nightmareai / majesty-diffusion

Generate images from text using CLIP guided latent diffusion

Cold

Public
8.3K runs
A100 (80GB)
GitHub

Run with an API

Playground API Examples README Versions

Input

clip_prompts

string

Shift + Return to add a new line

The visual style of the image is akin to a retro 8-bit look, with clean lines and flat colors. There is a cartoonish quality to some of the characters and objects, as if they are depictions of vaporwave tropes or influences.The visual style of the image is akin to a retro 8-bit look, with clean lines and flat colors. There is a cartoonish quality to some of the characters and objects, as if they are depictions of vaporwave tropes or influences.

Prompts for CLIP guidance, multiple prompts allowed, one per line. Supports weights.

Default: "The portrait of a Majestic Princess, trending on artstation\n"

latent_prompt

string

Shift + Return to add a new line

Prompt for latent diffusion, single prompt, no weights.

Default: "The portrait of a Majestic Princess, trending on artstation"

height

integer

Output height (height OR width must be less than 1024 to avoid OOM)

Default: 512

width

integer

Output width

Default: 512

clip_scale

integer

Determines how much the CLIP prompts affect the image. Note the numeric scale is not the same as the latent prompt.

Default: 9500

latent_scale

integer

Determines how much the latent_prompt affects the image. Lower help with text interpretation, higher help with composition. Try values between 0-15. If you see too much text, lower it

aesthetic_loss_scale

integer

Aesthetic loss scale

Default: 400

starting_timestep

number

Starting timestep

Default: 0.9

model

string

Latent diffusion model (recommended to stick with finetuned - ongo and erlich may need to download, taking extra time)

Default: "finetuned"

latent_negative

string

Shift + Return to add a new line

Negative prompt for Latent Diffusion (things to steer away from)

Default: ""

output_steps

integer

Steps between outputs, 0 to disable progressive output. Minor speed impact.

Default: 10

init_image

file

Initial image (optional, used instead of noise if supplied)

init_mask

file

A mask same width and height as the initial image with the color white indicating where to inpaint

init_scale

integer

Controls how much the init image should influence the final result. Experiment with values around 1000

Default: 1000

init_brightness

number

Init image brightness

Default: 0

custom_settings

string

Shift + Return to add a new line

Custom settings cfg content, for custom or API usage. See Majesty docs.

Default: "\n"

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

npx create-replicate --model=nightmareai/majesty-diffusion

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 nightmareai/majesty-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nightmareai/majesty-diffusion:76f01b269da5b6f12d201700e3e7d253b7decefe4d9d8ae9417df5977f63fb8d",
  {
    input: {
      model: "finetuned",
      width: 640,
      height: 768,
      clip_scale: 16000,
      init_scale: 1000,
      clip_prompts: "The visual style of the image is akin to a retro 8-bit look, with clean lines and flat colors. There is a cartoonish quality to some of the characters and objects, as if they are depictions of vaporwave tropes or influences.",
      latent_scale: 12,
      output_steps: 10,
      latent_prompt: "vaporwave princess",
      custom_settings: "\n",
      init_brightness: 0,
      latent_negative: "",
      starting_timestep: 0.9,
      aesthetic_loss_scale: 400
    }
  }
);
console.log(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 nightmareai/majesty-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nightmareai/majesty-diffusion:76f01b269da5b6f12d201700e3e7d253b7decefe4d9d8ae9417df5977f63fb8d",
    input={
        "model": "finetuned",
        "width": 640,
        "height": 768,
        "clip_scale": 16000,
        "init_scale": 1000,
        "clip_prompts": "The visual style of the image is akin to a retro 8-bit look, with clean lines and flat colors. There is a cartoonish quality to some of the characters and objects, as if they are depictions of vaporwave tropes or influences.",
        "latent_scale": 12,
        "output_steps": 10,
        "latent_prompt": "vaporwave princess",
        "custom_settings": "\n",
        "init_brightness": 0,
        "latent_negative": "",
        "starting_timestep": 0.9,
        "aesthetic_loss_scale": 400
    }
)

# The nightmareai/majesty-diffusion model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/nightmareai/majesty-diffusion/api#output-schema
    print(item)

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 nightmareai/majesty-diffusion 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": "76f01b269da5b6f12d201700e3e7d253b7decefe4d9d8ae9417df5977f63fb8d",
    "input": {
      "model": "finetuned",
      "width": 640,
      "height": 768,
      "clip_scale": 16000,
      "init_scale": 1000,
      "clip_prompts": "The visual style of the image is akin to a retro 8-bit look, with clean lines and flat colors. There is a cartoonish quality to some of the characters and objects, as if they are depictions of vaporwave tropes or influences.",
      "latent_scale": 12,
      "output_steps": 10,
      "latent_prompt": "vaporwave princess",
      "custom_settings": "\\n",
      "init_brightness": 0,
      "latent_negative": "",
      "starting_timestep": 0.9,
      "aesthetic_loss_scale": 400
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-07-26T15:06:02.303289Z",
  "created_at": "2022-07-26T15:01:50.303671Z",
  "data_removed": false,
  "error": null,
  "id": "ziyebr5lqvagdfrkzwqeaoxahy",
  "input": {
    "width": 640,
    "height": 768,
    "clip_scale": 16000,
    "clip_prompts": "The visual style of the image is akin to a retro 8-bit look, with clean lines and flat colors. There is a cartoonish quality to some of the characters and objects, as if they are depictions of vaporwave tropes or influences.",
    "latent_scale": 12,
    "latent_prompt": "vaporwave princess",
    "aesthetic_loss_scale": 400
  },
  "logs": "Sampling images 1/1\n\nData shape for DDIM sampling is (1, 4, 48, 40), eta 1.3\nRunning DDIM Sampling with 119 timesteps\nSampling:   0%|          | 0/1 [00:00<?, ?it/s]\n\nDDIM Sampler:   0%|          | 0/119 [00:00<?, ?it/s]\u001b[A\n\nDDIM Sampler:   1%|          | 1/119 [00:11<22:48, 11.59s/it]\u001b[A\n\nDDIM Sampler:   2%|▏         | 2/119 [00:12<10:03,  5.16s/it]\u001b[A\n\nDDIM Sampler:   3%|▎         | 3/119 [00:12<05:59,  3.10s/it]\u001b[A\n\nDDIM Sampler:   3%|▎         | 4/119 [00:13<04:04,  2.13s/it]\u001b[A\n\nDDIM Sampler:   4%|▍         | 5/119 [00:14<03:00,  1.58s/it]\u001b[A\n\nDDIM Sampler:   5%|▌         | 6/119 [00:14<02:23,  1.27s/it]\u001b[A\n\nDDIM Sampler:   6%|▌         | 7/119 [00:15<01:59,  1.07s/it]\u001b[A\n\nDDIM Sampler:   7%|▋         | 8/119 [00:16<01:43,  1.07it/s]\u001b[A\n\nDDIM Sampler:   8%|▊         | 9/119 [00:16<01:31,  1.21it/s]\u001b[A\n\nDDIM Sampler:   8%|▊         | 10/119 [00:17<01:23,  1.30it/s]\u001b[A\n\nDDIM Sampler:   9%|▉         | 11/119 [00:17<01:18,  1.37it/s]\u001b[A\n\nDDIM Sampler:  10%|█         | 12/119 [00:18<01:15,  1.42it/s]\u001b[A\n\nDDIM Sampler:  11%|█         | 13/119 [00:19<01:12,  1.47it/s]\u001b[A\n\nDDIM Sampler:  12%|█▏        | 14/119 [00:19<01:10,  1.49it/s]\u001b[A\n\nDDIM Sampler:  13%|█▎        | 15/119 [00:20<01:08,  1.52it/s]\u001b[A\n\nDDIM Sampler:  13%|█▎        | 16/119 [00:21<01:06,  1.55it/s]\u001b[A\n\nDDIM Sampler:  14%|█▍        | 17/119 [00:21<01:05,  1.55it/s]\u001b[A\n\nDDIM Sampler:  15%|█▌        | 18/119 [00:22<01:04,  1.56it/s]\u001b[A\n\nDDIM Sampler:  16%|█▌        | 19/119 [00:23<01:03,  1.57it/s]\u001b[A\n\nDDIM Sampler:  17%|█▋        | 20/119 [00:23<01:02,  1.57it/s]\u001b[A\n\nDDIM Sampler:  18%|█▊        | 21/119 [00:24<01:02,  1.57it/s]\u001b[A\n\nDDIM Sampler:  18%|█▊        | 22/119 [00:24<01:02,  1.56it/s]\u001b[A\n\nDDIM Sampler:  19%|█▉        | 23/119 [00:25<01:01,  1.57it/s]\u001b[A\n\nDDIM Sampler:  20%|██        | 24/119 [00:26<01:00,  1.57it/s]\u001b[A\n\nDDIM Sampler:  21%|██        | 25/119 [00:26<00:59,  1.57it/s]\u001b[A\n\nDDIM Sampler:  22%|██▏       | 26/119 [00:27<00:59,  1.57it/s]\u001b[A\n\nDDIM Sampler:  23%|██▎       | 27/119 [00:28<00:58,  1.57it/s]\u001b[A\n\nDDIM Sampler:  24%|██▎       | 28/119 [00:28<00:57,  1.59it/s]\u001b[A\n\nDDIM Sampler:  24%|██▍       | 29/119 [00:29<00:56,  1.60it/s]\u001b[A\n\nDDIM Sampler:  25%|██▌       | 30/119 [00:29<00:55,  1.61it/s]\u001b[A\n\nDDIM Sampler:  26%|██▌       | 31/119 [00:30<00:54,  1.61it/s]\u001b[A\n\nDDIM Sampler:  27%|██▋       | 32/119 [00:31<00:53,  1.62it/s]\u001b[A\n\nDDIM Sampler:  28%|██▊       | 33/119 [00:31<00:52,  1.63it/s]\u001b[A\n\nDDIM Sampler:  29%|██▊       | 34/119 [00:32<00:51,  1.64it/s]\u001b[A\n\nDDIM Sampler:  29%|██▉       | 35/119 [00:33<00:50,  1.65it/s]\u001b[A\n\nDDIM Sampler:  30%|███       | 36/119 [00:33<00:50,  1.65it/s]\u001b[A\n\nDDIM Sampler:  31%|███       | 37/119 [00:34<00:49,  1.65it/s]\u001b[A\n\nDDIM Sampler:  32%|███▏      | 38/119 [00:34<00:49,  1.65it/s]\u001b[A\n\nDDIM Sampler:  33%|███▎      | 39/119 [00:35<00:48,  1.64it/s]\u001b[A\n\nDDIM Sampler:  34%|███▎      | 40/119 [00:36<00:48,  1.64it/s]\u001b[A\n\nDDIM Sampler:  34%|███▍      | 41/119 [00:36<00:47,  1.63it/s]\u001b[A\n\nDDIM Sampler:  35%|███▌      | 42/119 [00:37<00:47,  1.62it/s]\u001b[A\n\nDDIM Sampler:  36%|███▌      | 43/119 [00:37<00:47,  1.59it/s]\u001b[A\n\nDDIM Sampler:  37%|███▋      | 44/119 [00:38<00:47,  1.58it/s]\u001b[A\n\nDDIM Sampler:  38%|███▊      | 45/119 [00:39<00:47,  1.57it/s]\u001b[A\n\nDDIM Sampler:  39%|███▊      | 46/119 [00:39<00:46,  1.57it/s]\u001b[A\n\nDDIM Sampler:  39%|███▉      | 47/119 [00:40<00:45,  1.58it/s]\u001b[A\n\nDDIM Sampler:  40%|████      | 48/119 [00:41<00:44,  1.58it/s]\u001b[A\n\nDDIM Sampler:  41%|████      | 49/119 [00:41<00:44,  1.58it/s]\u001b[A\n\nDDIM Sampler:  42%|████▏     | 50/119 [00:42<00:43,  1.58it/s]\u001b[A\n\nDDIM Sampler:  43%|████▎     | 51/119 [00:43<00:42,  1.58it/s]\u001b[A\n\nDDIM Sampler:  44%|████▎     | 52/119 [00:43<00:42,  1.58it/s]\u001b[A\n\nDDIM Sampler:  45%|████▍     | 53/119 [00:44<00:41,  1.58it/s]\u001b[A\n\nDDIM Sampler:  45%|████▌     | 54/119 [00:44<00:41,  1.57it/s]\u001b[A\n\nDDIM Sampler:  46%|████▌     | 55/119 [00:45<00:40,  1.58it/s]\u001b[A\n\nDDIM Sampler:  47%|████▋     | 56/119 [00:46<00:39,  1.58it/s]\u001b[A\n\nDDIM Sampler:  48%|████▊     | 57/119 [00:46<00:39,  1.58it/s]\u001b[A\n\nDDIM Sampler:  49%|████▊     | 58/119 [00:47<00:38,  1.58it/s]\u001b[A\n\nDDIM Sampler:  50%|████▉     | 59/119 [00:48<00:37,  1.58it/s]\u001b[A\n\nDDIM Sampler:  50%|█████     | 60/119 [00:48<00:37,  1.57it/s]\u001b[A\n\nDDIM Sampler:  51%|█████▏    | 61/119 [00:49<00:36,  1.58it/s]\u001b[A\n\nDDIM Sampler:  52%|█████▏    | 62/119 [00:50<00:36,  1.57it/s]\u001b[A\n\nDDIM Sampler:  53%|█████▎    | 63/119 [00:50<00:36,  1.55it/s]\u001b[A\n\nDDIM Sampler:  54%|█████▍    | 64/119 [00:51<00:35,  1.54it/s]\u001b[A\n\nDDIM Sampler:  55%|█████▍    | 65/119 [00:52<00:35,  1.53it/s]\u001b[A\n\nDDIM Sampler:  55%|█████▌    | 66/119 [00:52<00:34,  1.53it/s]\u001b[A\n\nDDIM Sampler:  56%|█████▋    | 67/119 [00:53<00:34,  1.52it/s]\u001b[A\n\nDDIM Sampler:  57%|█████▋    | 68/119 [00:54<00:33,  1.52it/s]\u001b[A\n\nDDIM Sampler:  58%|█████▊    | 69/119 [00:54<00:33,  1.51it/s]\u001b[A\n\nDDIM Sampler:  59%|█████▉    | 70/119 [00:55<00:32,  1.51it/s]\u001b[A\n\nDDIM Sampler:  60%|█████▉    | 71/119 [00:55<00:31,  1.51it/s]\u001b[A\n\nDDIM Sampler:  61%|██████    | 72/119 [00:56<00:31,  1.51it/s]\u001b[A\n\nDDIM Sampler:  61%|██████▏   | 73/119 [00:57<00:30,  1.51it/s]\u001b[A\n\nDDIM Sampler:  62%|██████▏   | 74/119 [00:57<00:29,  1.51it/s]\u001b[A\n\nDDIM Sampler:  63%|██████▎   | 75/119 [00:58<00:29,  1.51it/s]\u001b[A\n\nDDIM Sampler:  64%|██████▍   | 76/119 [00:59<00:28,  1.51it/s]\u001b[A\n\nDDIM Sampler:  65%|██████▍   | 77/119 [00:59<00:27,  1.51it/s]\u001b[A\n\nDDIM Sampler:  66%|██████▌   | 78/119 [01:00<00:27,  1.51it/s]\u001b[A\n\nDDIM Sampler:  66%|██████▋   | 79/119 [01:01<00:26,  1.51it/s]\u001b[A\n\nDDIM Sampler:  67%|██████▋   | 80/119 [01:01<00:25,  1.50it/s]\u001b[A\n\nDDIM Sampler:  68%|██████▊   | 81/119 [01:02<00:25,  1.50it/s]\u001b[A\n\nDDIM Sampler:  69%|██████▉   | 82/119 [01:03<00:24,  1.50it/s]\u001b[A\n\nDDIM Sampler:  70%|██████▉   | 83/119 [01:03<00:23,  1.50it/s]\u001b[A\n\nDDIM Sampler:  71%|███████   | 84/119 [01:04<00:23,  1.50it/s]\u001b[A\n\nDDIM Sampler:  71%|███████▏  | 85/119 [01:05<00:22,  1.50it/s]\u001b[A\n\nDDIM Sampler:  72%|███████▏  | 86/119 [01:05<00:22,  1.49it/s]\u001b[A\n\nDDIM Sampler:  73%|███████▎  | 87/119 [01:06<00:21,  1.49it/s]\u001b[A\n\nDDIM Sampler:  74%|███████▍  | 88/119 [01:07<00:20,  1.49it/s]\u001b[A\n\nDDIM Sampler:  75%|███████▍  | 89/119 [01:07<00:20,  1.50it/s]\u001b[A\n\nDDIM Sampler:  76%|███████▌  | 90/119 [01:08<00:19,  1.50it/s]\u001b[A\n\nDDIM Sampler:  76%|███████▋  | 91/119 [01:09<00:18,  1.49it/s]\u001b[A\n\nDDIM Sampler:  77%|███████▋  | 92/119 [01:10<00:18,  1.49it/s]\u001b[A\n\nDDIM Sampler:  78%|███████▊  | 93/119 [01:10<00:17,  1.49it/s]\u001b[A\n\nDDIM Sampler:  79%|███████▉  | 94/119 [01:11<00:16,  1.49it/s]\u001b[A\n\nDDIM Sampler:  80%|███████▉  | 95/119 [01:12<00:16,  1.49it/s]\u001b[A\n\nDDIM Sampler:  81%|████████  | 96/119 [01:12<00:15,  1.49it/s]\u001b[A\n\nDDIM Sampler:  82%|████████▏ | 97/119 [01:13<00:14,  1.48it/s]\u001b[A\n\nDDIM Sampler:  82%|████████▏ | 98/119 [01:14<00:14,  1.49it/s]\u001b[A\n\nDDIM Sampler:  83%|████████▎ | 99/119 [01:14<00:13,  1.48it/s]\u001b[A\n\nDDIM Sampler:  84%|████████▍ | 100/119 [01:15<00:12,  1.49it/s]\u001b[A\n\nDDIM Sampler:  85%|████████▍ | 101/119 [01:16<00:12,  1.49it/s]\u001b[A\n\nDDIM Sampler:  86%|████████▌ | 102/119 [01:16<00:11,  1.50it/s]\u001b[A\n\nDDIM Sampler:  87%|████████▋ | 103/119 [01:17<00:10,  1.50it/s]\u001b[A\n\nDDIM Sampler:  87%|████████▋ | 104/119 [01:18<00:10,  1.49it/s]\u001b[A\n\nDDIM Sampler:  88%|████████▊ | 105/119 [01:18<00:09,  1.50it/s]\u001b[A\n\nDDIM Sampler:  89%|████████▉ | 106/119 [01:19<00:08,  1.51it/s]\u001b[A\n\nDDIM Sampler:  90%|████████▉ | 107/119 [01:20<00:07,  1.51it/s]\u001b[A\n\nDDIM Sampler:  91%|█████████ | 108/119 [01:20<00:07,  1.51it/s]\u001b[A\n\nDDIM Sampler:  92%|█████████▏| 109/119 [01:21<00:06,  1.51it/s]\u001b[A\n\nDDIM Sampler:  92%|█████████▏| 110/119 [01:22<00:05,  1.51it/s]\u001b[A\n\nDDIM Sampler:  93%|█████████▎| 111/119 [01:22<00:05,  1.51it/s]\u001b[A\n\nDDIM Sampler:  94%|█████████▍| 112/119 [01:23<00:04,  1.50it/s]\u001b[A\n\nDDIM Sampler:  95%|█████████▍| 113/119 [01:24<00:03,  1.51it/s]\u001b[A\n\nDDIM Sampler:  96%|█████████▌| 114/119 [01:24<00:03,  1.51it/s]\u001b[A\n\nDDIM Sampler:  97%|█████████▋| 115/119 [01:25<00:02,  1.51it/s]\u001b[A\n\nDDIM Sampler:  97%|█████████▋| 116/119 [01:25<00:01,  1.51it/s]\u001b[A\n\nDDIM Sampler:  98%|█████████▊| 117/119 [01:26<00:01,  1.51it/s]\u001b[A\n\nDDIM Sampler:  99%|█████████▉| 118/119 [01:27<00:00,  1.51it/s]\u001b[A\n\nDDIM Sampler: 100%|██████████| 119/119 [01:27<00:00,  1.51it/s]\u001b[A\nDDIM Sampler: 100%|██████████| 119/119 [01:27<00:00,  1.35it/s]\npython inference_gfpgan.py -i /tmp/tmprqvpx06_gfpgan/temp_1658847856.png -o results -v 1.3 -s 2\n\nhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n\t- Avoid using `tokenizers` before the fork if possible\n\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nDownloading: \"https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth\" to /root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/realesrgan/weights/RealESRGAN_x2plus.pth\n\n\n  0%|          | 0.00/64.0M [00:00<?, ?B/s]\n 16%|█▌        | 10.1M/64.0M [00:00<00:00, 106MB/s]\n 58%|█████▊    | 37.1M/64.0M [00:00<00:00, 210MB/s]\n100%|█████████▉| 63.8M/64.0M [00:00<00:00, 242MB/s]\n100%|██████████| 64.0M/64.0M [00:00<00:00, 223MB/s]\nProcessing temp_1658847856.png ...\n\tTile 1/1\nResults are in the [results] folder.\nData shape for DDIM sampling is (1, 4, 48, 40), eta 1.1\nRunning DDIM Sampling with 74 timesteps\n\n\nDDIM Sampler:   0%|          | 0/74 [00:00<?, ?it/s]\u001b[A\n\nDDIM Sampler:   1%|▏         | 1/74 [00:09<11:30,  9.46s/it]\u001b[A\n\nDDIM Sampler:   3%|▎         | 2/74 [00:10<05:25,  4.53s/it]\u001b[A\n\nDDIM Sampler:   4%|▍         | 3/74 [00:11<03:29,  2.95s/it]\u001b[A\n\nDDIM Sampler:   5%|▌         | 4/74 [00:12<02:34,  2.21s/it]\u001b[A\n\nDDIM Sampler:   7%|▋         | 5/74 [00:13<02:04,  1.80s/it]\u001b[A\n\nDDIM Sampler:   8%|▊         | 6/74 [00:14<01:45,  1.55s/it]\u001b[A\n\nDDIM Sampler:   9%|▉         | 7/74 [00:15<01:33,  1.40s/it]\u001b[A\n\nDDIM Sampler:  11%|█         | 8/74 [00:16<01:25,  1.30s/it]\u001b[A\n\nDDIM Sampler:  12%|█▏        | 9/74 [00:18<01:19,  1.23s/it]\u001b[A\n\nDDIM Sampler:  14%|█▎        | 10/74 [00:19<01:15,  1.18s/it]\u001b[A\n\nDDIM Sampler:  15%|█▍        | 11/74 [00:20<01:12,  1.14s/it]\u001b[A\n\nDDIM Sampler:  16%|█▌        | 12/74 [00:21<01:09,  1.12s/it]\u001b[A\n\nDDIM Sampler:  18%|█▊        | 13/74 [00:22<01:07,  1.11s/it]\u001b[A\n\nDDIM Sampler:  19%|█▉        | 14/74 [00:23<01:05,  1.10s/it]\u001b[A\n\nDDIM Sampler:  20%|██        | 15/74 [00:24<01:04,  1.09s/it]\u001b[A\n\nDDIM Sampler:  22%|██▏       | 16/74 [00:25<01:02,  1.08s/it]\u001b[A\n\nDDIM Sampler:  23%|██▎       | 17/74 [00:26<01:01,  1.08s/it]\u001b[A\n\nDDIM Sampler:  24%|██▍       | 18/74 [00:27<01:00,  1.08s/it]\u001b[A\n\nDDIM Sampler:  26%|██▌       | 19/74 [00:28<00:59,  1.08s/it]\u001b[A\n\nDDIM Sampler:  27%|██▋       | 20/74 [00:29<00:58,  1.08s/it]\u001b[A\n\nDDIM Sampler:  28%|██▊       | 21/74 [00:30<00:56,  1.07s/it]\u001b[A\n\nDDIM Sampler:  30%|██▉       | 22/74 [00:31<00:56,  1.08s/it]\u001b[A\n\nDDIM Sampler:  31%|███       | 23/74 [00:33<00:54,  1.08s/it]\u001b[A\n\nDDIM Sampler:  32%|███▏      | 24/74 [00:34<00:53,  1.07s/it]\u001b[A\n\nDDIM Sampler:  34%|███▍      | 25/74 [00:35<00:52,  1.07s/it]\u001b[A\n\nDDIM Sampler:  35%|███▌      | 26/74 [00:36<00:51,  1.07s/it]\u001b[A\n\nDDIM Sampler:  36%|███▋      | 27/74 [00:37<00:50,  1.07s/it]\u001b[A\n\nDDIM Sampler:  38%|███▊      | 28/74 [00:38<00:49,  1.07s/it]\u001b[A\n\nDDIM Sampler:  39%|███▉      | 29/74 [00:39<00:48,  1.07s/it]\u001b[A\n\nDDIM Sampler:  41%|████      | 30/74 [00:40<00:47,  1.07s/it]\u001b[A\n\nDDIM Sampler:  42%|████▏     | 31/74 [00:41<00:46,  1.07s/it]\u001b[A\n\nDDIM Sampler:  43%|████▎     | 32/74 [00:42<00:45,  1.08s/it]\u001b[A\n\nDDIM Sampler:  45%|████▍     | 33/74 [00:43<00:44,  1.08s/it]\u001b[A\n\nDDIM Sampler:  46%|████▌     | 34/74 [00:44<00:42,  1.07s/it]\u001b[A\n\nDDIM Sampler:  47%|████▋     | 35/74 [00:45<00:41,  1.08s/it]\u001b[A\n\nDDIM Sampler:  49%|████▊     | 36/74 [00:46<00:40,  1.07s/it]\u001b[A\n\nDDIM Sampler:  50%|█████     | 37/74 [00:48<00:39,  1.08s/it]\u001b[A\n\nDDIM Sampler:  51%|█████▏    | 38/74 [00:49<00:38,  1.08s/it]\u001b[A\n\nDDIM Sampler:  53%|█████▎    | 39/74 [00:50<00:37,  1.08s/it]\u001b[A\n\nDDIM Sampler:  54%|█████▍    | 40/74 [00:51<00:36,  1.08s/it]\u001b[A\n\nDDIM Sampler:  55%|█████▌    | 41/74 [00:52<00:35,  1.09s/it]\u001b[A\n\nDDIM Sampler:  57%|█████▋    | 42/74 [00:53<00:34,  1.09s/it]\u001b[A\n\nDDIM Sampler:  58%|█████▊    | 43/74 [00:54<00:33,  1.09s/it]\u001b[A\n\nDDIM Sampler:  59%|█████▉    | 44/74 [00:55<00:32,  1.09s/it]\u001b[A\n\nDDIM Sampler:  61%|██████    | 45/74 [00:56<00:31,  1.09s/it]\u001b[A\n\nDDIM Sampler:  62%|██████▏   | 46/74 [00:57<00:30,  1.09s/it]\u001b[A\n\nDDIM Sampler:  64%|██████▎   | 47/74 [00:58<00:29,  1.09s/it]\u001b[A\n\nDDIM Sampler:  65%|██████▍   | 48/74 [01:00<00:28,  1.10s/it]\u001b[A\n\nDDIM Sampler:  66%|██████▌   | 49/74 [01:01<00:27,  1.10s/it]\u001b[A\n\nDDIM Sampler:  68%|██████▊   | 50/74 [01:02<00:26,  1.10s/it]\u001b[A\n\nDDIM Sampler:  69%|██████▉   | 51/74 [01:03<00:25,  1.10s/it]\u001b[A\n\nDDIM Sampler:  70%|███████   | 52/74 [01:04<00:24,  1.10s/it]\u001b[A\n\nDDIM Sampler:  72%|███████▏  | 53/74 [01:05<00:23,  1.10s/it]\u001b[A\n\nDDIM Sampler:  73%|███████▎  | 54/74 [01:06<00:22,  1.10s/it]\u001b[A\n\nDDIM Sampler:  74%|███████▍  | 55/74 [01:07<00:20,  1.10s/it]\u001b[A\n\nDDIM Sampler:  76%|███████▌  | 56/74 [01:08<00:19,  1.10s/it]\u001b[A\n\nDDIM Sampler:  77%|███████▋  | 57/74 [01:09<00:18,  1.10s/it]\u001b[A\n\nDDIM Sampler:  78%|███████▊  | 58/74 [01:11<00:17,  1.10s/it]\u001b[A\n\nDDIM Sampler:  80%|███████▉  | 59/74 [01:12<00:16,  1.10s/it]\u001b[A\n\nDDIM Sampler:  81%|████████  | 60/74 [01:13<00:15,  1.10s/it]\u001b[A\n\nDDIM Sampler:  82%|████████▏ | 61/74 [01:14<00:14,  1.10s/it]\u001b[A\n\nDDIM Sampler:  84%|████████▍ | 62/74 [01:15<00:13,  1.10s/it]\u001b[A\n\nDDIM Sampler:  85%|████████▌ | 63/74 [01:16<00:12,  1.10s/it]\u001b[A\n\nDDIM Sampler:  86%|████████▋ | 64/74 [01:17<00:11,  1.10s/it]\u001b[A\n\nDDIM Sampler:  88%|████████▊ | 65/74 [01:18<00:09,  1.10s/it]\u001b[A\n\nDDIM Sampler:  89%|████████▉ | 66/74 [01:19<00:08,  1.10s/it]\u001b[A\n\nDDIM Sampler:  91%|█████████ | 67/74 [01:21<00:07,  1.10s/it]\u001b[A\n\nDDIM Sampler:  92%|█████████▏| 68/74 [01:22<00:06,  1.10s/it]\u001b[A\n\nDDIM Sampler:  93%|█████████▎| 69/74 [01:23<00:05,  1.10s/it]\u001b[A\n\nDDIM Sampler:  95%|█████████▍| 70/74 [01:24<00:04,  1.10s/it]\u001b[A\n\nDDIM Sampler:  96%|█████████▌| 71/74 [01:25<00:03,  1.11s/it]\u001b[A\n\nDDIM Sampler:  97%|█████████▋| 72/74 [01:26<00:02,  1.11s/it]\u001b[A\n\nDDIM Sampler:  99%|█████████▊| 73/74 [01:27<00:01,  1.11s/it]\u001b[A\n\nDDIM Sampler: 100%|██████████| 74/74 [01:28<00:00,  1.11s/it]\u001b[A\nDDIM Sampler: 100%|██████████| 74/74 [01:28<00:00,  1.20s/it]\n\nSampling: 100%|██████████| 1/1 [03:14<00:00, 194.40s/it]\nSampling: 100%|██████████| 1/1 [03:14<00:00, 194.40s/it]",
  "metrics": {
    "predict_time": 195.271336,
    "total_time": 251.999618
  },
  "output": [
    "https://replicate.delivery/mgxm/05c51477-135f-4bf5-8347-71ef182e444f/0.png",
    "https://replicate.delivery/mgxm/44c843b4-c91a-43a2-a34a-82413ae01556/10.png",
    "https://replicate.delivery/mgxm/465b41cb-ace8-4f2b-ac33-b18205ad8b47/20.png",
    "https://replicate.delivery/mgxm/2e55d006-9e01-4f96-a55b-7b8f7a51a405/30.png",
    "https://replicate.delivery/mgxm/ec799994-5cf9-45a4-a5da-0dc8492dbc21/40.png",
    "https://replicate.delivery/mgxm/892673a8-30c1-4de3-81d2-817d43c23c85/50.png",
    "https://replicate.delivery/mgxm/7a9a13c5-f575-445f-a967-8e7d93805ea9/60.png",
    "https://replicate.delivery/mgxm/83afa9a1-df65-4306-b9f3-e0060b507e50/70.png",
    "https://replicate.delivery/mgxm/5475a2e9-f8df-4575-b3d9-27d2845c1767/80.png",
    "https://replicate.delivery/mgxm/e48ab18e-7a1e-42ec-baa4-405e5ca13a18/90.png",
    "https://replicate.delivery/mgxm/390bd57f-94e2-4070-97cb-1d0371878cc8/100.png",
    "https://replicate.delivery/mgxm/791567d3-e994-45ab-afdc-56aa8c73e601/110.png",
    "https://replicate.delivery/mgxm/5a8297cd-2da5-463d-8e30-a36dc3d8b97a/120.png",
    "https://replicate.delivery/mgxm/9326daeb-8302-4d88-872d-3a12e4c82c7a/130.png",
    "https://replicate.delivery/mgxm/b995b6b5-e030-4c1b-906f-786d6379b699/140.png",
    "https://replicate.delivery/mgxm/c75d995c-3234-4281-b9bd-67efac64f484/150.png",
    "https://replicate.delivery/mgxm/4de3c739-de10-4c99-9d28-eec0c5cffc0a/160.png",
    "https://replicate.delivery/mgxm/6fbde938-897a-4d32-9390-0f05873de607/170.png",
    "https://replicate.delivery/mgxm/2ce0cb66-ff04-4c00-8090-b991a0342059/180.png",
    "https://replicate.delivery/mgxm/5d538fbb-a119-4a13-9d4f-ebde6bee3ed3/190.png",
    "https://replicate.delivery/mgxm/b95b22ef-54d0-4248-94ef-268635aac529/1658847957.png"
  ],
  "started_at": "2022-07-26T15:02:47.031953Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ziyebr5lqvagdfrkzwqeaoxahy",
    "cancel": "https://api.replicate.com/v1/predictions/ziyebr5lqvagdfrkzwqeaoxahy/cancel"
  },
  "version": "73bfb38ec5c159e3dcbe2dc69d2db245c1cc07a94377829c49dded3a7ddb7e3a"
}

Generated in

3 minutes 15 seconds

Tweak itReport

Sampling images 1/1

Data shape for DDIM sampling is (1, 4, 48, 40), eta 1.3
Running DDIM Sampling with 119 timesteps
Sampling:   0%|          | 0/1 [00:00<?, ?it/s]

DDIM Sampler:   0%|          | 0/119 [00:00<?, ?it/s]

DDIM Sampler:   1%|          | 1/119 [00:11<22:48, 11.59s/it]

DDIM Sampler:   2%|▏         | 2/119 [00:12<10:03,  5.16s/it]

DDIM Sampler:   3%|▎         | 3/119 [00:12<05:59,  3.10s/it]

DDIM Sampler:   3%|▎         | 4/119 [00:13<04:04,  2.13s/it]

DDIM Sampler:   4%|▍         | 5/119 [00:14<03:00,  1.58s/it]

DDIM Sampler:   5%|▌         | 6/119 [00:14<02:23,  1.27s/it]

DDIM Sampler:   6%|▌         | 7/119 [00:15<01:59,  1.07s/it]

DDIM Sampler:   7%|▋         | 8/119 [00:16<01:43,  1.07it/s]

DDIM Sampler:   8%|▊         | 9/119 [00:16<01:31,  1.21it/s]

DDIM Sampler:   8%|▊         | 10/119 [00:17<01:23,  1.30it/s]

DDIM Sampler:   9%|▉         | 11/119 [00:17<01:18,  1.37it/s]

DDIM Sampler:  10%|█         | 12/119 [00:18<01:15,  1.42it/s]

DDIM Sampler:  11%|█         | 13/119 [00:19<01:12,  1.47it/s]

DDIM Sampler:  12%|█▏        | 14/119 [00:19<01:10,  1.49it/s]

DDIM Sampler:  13%|█▎        | 15/119 [00:20<01:08,  1.52it/s]

DDIM Sampler:  13%|█▎        | 16/119 [00:21<01:06,  1.55it/s]

DDIM Sampler:  14%|█▍        | 17/119 [00:21<01:05,  1.55it/s]

DDIM Sampler:  15%|█▌        | 18/119 [00:22<01:04,  1.56it/s]

DDIM Sampler:  16%|█▌        | 19/119 [00:23<01:03,  1.57it/s]

DDIM Sampler:  17%|█▋        | 20/119 [00:23<01:02,  1.57it/s]

DDIM Sampler:  18%|█▊        | 21/119 [00:24<01:02,  1.57it/s]

DDIM Sampler:  18%|█▊        | 22/119 [00:24<01:02,  1.56it/s]

DDIM Sampler:  19%|█▉        | 23/119 [00:25<01:01,  1.57it/s]

DDIM Sampler:  20%|██        | 24/119 [00:26<01:00,  1.57it/s]

DDIM Sampler:  21%|██        | 25/119 [00:26<00:59,  1.57it/s]

DDIM Sampler:  22%|██▏       | 26/119 [00:27<00:59,  1.57it/s]

DDIM Sampler:  23%|██▎       | 27/119 [00:28<00:58,  1.57it/s]

DDIM Sampler:  24%|██▎       | 28/119 [00:28<00:57,  1.59it/s]

DDIM Sampler:  24%|██▍       | 29/119 [00:29<00:56,  1.60it/s]

DDIM Sampler:  25%|██▌       | 30/119 [00:29<00:55,  1.61it/s]

DDIM Sampler:  26%|██▌       | 31/119 [00:30<00:54,  1.61it/s]

DDIM Sampler:  27%|██▋       | 32/119 [00:31<00:53,  1.62it/s]

DDIM Sampler:  28%|██▊       | 33/119 [00:31<00:52,  1.63it/s]

DDIM Sampler:  29%|██▊       | 34/119 [00:32<00:51,  1.64it/s]

DDIM Sampler:  29%|██▉       | 35/119 [00:33<00:50,  1.65it/s]

DDIM Sampler:  30%|███       | 36/119 [00:33<00:50,  1.65it/s]

DDIM Sampler:  31%|███       | 37/119 [00:34<00:49,  1.65it/s]

DDIM Sampler:  32%|███▏      | 38/119 [00:34<00:49,  1.65it/s]

DDIM Sampler:  33%|███▎      | 39/119 [00:35<00:48,  1.64it/s]

DDIM Sampler:  34%|███▎      | 40/119 [00:36<00:48,  1.64it/s]

DDIM Sampler:  34%|███▍      | 41/119 [00:36<00:47,  1.63it/s]

DDIM Sampler:  35%|███▌      | 42/119 [00:37<00:47,  1.62it/s]

DDIM Sampler:  36%|███▌      | 43/119 [00:37<00:47,  1.59it/s]

DDIM Sampler:  37%|███▋      | 44/119 [00:38<00:47,  1.58it/s]

DDIM Sampler:  38%|███▊      | 45/119 [00:39<00:47,  1.57it/s]

DDIM Sampler:  39%|███▊      | 46/119 [00:39<00:46,  1.57it/s]

DDIM Sampler:  39%|███▉      | 47/119 [00:40<00:45,  1.58it/s]

DDIM Sampler:  40%|████      | 48/119 [00:41<00:44,  1.58it/s]

DDIM Sampler:  41%|████      | 49/119 [00:41<00:44,  1.58it/s]

DDIM Sampler:  42%|████▏     | 50/119 [00:42<00:43,  1.58it/s]

DDIM Sampler:  43%|████▎     | 51/119 [00:43<00:42,  1.58it/s]

DDIM Sampler:  44%|████▎     | 52/119 [00:43<00:42,  1.58it/s]

DDIM Sampler:  45%|████▍     | 53/119 [00:44<00:41,  1.58it/s]

DDIM Sampler:  45%|████▌     | 54/119 [00:44<00:41,  1.57it/s]

DDIM Sampler:  46%|████▌     | 55/119 [00:45<00:40,  1.58it/s]

DDIM Sampler:  47%|████▋     | 56/119 [00:46<00:39,  1.58it/s]

DDIM Sampler:  48%|████▊     | 57/119 [00:46<00:39,  1.58it/s]

DDIM Sampler:  49%|████▊     | 58/119 [00:47<00:38,  1.58it/s]

DDIM Sampler:  50%|████▉     | 59/119 [00:48<00:37,  1.58it/s]

DDIM Sampler:  50%|█████     | 60/119 [00:48<00:37,  1.57it/s]

DDIM Sampler:  51%|█████▏    | 61/119 [00:49<00:36,  1.58it/s]

DDIM Sampler:  52%|█████▏    | 62/119 [00:50<00:36,  1.57it/s]

DDIM Sampler:  53%|█████▎    | 63/119 [00:50<00:36,  1.55it/s]

DDIM Sampler:  54%|█████▍    | 64/119 [00:51<00:35,  1.54it/s]

DDIM Sampler:  55%|█████▍    | 65/119 [00:52<00:35,  1.53it/s]

DDIM Sampler:  55%|█████▌    | 66/119 [00:52<00:34,  1.53it/s]

DDIM Sampler:  56%|█████▋    | 67/119 [00:53<00:34,  1.52it/s]

DDIM Sampler:  57%|█████▋    | 68/119 [00:54<00:33,  1.52it/s]

DDIM Sampler:  58%|█████▊    | 69/119 [00:54<00:33,  1.51it/s]

DDIM Sampler:  59%|█████▉    | 70/119 [00:55<00:32,  1.51it/s]

DDIM Sampler:  60%|█████▉    | 71/119 [00:55<00:31,  1.51it/s]

DDIM Sampler:  61%|██████    | 72/119 [00:56<00:31,  1.51it/s]

DDIM Sampler:  61%|██████▏   | 73/119 [00:57<00:30,  1.51it/s]

DDIM Sampler:  62%|██████▏   | 74/119 [00:57<00:29,  1.51it/s]

DDIM Sampler:  63%|██████▎   | 75/119 [00:58<00:29,  1.51it/s]

DDIM Sampler:  64%|██████▍   | 76/119 [00:59<00:28,  1.51it/s]

DDIM Sampler:  65%|██████▍   | 77/119 [00:59<00:27,  1.51it/s]

DDIM Sampler:  66%|██████▌   | 78/119 [01:00<00:27,  1.51it/s]

DDIM Sampler:  66%|██████▋   | 79/119 [01:01<00:26,  1.51it/s]

DDIM Sampler:  67%|██████▋   | 80/119 [01:01<00:25,  1.50it/s]

DDIM Sampler:  68%|██████▊   | 81/119 [01:02<00:25,  1.50it/s]

DDIM Sampler:  69%|██████▉   | 82/119 [01:03<00:24,  1.50it/s]

DDIM Sampler:  70%|██████▉   | 83/119 [01:03<00:23,  1.50it/s]

DDIM Sampler:  71%|███████   | 84/119 [01:04<00:23,  1.50it/s]

DDIM Sampler:  71%|███████▏  | 85/119 [01:05<00:22,  1.50it/s]

DDIM Sampler:  72%|███████▏  | 86/119 [01:05<00:22,  1.49it/s]

DDIM Sampler:  73%|███████▎  | 87/119 [01:06<00:21,  1.49it/s]

DDIM Sampler:  74%|███████▍  | 88/119 [01:07<00:20,  1.49it/s]

DDIM Sampler:  75%|███████▍  | 89/119 [01:07<00:20,  1.50it/s]

DDIM Sampler:  76%|███████▌  | 90/119 [01:08<00:19,  1.50it/s]

DDIM Sampler:  76%|███████▋  | 91/119 [01:09<00:18,  1.49it/s]

DDIM Sampler:  77%|███████▋  | 92/119 [01:10<00:18,  1.49it/s]

DDIM Sampler:  78%|███████▊  | 93/119 [01:10<00:17,  1.49it/s]

DDIM Sampler:  79%|███████▉  | 94/119 [01:11<00:16,  1.49it/s]

DDIM Sampler:  80%|███████▉  | 95/119 [01:12<00:16,  1.49it/s]

DDIM Sampler:  81%|████████  | 96/119 [01:12<00:15,  1.49it/s]

DDIM Sampler:  82%|████████▏ | 97/119 [01:13<00:14,  1.48it/s]

DDIM Sampler:  82%|████████▏ | 98/119 [01:14<00:14,  1.49it/s]

DDIM Sampler:  83%|████████▎ | 99/119 [01:14<00:13,  1.48it/s]

DDIM Sampler:  84%|████████▍ | 100/119 [01:15<00:12,  1.49it/s]

DDIM Sampler:  85%|████████▍ | 101/119 [01:16<00:12,  1.49it/s]

DDIM Sampler:  86%|████████▌ | 102/119 [01:16<00:11,  1.50it/s]

DDIM Sampler:  87%|████████▋ | 103/119 [01:17<00:10,  1.50it/s]

DDIM Sampler:  87%|████████▋ | 104/119 [01:18<00:10,  1.49it/s]

DDIM Sampler:  88%|████████▊ | 105/119 [01:18<00:09,  1.50it/s]

DDIM Sampler:  89%|████████▉ | 106/119 [01:19<00:08,  1.51it/s]

DDIM Sampler:  90%|████████▉ | 107/119 [01:20<00:07,  1.51it/s]

DDIM Sampler:  91%|█████████ | 108/119 [01:20<00:07,  1.51it/s]

DDIM Sampler:  92%|█████████▏| 109/119 [01:21<00:06,  1.51it/s]

DDIM Sampler:  92%|█████████▏| 110/119 [01:22<00:05,  1.51it/s]

DDIM Sampler:  93%|█████████▎| 111/119 [01:22<00:05,  1.51it/s]

DDIM Sampler:  94%|█████████▍| 112/119 [01:23<00:04,  1.50it/s]

DDIM Sampler:  95%|█████████▍| 113/119 [01:24<00:03,  1.51it/s]

DDIM Sampler:  96%|█████████▌| 114/119 [01:24<00:03,  1.51it/s]

DDIM Sampler:  97%|█████████▋| 115/119 [01:25<00:02,  1.51it/s]

DDIM Sampler:  97%|█████████▋| 116/119 [01:25<00:01,  1.51it/s]

DDIM Sampler:  98%|█████████▊| 117/119 [01:26<00:01,  1.51it/s]

DDIM Sampler:  99%|█████████▉| 118/119 [01:27<00:00,  1.51it/s]

DDIM Sampler: 100%|██████████| 119/119 [01:27<00:00,  1.51it/s]
DDIM Sampler: 100%|██████████| 119/119 [01:27<00:00,  1.35it/s]
python inference_gfpgan.py -i /tmp/tmprqvpx06_gfpgan/temp_1658847856.png -o results -v 1.3 -s 2

huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
Downloading: "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth" to /root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/realesrgan/weights/RealESRGAN_x2plus.pth


  0%|          | 0.00/64.0M [00:00<?, ?B/s]
 16%|█▌        | 10.1M/64.0M [00:00<00:00, 106MB/s]
 58%|█████▊    | 37.1M/64.0M [00:00<00:00, 210MB/s]
100%|█████████▉| 63.8M/64.0M [00:00<00:00, 242MB/s]
100%|██████████| 64.0M/64.0M [00:00<00:00, 223MB/s]
Processing temp_1658847856.png ...
	Tile 1/1
Results are in the [results] folder.
Data shape for DDIM sampling is (1, 4, 48, 40), eta 1.1
Running DDIM Sampling with 74 timesteps


DDIM Sampler:   0%|          | 0/74 [00:00<?, ?it/s]

DDIM Sampler:   1%|▏         | 1/74 [00:09<11:30,  9.46s/it]

DDIM Sampler:   3%|▎         | 2/74 [00:10<05:25,  4.53s/it]

DDIM Sampler:   4%|▍         | 3/74 [00:11<03:29,  2.95s/it]

DDIM Sampler:   5%|▌         | 4/74 [00:12<02:34,  2.21s/it]

DDIM Sampler:   7%|▋         | 5/74 [00:13<02:04,  1.80s/it]

DDIM Sampler:   8%|▊         | 6/74 [00:14<01:45,  1.55s/it]

DDIM Sampler:   9%|▉         | 7/74 [00:15<01:33,  1.40s/it]

DDIM Sampler:  11%|█         | 8/74 [00:16<01:25,  1.30s/it]

DDIM Sampler:  12%|█▏        | 9/74 [00:18<01:19,  1.23s/it]

DDIM Sampler:  14%|█▎        | 10/74 [00:19<01:15,  1.18s/it]

DDIM Sampler:  15%|█▍        | 11/74 [00:20<01:12,  1.14s/it]

DDIM Sampler:  16%|█▌        | 12/74 [00:21<01:09,  1.12s/it]

DDIM Sampler:  18%|█▊        | 13/74 [00:22<01:07,  1.11s/it]

DDIM Sampler:  19%|█▉        | 14/74 [00:23<01:05,  1.10s/it]

DDIM Sampler:  20%|██        | 15/74 [00:24<01:04,  1.09s/it]

DDIM Sampler:  22%|██▏       | 16/74 [00:25<01:02,  1.08s/it]

DDIM Sampler:  23%|██▎       | 17/74 [00:26<01:01,  1.08s/it]

DDIM Sampler:  24%|██▍       | 18/74 [00:27<01:00,  1.08s/it]

DDIM Sampler:  26%|██▌       | 19/74 [00:28<00:59,  1.08s/it]

DDIM Sampler:  27%|██▋       | 20/74 [00:29<00:58,  1.08s/it]

DDIM Sampler:  28%|██▊       | 21/74 [00:30<00:56,  1.07s/it]

DDIM Sampler:  30%|██▉       | 22/74 [00:31<00:56,  1.08s/it]

DDIM Sampler:  31%|███       | 23/74 [00:33<00:54,  1.08s/it]

DDIM Sampler:  32%|███▏      | 24/74 [00:34<00:53,  1.07s/it]

DDIM Sampler:  34%|███▍      | 25/74 [00:35<00:52,  1.07s/it]

DDIM Sampler:  35%|███▌      | 26/74 [00:36<00:51,  1.07s/it]

DDIM Sampler:  36%|███▋      | 27/74 [00:37<00:50,  1.07s/it]

DDIM Sampler:  38%|███▊      | 28/74 [00:38<00:49,  1.07s/it]

DDIM Sampler:  39%|███▉      | 29/74 [00:39<00:48,  1.07s/it]

DDIM Sampler:  41%|████      | 30/74 [00:40<00:47,  1.07s/it]

DDIM Sampler:  42%|████▏     | 31/74 [00:41<00:46,  1.07s/it]

DDIM Sampler:  43%|████▎     | 32/74 [00:42<00:45,  1.08s/it]

DDIM Sampler:  45%|████▍     | 33/74 [00:43<00:44,  1.08s/it]

DDIM Sampler:  46%|████▌     | 34/74 [00:44<00:42,  1.07s/it]

DDIM Sampler:  47%|████▋     | 35/74 [00:45<00:41,  1.08s/it]

DDIM Sampler:  49%|████▊     | 36/74 [00:46<00:40,  1.07s/it]

DDIM Sampler:  50%|█████     | 37/74 [00:48<00:39,  1.08s/it]

DDIM Sampler:  51%|█████▏    | 38/74 [00:49<00:38,  1.08s/it]

DDIM Sampler:  53%|█████▎    | 39/74 [00:50<00:37,  1.08s/it]

DDIM Sampler:  54%|█████▍    | 40/74 [00:51<00:36,  1.08s/it]

DDIM Sampler:  55%|█████▌    | 41/74 [00:52<00:35,  1.09s/it]

DDIM Sampler:  57%|█████▋    | 42/74 [00:53<00:34,  1.09s/it]

DDIM Sampler:  58%|█████▊    | 43/74 [00:54<00:33,  1.09s/it]

DDIM Sampler:  59%|█████▉    | 44/74 [00:55<00:32,  1.09s/it]

DDIM Sampler:  61%|██████    | 45/74 [00:56<00:31,  1.09s/it]

DDIM Sampler:  62%|██████▏   | 46/74 [00:57<00:30,  1.09s/it]

DDIM Sampler:  64%|██████▎   | 47/74 [00:58<00:29,  1.09s/it]

DDIM Sampler:  65%|██████▍   | 48/74 [01:00<00:28,  1.10s/it]

DDIM Sampler:  66%|██████▌   | 49/74 [01:01<00:27,  1.10s/it]

DDIM Sampler:  68%|██████▊   | 50/74 [01:02<00:26,  1.10s/it]

DDIM Sampler:  69%|██████▉   | 51/74 [01:03<00:25,  1.10s/it]

DDIM Sampler:  70%|███████   | 52/74 [01:04<00:24,  1.10s/it]

DDIM Sampler:  72%|███████▏  | 53/74 [01:05<00:23,  1.10s/it]

DDIM Sampler:  73%|███████▎  | 54/74 [01:06<00:22,  1.10s/it]

DDIM Sampler:  74%|███████▍  | 55/74 [01:07<00:20,  1.10s/it]

DDIM Sampler:  76%|███████▌  | 56/74 [01:08<00:19,  1.10s/it]

DDIM Sampler:  77%|███████▋  | 57/74 [01:09<00:18,  1.10s/it]

DDIM Sampler:  78%|███████▊  | 58/74 [01:11<00:17,  1.10s/it]

DDIM Sampler:  80%|███████▉  | 59/74 [01:12<00:16,  1.10s/it]

DDIM Sampler:  81%|████████  | 60/74 [01:13<00:15,  1.10s/it]

DDIM Sampler:  82%|████████▏ | 61/74 [01:14<00:14,  1.10s/it]

DDIM Sampler:  84%|████████▍ | 62/74 [01:15<00:13,  1.10s/it]

DDIM Sampler:  85%|████████▌ | 63/74 [01:16<00:12,  1.10s/it]

DDIM Sampler:  86%|████████▋ | 64/74 [01:17<00:11,  1.10s/it]

DDIM Sampler:  88%|████████▊ | 65/74 [01:18<00:09,  1.10s/it]

DDIM Sampler:  89%|████████▉ | 66/74 [01:19<00:08,  1.10s/it]

DDIM Sampler:  91%|█████████ | 67/74 [01:21<00:07,  1.10s/it]

DDIM Sampler:  92%|█████████▏| 68/74 [01:22<00:06,  1.10s/it]

DDIM Sampler:  93%|█████████▎| 69/74 [01:23<00:05,  1.10s/it]

DDIM Sampler:  95%|█████████▍| 70/74 [01:24<00:04,  1.10s/it]

DDIM Sampler:  96%|█████████▌| 71/74 [01:25<00:03,  1.11s/it]

DDIM Sampler:  97%|█████████▋| 72/74 [01:26<00:02,  1.11s/it]

DDIM Sampler:  99%|█████████▊| 73/74 [01:27<00:01,  1.11s/it]

DDIM Sampler: 100%|██████████| 74/74 [01:28<00:00,  1.11s/it]
DDIM Sampler: 100%|██████████| 74/74 [01:28<00:00,  1.20s/it]

Sampling: 100%|██████████| 1/1 [03:14<00:00, 194.40s/it]
Sampling: 100%|██████████| 1/1 [03:14<00:00, 194.40s/it]

This example was created by a different version, nightmareai/majesty-diffusion:73bfb38e.

Examples

View more examples

Run time and cost

This model costs approximately $0.75 to run on Replicate, or 1 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 9 minutes. The predict time for this model varies significantly based on the inputs.

Readme

Majesty Diffusion 👑

Generate images from text with majesty

Formerly known as Princess Generator

Majesty Diffusion are implementations of text-to-image diffusion models with a royal touch 👸

Created by @Dango233 and @apolinario from multimodal ai art

Find and contribute custom settings on the official Hugging Face Space!