163/500 [00:19<00:32, 10.43it/s]
 34%|███▍      | 170/500 [00:19<00:24, 13.24it/s]
 34%|███▍      | 172/500 [00:20<00:37,  8.73it/s]
 36%|███▌      | 180/500 [00:20<00:25, 12.41it/s]
 36%|███▋      | 182/500 [00:21<00:38,  8.31it/s]
 37%|███▋      | 184/500 [00:22<00:45,  6.99it/s]
 38%|███▊      | 191/500 [00:22<00:34,  8.93it/s]
 39%|███▊      | 193/500 [00:23<00:41,  7.38it/s]
 40%|████      | 201/500 [00:23<00:30,  9.82it/s]
 41%|████      | 203/500 [00:24<00:37,  7.98it/s]
 41%|████      | 204/500 [00:24<00:40,  7.23it/s]
 42%|████▏     | 211/500 [00:24<00:30,  9.38it/s]
 42%|████▏     | 212/500 [00:25<00:34,  8.27it/s]
 43%|████▎     | 213/500 [00:25<00:39,  7.28it/s]
 43%|████▎     | 214/500 [00:25<00:44,  6.44it/s]
 44%|████▍     | 221/500 [00:26<00:29,  9.35it/s]
 44%|████▍     | 222/500 [00:26<00:34,  8.07it/s]
 45%|████▍     | 223/500 [00:26<00:39,  7.01it/s]
 45%|████▍     | 224/500 [00:26<00:44,  6.17it/s]
 45%|████▌     | 225/500 [00:27<00:49,  5.51it/s]
 46%|████▌     | 231/500 [00:27<00:32,  8.20it/s]
 46%|████▋     | 232/500 [00:28<00:37,  7.12it/s]
 47%|████▋     | 233/500 [00:28<00:42,  6.25it/s]
 47%|████▋     | 234/500 [00:28<00:47,  5.58it/s]
 47%|████▋     | 235/500 [00:28<00:52,  5.08it/s]
 48%|████▊     | 241/500 [00:29<00:32,  7.98it/s]
 48%|████▊     | 242/500 [00:29<00:37,  6.95it/s]
 49%|████▊     | 243/500 [00:29<00:41,  6.12it/s]
 49%|████▉     | 244/500 [00:30<00:46,  5.48it/s]
 49%|████▉     | 245/500 [00:30<00:51,  5.00it/s]
 49%|████▉     | 246/500 [00:30<00:54,  4.64it/s]
 49%|████▉     | 247/500 [00:30<00:57,  4.38it/s]
 50%|█████     | 251/500 [00:31<00:41,  5.94it/s]
 50%|█████     | 252/500 [00:31<00:45,  5.39it/s]
 51%|█████     | 253/500 [00:31<00:49,  4.96it/s]
 51%|█████     | 254/500 [00:32<00:53,  4.63it/s]
 51%|█████     | 255/500 [00:32<00:55,  4.38it/s]
 51%|█████     | 256/500 [00:32<00:58,  4.20it/s]
 52%|█████▏    | 261/500 [00:33<00:35,  6.68it/s]
 52%|█████▏    | 262/500 [00:33<00:39,  5.96it/s]
 53%|█████▎    | 263/500 [00:33<00:44,  5.38it/s]
 53%|█████▎    | 264/500 [00:34<00:47,  4.94it/s]
 53%|█████▎    | 265/500 [00:34<00:51,  4.60it/s]
 54%|█████▍    | 271/500 [00:34<00:29,  7.73it/s]
 54%|█████▍    | 272/500 [00:35<00:33,  6.75it/s]
 55%|█████▍    | 273/500 [00:35<00:38,  5.97it/s]
 55%|█████▍    | 274/500 [00:35<00:42,  5.37it/s]
 55%|█████▌    | 275/500 [00:35<00:45,  4.91it/s]
 55%|█████▌    | 276/500 [00:36<00:48,  4.58it/s]
 55%|█████▌    | 277/500 [00:36<00:51,  4.34it/s]
 56%|█████▌    | 281/500 [00:36<00:37,  5.91it/s]
 56%|█████▋    | 282/500 [00:37<00:40,  5.37it/s]
 57%|█████▋    | 283/500 [00:37<00:43,  4.95it/s]
 57%|█████▋    | 284/500 [00:37<00:46,  4.62it/s]
 57%|█████▋    | 285/500 [00:38<00:49,  4.38it/s]
 58%|█████▊    | 291/500 [00:38<00:27,  7.61it/s]
 58%|█████▊    | 292/500 [00:38<00:31,  6.66it/s]
 59%|█████▊    | 293/500 [00:39<00:35,  5.90it/s]
 59%|█████▉    | 294/500 [00:39<00:38,  5.32it/s]
 59%|█████▉    | 295/500 [00:39<00:42,  4.88it/s]
 59%|█████▉    | 296/500 [00:39<00:44,  4.56it/s]
 60%|██████    | 301/500 [00:40<00:28,  6.87it/s]
 60%|██████    | 302/500 [00:40<00:32,  6.10it/s]
 61%|██████    | 303/500 [00:40<00:35,  5.48it/s]
 61%|██████    | 304/500 [00:41<00:39,  5.01it/s]
 61%|██████    | 305/500 [00:41<00:41,  4.66it/s]
 61%|██████    | 306/500 [00:41<00:44,  4.40it/s]
 62%|██████▏   | 311/500 [00:42<00:27,  6.79it/s]
 62%|██████▏   | 312/500 [00:42<00:31,  6.03it/s]
 63%|██████▎   | 313/500 [00:42<00:34,  5.43it/s]
 63%|██████▎   | 314/500 [00:42<00:37,  4.98it/s]
 63%|██████▎   | 315/500 [00:43<00:39,  4.63it/s]
 64%|██████▍   | 321/500 [00:43<00:23,  7.75it/s]
 64%|██████▍   | 322/500 [00:44<00:26,  6.77it/s]
 65%|██████▍   | 323/500 [00:44<00:29,  5.98it/s]
 65%|██████▍   | 324/500 [00:44<00:32,  5.38it/s]
 65%|██████▌   | 325/500 [00:44<00:35,  4.92it/s]
 65%|██████▌   | 326/500 [00:45<00:37,  4.59it/s]
 65%|██████▌   | 327/500 [00:45<00:39,  4.35it/s]
 66%|██████▌   | 331/500 [00:45<00:28,  5.91it/s]
 66%|██████▋   | 332/500 [00:46<00:31,  5.37it/s]
 67%|██████▋   | 333/500 [00:46<00:33,  4.95it/s]
 67%|██████▋   | 334/500 [00:46<00:35,  4.62it/s]
 67%|██████▋   | 335/500 [00:46<00:37,  4.38it/s]
 67%|██████▋   | 336/500 [00:47<00:39,  4.19it/s]
 67%|██████▋   | 337/500 [00:47<00:40,  4.06it/s]
 68%|██████▊   | 341/500 [00:47<00:27,  5.75it/s]
 68%|██████▊   | 342/500 [00:48<00:30,  5.25it/s]
 69%|██████▊   | 343/500 [00:48<00:32,  4.86it/s]
 69%|██████▉   | 344/500 [00:48<00:34,  4.55it/s]
 69%|██████▉   | 345/500 [00:49<00:35,  4.32it/s]
 69%|██████▉   | 346/500 [00:49<00:37,  4.16it/s]
 69%|██████▉   | 347/500 [00:49<00:37,  4.04it/s]
 70%|███████   | 351/500 [00:50<00:25,  5.73it/s]
 70%|███████   | 352/500 [00:50<00:28,  5.24it/s]
 71%|███████   | 353/500 [00:50<00:30,  4.85it/s]
 71%|███████   | 354/500 [00:50<00:32,  4.55it/s]
 71%|███████   | 355/500 [00:51<00:33,  4.32it/s]
 71%|███████   | 356/500 [00:51<00:34,  4.16it/s]
 72%|███████▏  | 361/500 [00:51<00:20,  6.65it/s]
 72%|███████▏  | 362/500 [00:52<00:23,  5.94it/s]
 73%|███████▎  | 363/500 [00:52<00:25,  5.36it/s]
 73%|███████▎  | 364/500 [00:52<00:27,  4.92it/s]
 73%|███████▎  | 365/500 [00:52<00:29,  4.59it/s]
 73%|███████▎  | 366/500 [00:53<00:30,  4.35it/s]
 73%|███████▎  | 367/500 [00:53<00:31,  4.17it/s]
 74%|███████▎  | 368/500 [00:53<00:32,  4.05it/s]
 74%|███████▍  | 371/500 [00:54<00:26,  4.87it/s]
 74%|███████▍  | 372/500 [00:54<00:27,  4.59it/s]
 75%|███████▍  | 373/500 [00:54<00:29,  4.37it/s]
 75%|███████▍  | 374/500 [00:55<00:30,  4.19it/s]
 75%|███████▌  | 375/500 [00:55<00:30,  4.07it/s]
 75%|███████▌  | 376/500 [00:55<00:31,  3.98it/s]
 76%|███████▌  | 381/500 [00:56<00:18,  6.55it/s]
 76%|███████▋  | 382/500 [00:56<00:20,  5.85it/s]
 77%|███████▋  | 383/500 [00:56<00:22,  5.30it/s]
 77%|███████▋  | 384/500 [00:56<00:23,  4.88it/s]
 77%|███████▋  | 385/500 [00:57<00:25,  4.56it/s]
 77%|███████▋  | 386/500 [00:57<00:26,  4.33it/s]
 78%|███████▊  | 391/500 [00:57<00:16,  6.74it/s]
 78%|███████▊  | 392/500 [00:58<00:17,  6.00it/s]
 79%|███████▊  | 393/500 [00:58<00:19,  5.41it/s]
 79%|███████▉  | 394/500 [00:58<00:21,  4.96it/s]
 79%|███████▉  | 395/500 [00:59<00:22,  4.62it/s]
 79%|███████▉  | 396/500 [00:59<00:23,  4.37it/s]
 79%|███████▉  | 397/500 [00:59<00:24,  4.18it/s]
 80%|████████  | 401/500 [01:00<00:17,  5.82it/s]
 80%|████████  | 402/500 [01:00<00:18,  5.30it/s]
 81%|████████  | 403/500 [01:00<00:19,  4.89it/s]
 81%|████████  | 404/500 [01:00<00:20,  4.58it/s]
 81%|████████  | 405/500 [01:01<00:21,  4.34it/s]
 81%|████████  | 406/500 [01:01<00:22,  4.17it/s]
 81%|████████▏ | 407/500 [01:01<00:22,  4.05it/s]
 82%|████████▏ | 408/500 [01:01<00:23,  3.96it/s]
 82%|████████▏ | 411/500 [01:02<00:18,  4.83it/s]
 82%|████████▏ | 412/500 [01:02<00:19,  4.56it/s]
 83%|████████▎ | 413/500 [01:03<00:20,  4.34it/s]
 83%|████████▎ | 414/500 [01:03<00:20,  4.18it/s]
 83%|████████▎ | 415/500 [01:03<00:20,  4.05it/s]
 83%|████████▎ | 416/500 [01:03<00:21,  3.97it/s]
 83%|████████▎ | 417/500 [01:04<00:21,  3.90it/s]
 84%|████████▎ | 418/500 [01:04<00:21,  3.85it/s]
 84%|████████▍ | 419/500 [01:04<00:21,  3.82it/s]
 84%|████████▍ | 420/500 [01:04<00:21,  3.80it/s]
 84%|████████▍ | 421/500 [01:05<00:26,  2.99it/s]
 84%|████████▍ | 422/500 [01:05<00:24,  3.18it/s]
 85%|████████▍ | 423/500 [01:05<00:23,  3.32it/s]
 85%|████████▍ | 424/500 [01:06<00:22,  3.44it/s]
 85%|████████▌ | 425/500 [01:06<00:21,  3.52it/s]
 85%|████████▌ | 426/500 [01:06<00:20,  3.58it/s]
 85%|████████▌ | 427/500 [01:06<00:20,  3.63it/s]
 86%|████████▌ | 428/500 [01:07<00:19,  3.66it/s]
 86%|████████▌ | 429/500 [01:07<00:19,  3.68it/s]
 86%|████████▌ | 430/500 [01:07<00:18,  3.70it/s]
 86%|████████▌ | 431/500 [01:08<00:23,  2.90it/s]
 86%|████████▋ | 432/500 [01:08<00:21,  3.10it/s]
 87%|████████▋ | 433/500 [01:08<00:20,  3.27it/s]
 87%|████████▋ | 434/500 [01:09<00:19,  3.40it/s]
 87%|████████▋ | 435/500 [01:09<00:18,  3.49it/s]
 87%|████████▋ | 436/500 [01:09<00:17,  3.56it/s]
 87%|████████▋ | 437/500 [01:09<00:17,  3.61it/s]
 88%|████████▊ | 438/500 [01:10<00:16,  3.65it/s]
 88%|████████▊ | 439/500 [01:10<00:16,  3.68it/s]
 88%|████████▊ | 440/500 [01:10<00:16,  3.69it/s]
 88%|████████▊ | 441/500 [01:11<00:20,  2.93it/s]
 88%|████████▊ | 442/500 [01:11<00:18,  3.13it/s]
 89%|████████▊ | 443/500 [01:11<00:17,  3.29it/s]
 89%|████████▉ | 444/500 [01:12<00:16,  3.41it/s]
 89%|████████▉ | 445/500 [01:12<00:15,  3.50it/s]
 89%|████████▉ | 446/500 [01:12<00:15,  3.57it/s]
 89%|████████▉ | 447/500 [01:12<00:14,  3.62it/s]
 90%|████████▉ | 448/500 [01:13<00:14,  3.66it/s]
 90%|████████▉ | 449/500 [01:13<00:13,  3.68it/s]
 90%|█████████ | 450/500 [01:13<00:13,  3.70it/s]
 90%|█████████ | 451/500 [01:14<00:16,  2.93it/s]
 90%|█████████ | 452/500 [01:14<00:15,  3.13it/s]
 91%|█████████ | 453/500 [01:14<00:14,  3.29it/s]
 91%|█████████ | 454/500 [01:14<00:13,  3.42it/s]
 91%|█████████ | 455/500 [01:15<00:12,  3.51it/s]
 91%|█████████ | 456/500 [01:15<00:12,  3.58it/s]
 91%|█████████▏| 457/500 [01:15<00:11,  3.63it/s]
 92%|█████████▏| 458/500 [01:16<00:11,  3.66it/s]
 92%|█████████▏| 459/500 [01:16<00:11,  3.69it/s]
 92%|█████████▏| 460/500 [01:16<00:10,  3.70it/s]
 92%|█████████▏| 461/500 [01:17<00:13,  2.93it/s]
 92%|█████████▏| 462/500 [01:17<00:12,  3.13it/s]
 93%|█████████▎| 463/500 [01:17<00:11,  3.29it/s]
 93%|█████████▎| 464/500 [01:17<00:10,  3.42it/s]
 93%|█████████▎| 465/500 [01:18<00:09,  3.51it/s]
 93%|█████████▎| 466/500 [01:18<00:09,  3.57it/s]
 93%|█████████▎| 467/500 [01:18<00:09,  3.62it/s]
 94%|█████████▎| 468/500 [01:18<00:08,  3.66it/s]
 94%|█████████▍| 469/500 [01:19<00:08,  3.68it/s]
 94%|█████████▍| 470/500 [01:19<00:08,  3.70it/s]
 94%|█████████▍| 471/500 [01:19<00:09,  2.93it/s]
 94%|█████████▍| 472/500 [01:20<00:08,  3.13it/s]
 95%|█████████▍| 473/500 [01:20<00:08,  3.29it/s]
 95%|█████████▍| 474/500 [01:20<00:07,  3.42it/s]
 95%|█████████▌| 475/500 [01:21<00:07,  3.51it/s]
 95%|█████████▌| 476/500 [01:21<00:06,  3.57it/s]
 95%|█████████▌| 477/500 [01:21<00:06,  3.62it/s]
 96%|█████████▌| 478/500 [01:21<00:06,  3.66it/s]
 96%|█████████▌| 479/500 [01:22<00:05,  3.68it/s]
 96%|█████████▌| 480/500 [01:22<00:05,  3.69it/s]
 96%|█████████▌| 481/500 [01:22<00:06,  2.93it/s]
 96%|█████████▋| 482/500 [01:23<00:05,  3.13it/s]
 97%|█████████▋| 483/500 [01:23<00:05,  3.29it/s]
 97%|█████████▋| 484/500 [01:23<00:04,  3.41it/s]
 97%|█████████▋| 485/500 [01:23<00:04,  3.50it/s]
 97%|█████████▋| 486/500 [01:24<00:03,  3.57it/s]
 97%|█████████▋| 487/500 [01:24<00:03,  3.62it/s]
 98%|█████████▊| 488/500 [01:24<00:03,  3.65it/s]
 98%|█████████▊| 489/500 [01:25<00:02,  3.68it/s]
 98%|█████████▊| 490/500 [01:25<00:02,  3.70it/s]
 98%|█████████▊| 491/500 [01:25<00:03,  2.93it/s]
 98%|█████████▊| 492/500 [01:26<00:02,  3.13it/s]
 99%|█████████▊| 493/500 [01:26<00:02,  3.29it/s]
 99%|█████████▉| 494/500 [01:26<00:01,  3.41it/s]
 99%|█████████▉| 495/500 [01:26<00:01,  3.51it/s]
 99%|█████████▉| 496/500 [01:27<00:01,  3.57it/s]
 99%|█████████▉| 497/500 [01:27<00:00,  3.62it/s]
100%|█████████▉| 498/500 [01:27<00:00,  3.65it/s]
100%|█████████▉| 499/500 [01:27<00:00,  3.68it/s]
100%|██████████| 500/500 [01:28<00:00,  3.70it/s]
100%|██████████| 500/500 [01:28<00:00,  5.67it/s]
End null text inversion
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:06,  7.48it/s]
  4%|▍         | 2/50 [00:00<00:08,  5.71it/s]
  6%|▌         | 3/50 [00:00<00:08,  5.31it/s]
  8%|▊         | 4/50 [00:00<00:08,  5.15it/s]
 10%|█         | 5/50 [00:00<00:08,  5.05it/s]
 12%|█▏        | 6/50 [00:01<00:08,  5.00it/s]
 14%|█▍        | 7/50 [00:01<00:08,  4.97it/s]
 16%|█▌        | 8/50 [00:01<00:08,  4.95it/s]
 18%|█▊        | 9/50 [00:01<00:08,  4.94it/s]
 20%|██        | 10/50 [00:01<00:08,  4.87it/s]
 22%|██▏       | 11/50 [00:02<00:07,  4.94it/s]
 24%|██▍       | 12/50 [00:02<00:07,  4.93it/s]
 26%|██▌       | 13/50 [00:02<00:07,  4.90it/s]
 28%|██▊       | 14/50 [00:02<00:07,  4.91it/s]
 30%|███       | 15/50 [00:02<00:07,  4.90it/s]
 32%|███▏      | 16/50 [00:03<00:06,  4.93it/s]
 34%|███▍      | 17/50 [00:03<00:06,  4.92it/s]
 36%|███▌      | 18/50 [00:03<00:06,  4.91it/s]
 38%|███▊      | 19/50 [00:03<00:06,  4.91it/s]
 40%|████      | 20/50 [00:04<00:06,  4.90it/s]
 42%|████▏     | 21/50 [00:04<00:05,  4.90it/s]
 44%|████▍     | 22/50 [00:04<00:05,  4.90it/s]
 46%|████▌     | 23/50 [00:04<00:05,  4.90it/s]
 48%|████▊     | 24/50 [00:04<00:05,  4.90it/s]
 50%|█████     | 25/50 [00:05<00:05,  4.89it/s]
 52%|█████▏    | 26/50 [00:05<00:04,  4.89it/s]
 54%|█████▍    | 27/50 [00:05<00:04,  4.91it/s]
 56%|█████▌    | 28/50 [00:05<00:04,  4.91it/s]
 58%|█████▊    | 29/50 [00:05<00:04,  4.91it/s]
 60%|██████    | 30/50 [00:06<00:04,  4.90it/s]
 62%|██████▏   | 31/50 [00:06<00:03,  4.90it/s]
 64%|██████▍   | 32/50 [00:06<00:03,  4.91it/s]
 66%|██████▌   | 33/50 [00:06<00:03,  4.91it/s]
 68%|██████▊   | 34/50 [00:06<00:03,  4.90it/s]
 70%|███████   | 35/50 [00:07<00:03,  4.90it/s]
 72%|███████▏  | 36/50 [00:07<00:02,  4.91it/s]
 74%|███████▍  | 37/50 [00:07<00:02,  4.90it/s]
 76%|███████▌  | 38/50 [00:07<00:02,  4.91it/s]
 78%|███████▊  | 39/50 [00:07<00:02,  4.91it/s]
 80%|████████  | 40/50 [00:08<00:02,  4.89it/s]
 82%|████████▏ | 41/50 [00:08<00:01,  4.90it/s]
 84%|████████▍ | 42/50 [00:08<00:01,  4.90it/s]
 86%|████████▌ | 43/50 [00:08<00:01,  4.91it/s]
 88%|████████▊ | 44/50 [00:08<00:01,  4.91it/s]
 90%|█████████ | 45/50 [00:09<00:01,  4.91it/s]
 92%|█████████▏| 46/50 [00:09<00:00,  4.91it/s]
 94%|█████████▍| 47/50 [00:09<00:00,  4.91it/s]
 96%|█████████▌| 48/50 [00:09<00:00,  4.91it/s]
 98%|█████████▊| 49/50 [00:09<00:00,  4.90it/s]
100%|██████████| 50/50 [00:10<00:00,  4.91it/s]
100%|██████████| 50/50 [00:10<00:00,  4.94it/s]
Do self attn other obj masking
  0%|          | 0/3 [00:00<?, ?it/s]
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:13,  3.57it/s]
  4%|▍         | 2/50 [00:00<00:14,  3.21it/s]
  6%|▌         | 3/50 [00:00<00:15,  3.10it/s]
  8%|▊         | 4/50 [00:01<00:15,  3.05it/s]
 10%|█         | 5/50 [00:01<00:14,  3.03it/s]
 12%|█▏        | 6/50 [00:01<00:14,  3.01it/s]
 14%|█▍        | 7/50 [00:02<00:14,  3.00it/s]
 16%|█▌        | 8/50 [00:02<00:14,  2.99it/s]
 18%|█▊        | 9/50 [00:02<00:13,  2.99it/s]
 20%|██        | 10/50 [00:03<00:13,  2.99it/s]
 22%|██▏       | 11/50 [00:03<00:13,  2.99it/s]
 24%|██▍       | 12/50 [00:03<00:12,  2.99it/s]
 26%|██▌       | 13/50 [00:04<00:12,  2.98it/s]
 28%|██▊       | 14/50 [00:04<00:12,  2.98it/s]
 30%|███       | 15/50 [00:04<00:11,  2.98it/s]
 32%|███▏      | 16/50 [00:05<00:11,  2.98it/s]
 34%|███▍      | 17/50 [00:05<00:11,  2.98it/s]
 36%|███▌      | 18/50 [00:05<00:10,  2.98it/s]
 38%|███▊      | 19/50 [00:06<00:10,  2.98it/s]
 40%|████      | 20/50 [00:06<00:10,  2.98it/s]
 42%|████▏     | 21/50 [00:06<00:09,  2.98it/s]
 44%|████▍     | 22/50 [00:07<00:09,  2.98it/s]
 46%|████▌     | 23/50 [00:07<00:09,  2.98it/s]
 48%|████▊     | 24/50 [00:07<00:08,  2.98it/s]
 50%|█████     | 25/50 [00:08<00:08,  2.98it/s]
 52%|█████▏    | 26/50 [00:08<00:08,  2.98it/s]
 54%|█████▍    | 27/50 [00:09<00:07,  2.98it/s]
 56%|█████▌    | 28/50 [00:09<00:07,  2.98it/s]
 58%|█████▊    | 29/50 [00:09<00:07,  2.98it/s]
 60%|██████    | 30/50 [00:10<00:06,  2.97it/s]
 62%|██████▏   | 31/50 [00:10<00:06,  2.97it/s]
 64%|██████▍   | 32/50 [00:10<00:06,  2.97it/s]
 66%|██████▌   | 33/50 [00:11<00:05,  2.98it/s]
 68%|██████▊   | 34/50 [00:11<00:05,  2.97it/s]
 70%|███████   | 35/50 [00:11<00:05,  2.98it/s]
 72%|███████▏  | 36/50 [00:13<00:10,  1.38it/s]
 74%|███████▍  | 37/50 [00:13<00:07,  1.69it/s]
 76%|███████▌  | 38/50 [00:13<00:06,  1.95it/s]
 78%|███████▊  | 39/50 [00:14<00:05,  2.18it/s]
 80%|████████  | 40/50 [00:14<00:04,  2.37it/s]
 82%|████████▏ | 41/50 [00:14<00:03,  2.67it/s]
 84%|████████▍ | 42/50 [00:15<00:02,  2.78it/s]
 86%|████████▌ | 43/50 [00:15<00:02,  2.86it/s]
 88%|████████▊ | 44/50 [00:15<00:02,  2.92it/s]
 90%|█████████ | 45/50 [00:16<00:01,  2.96it/s]
 92%|█████████▏| 46/50 [00:16<00:01,  2.99it/s]
 94%|█████████▍| 47/50 [00:16<00:00,  3.01it/s]
 96%|█████████▌| 48/50 [00:17<00:00,  3.03it/s]
 98%|█████████▊| 49/50 [00:17<00:00,  3.04it/s]
100%|██████████| 50/50 [00:17<00:00,  3.05it/s]
100%|██████████| 50/50 [00:17<00:00,  2.81it/s]
 33%|███▎      | 1/3 [00:18<00:36, 18.18s/it]
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:13,  3.56it/s]
  4%|▍         | 2/50 [00:00<00:14,  3.20it/s]
  6%|▌         | 3/50 [00:00<00:15,  3.11it/s]
  8%|▊         | 4/50 [00:01<00:15,  3.05it/s]
 10%|█         | 5/50 [00:01<00:14,  3.03it/s]
 12%|█▏        | 6/50 [00:01<00:14,  3.01it/s]
 14%|█▍        | 7/50 [00:02<00:14,  3.01it/s]
 16%|█▌        | 8/50 [00:02<00:13,  3.00it/s]
 18%|█▊        | 9/50 [00:02<00:13,  2.99it/s]
 20%|██        | 10/50 [00:03<00:13,  2.99it/s]
 22%|██▏       | 11/50 [00:03<00:13,  2.98it/s]
 24%|██▍       | 12/50 [00:03<00:12,  2.98it/s]
 26%|██▌       | 13/50 [00:04<00:12,  2.98it/s]
 28%|██▊       | 14/50 [00:04<00:12,  2.98it/s]
 30%|███       | 15/50 [00:04<00:11,  2.98it/s]
 32%|███▏      | 16/50 [00:05<00:11,  2.98it/s]
 34%|███▍      | 17/50 [00:05<00:11,  2.98it/s]
 36%|███▌      | 18/50 [00:05<00:10,  2.98it/s]
 38%|███▊      | 19/50 [00:06<00:10,  2.98it/s]
 40%|████      | 20/50 [00:06<00:10,  2.98it/s]
 42%|████▏     | 21/50 [00:06<00:09,  2.98it/s]
 44%|████▍     | 22/50 [00:07<00:09,  2.98it/s]
 46%|████▌     | 23/50 [00:07<00:09,  2.98it/s]
 48%|████▊     | 24/50 [00:07<00:08,  2.98it/s]
 50%|█████     | 25/50 [00:08<00:08,  2.98it/s]
 52%|█████▏    | 26/50 [00:08<00:08,  2.98it/s]
 54%|█████▍    | 27/50 [00:09<00:07,  2.98it/s]
 56%|█████▌    | 28/50 [00:09<00:07,  2.98it/s]
 58%|█████▊    | 29/50 [00:09<00:07,  2.98it/s]
 60%|██████    | 30/50 [00:10<00:06,  2.98it/s]
 62%|██████▏   | 31/50 [00:10<00:06,  2.98it/s]
 64%|██████▍   | 32/50 [00:10<00:06,  2.98it/s]
 66%|██████▌   | 33/50 [00:11<00:05,  2.98it/s]
 68%|██████▊   | 34/50 [00:11<00:05,  2.98it/s]
 70%|███████   | 35/50 [00:11<00:05,  2.98it/s]
 72%|███████▏  | 36/50 [00:13<00:10,  1.36it/s]
 74%|███████▍  | 37/50 [00:13<00:07,  1.67it/s]
 76%|███████▌  | 38/50 [00:13<00:06,  1.93it/s]
 78%|███████▊  | 39/50 [00:14<00:05,  2.16it/s]
 80%|████████  | 40/50 [00:14<00:04,  2.35it/s]
 82%|████████▏ | 41/50 [00:14<00:03,  2.65it/s]
 84%|████████▍ | 42/50 [00:15<00:02,  2.76it/s]
 86%|████████▌ | 43/50 [00:15<00:02,  2.85it/s]
 88%|████████▊ | 44/50 [00:15<00:02,  2.91it/s]
 90%|█████████ | 45/50 [00:16<00:01,  2.95it/s]
 92%|█████████▏| 46/50 [00:16<00:01,  2.98it/s]
 94%|█████████▍| 47/50 [00:16<00:00,  3.01it/s]
 96%|█████████▌| 48/50 [00:17<00:00,  3.02it/s]
 98%|█████████▊| 49/50 [00:17<00:00,  3.03it/s]
100%|██████████| 50/50 [00:17<00:00,  3.04it/s]
100%|██████████| 50/50 [00:17<00:00,  2.80it/s]
 67%|██████▋   | 2/3 [00:36<00:18, 18.20s/it]
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:13,  3.56it/s]
  4%|▍         | 2/50 [00:00<00:14,  3.20it/s]
  6%|▌         | 3/50 [00:00<00:15,  3.09it/s]
  8%|▊         | 4/50 [00:01<00:15,  3.05it/s]
 10%|█         | 5/50 [00:01<00:14,  3.02it/s]
 12%|█▏        | 6/50 [00:01<00:14,  3.01it/s]
 14%|█▍        | 7/50 [00:02<00:14,  2.99it/s]
 16%|█▌        | 8/50 [00:02<00:14,  2.99it/s]
 18%|█▊        | 9/50 [00:02<00:13,  2.99it/s]
 20%|██        | 10/50 [00:03<00:13,  2.98it/s]
 22%|██▏       | 11/50 [00:03<00:13,  2.98it/s]
 24%|██▍       | 12/50 [00:03<00:12,  2.98it/s]
 26%|██▌       | 13/50 [00:04<00:12,  2.98it/s]
 28%|██▊       | 14/50 [00:04<00:12,  2.98it/s]
 30%|███       | 15/50 [00:04<00:11,  2.97it/s]
 32%|███▏      | 16/50 [00:05<00:11,  2.98it/s]
 34%|███▍      | 17/50 [00:05<00:11,  2.98it/s]
 36%|███▌      | 18/50 [00:05<00:10,  2.98it/s]
 38%|███▊      | 19/50 [00:06<00:10,  2.98it/s]
 40%|████      | 20/50 [00:06<00:10,  2.97it/s]
 42%|████▏     | 21/50 [00:06<00:09,  2.97it/s]
 44%|████▍     | 22/50 [00:07<00:09,  2.98it/s]
 46%|████▌     | 23/50 [00:07<00:09,  2.98it/s]
 48%|████▊     | 24/50 [00:08<00:08,  2.97it/s]
 50%|█████     | 25/50 [00:08<00:08,  2.97it/s]
 52%|█████▏    | 26/50 [00:08<00:08,  2.97it/s]
 54%|█████▍    | 27/50 [00:09<00:07,  2.97it/s]
 56%|█████▌    | 28/50 [00:09<00:07,  2.97it/s]
 58%|█████▊    | 29/50 [00:09<00:07,  2.98it/s]
 60%|██████    | 30/50 [00:10<00:06,  2.97it/s]
 62%|██████▏   | 31/50 [00:10<00:06,  2.98it/s]
 64%|██████▍   | 32/50 [00:10<00:06,  2.98it/s]
 66%|██████▌   | 33/50 [00:11<00:05,  2.97it/s]
 68%|██████▊   | 34/50 [00:11<00:05,  2.97it/s]
 70%|███████   | 35/50 [00:11<00:05,  2.97it/s]
 72%|███████▏  | 36/50 [00:13<00:10,  1.39it/s]
 74%|███████▍  | 37/50 [00:13<00:07,  1.70it/s]
 76%|███████▌  | 38/50 [00:13<00:06,  1.96it/s]
 78%|███████▊  | 39/50 [00:14<00:05,  2.18it/s]
 80%|████████  | 40/50 [00:14<00:04,  2.38it/s]
 82%|████████▏ | 41/50 [00:14<00:03,  2.67it/s]
 84%|████████▍ | 42/50 [00:15<00:02,  2.78it/s]
 86%|████████▌ | 43/50 [00:15<00:02,  2.86it/s]
 88%|████████▊ | 44/50 [00:15<00:02,  2.92it/s]
 90%|█████████ | 45/50 [00:16<00:01,  2.96it/s]
 92%|█████████▏| 46/50 [00:16<00:01,  2.99it/s]
 94%|█████████▍| 47/50 [00:16<00:00,  3.01it/s]
 96%|█████████▌| 48/50 [00:17<00:00,  3.02it/s]
 98%|█████████▊| 49/50 [00:17<00:00,  3.03it/s]
100%|██████████| 50/50 [00:17<00:00,  3.04it/s]
100%|██████████| 50/50 [00:17<00:00,  2.81it/s]
100%|██████████| 3/3 [00:54<00:00, 18.19s/it]
100%|██████████| 3/3 [00:54<00:00, 18.19s/it]

This output was created using a different version of the model, adirik/local-prompt-mixing:66a8d7d7.

Examples

View more examples

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

Local Prompt Mixing

Local prompt mixing is an image-to-image model which uses Stable Diffusion 1.4. It enables generating variations of an object in an image while preserving other elements in the image. See the original repository, project page or paper for details.

How to use the API

To use Local Prompt Mixing, simply upload an image (.jpg or .png) where you want to modify an object of interest. Provide a simple description of the image (prompt), the name of the object which will be modified. The outputs (variations on the object and the grid image which contains all of them) will be in .jpg format. The API input arguments are as follows:

prompt: a simple description of the image
object_of_interest: the object that you want to generate variations of it
proxy_words: the object(s) that you want to generate instead of object_of_interest
objects_to_preserve: the object(s) that you want to preserve in the image
number_of_variations: the number of auto-generated objects if you didn’t provide any proxy_words
steps: the number of denoising steps for Stable Diffusion
start_prompt_range: nth step where the prompt mixing begins
end_prompt_range: nth step where the prompt mixing ends
guidance_scale: the guidance scale of Stable Diffusion
seed: seed for reproducibility, default value is 10. Set to an arbitrary value for deterministic generation.

Important Notes

Your prompt must contain the word for object_of_interest (i.e. prompt: “a table below a lamp”, object_of_interest: “lamp”), otherwise API will not work properly.
This API has 2 major options for proxy words. If you provide your own words, Stable Diffusion will try to generate variations of the object of interest according to them. If they are sementically closer (i.e. lamp -> light), the performance will be better. If you don’t provide proxy words, API will select words sementically closer to your object of interest. The number of auto generated words are determined by number_of_variations parameter. Thus, please choose one of the approaches.
The parameters, “start_prompt_range” and “end_prompt_range” must be smaller than the parameter, “steps”. Also, “start_prompt_range” must be smaller than “end_prompt_range”.

References

@InProceedings{patashnik2023localizing, author = {Patashnik, Or and Garibi, Daniel and Azuri, Idan and Averbuch-Elor, Hadar and Cohen-Or, Daniel}, title = {Localizing Object-level Shape Variations with Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023} }