nightmareai/disco-diffusion:3db33992 – Run with an API on Replicate

Version

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

nightmareai /disco-diffusion:3db33992

Playground API

Input

steps

integer

Number of steps

Default: 100

prompt

string

Shift + Return to add a new line

a splendid day at the fair with a hot dog cart on fire, watercolor, trending on artstationa splendid day at the fair with a hot dog cart on fire, watercolor, trending on artstation

Text Prompt

Default: "A beautiful painting of a singular lighthouse, shining its light across a tumultuous sea of blood by greg rutkowski and thomas kinkade, Trending on artstation."

width

integer

Width

Default: 1280

height

integer

Height

Default: 768

diffusion_model

string

Diffusion Model

Default: "512x512_diffusion_uncond_finetune_008100"

diffusion_sampling_mode

string

Diffusion Sampling Mode

Default: "ddim"

ViTB32

boolean

Use ViTB32 model

Default: true

ViTB16

boolean

Use ViTB16 model

Default: true

ViTL14

boolean

Use ViTB14 model

Default: false

ViTL14_336

boolean

Use ViTL14_336 model

Default: false

RN50

boolean

Use RN50 model

Default: true

RN50x4

boolean

Use RN50x4 model

Default: false

RN50x16

boolean

Use RN50x16 model

Default: false

RN50x64

boolean

Use RN50x64 model

Default: false

RN50x101

boolean

Use RN50x101 model

Default: false

RN101

boolean

Use RN101 model

Default: false

use_secondary_model

boolean

Use secondary model

Default: true

clip_guidance_scale

integer

CLIP Guidance Scale

Default: 5000

tv_scale

integer

TV Scale

Default: 0

range_scale

integer

Range Scale

Default: 150

sat_scale

integer

Saturation Scale

Default: 0

cutn_batches

integer

Cut Batches

Default: 4

skip_augs

boolean

Skip Augmentations

Default: false

init_image

file

Init Image

target_image

file

Target Image

init_scale

integer

Init Scale

Default: 1000

target_scale

integer

Target Scale

Default: 20000

skip_steps

integer

Skip Steps

Default: 10

display_rate

integer

Steps between outputs, lower numbers may slow down generation.

Default: 20

seed

integer

(minimum: 0, maximum: 4294967295)

Seed (leave empty to use a random seed)

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

npx create-replicate --model=nightmareai/disco-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/disco-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "nightmareai/disco-diffusion:3db339922ea7421159874c71c20123079fa9c696849fb7a84da283ca5a9d5904",
  {
    input: {
      RN50: false,
      RN101: true,
      steps: 100,
      width: 1280,
      RN50x4: false,
      ViTB16: false,
      ViTB32: true,
      ViTL14: true,
      height: 768,
      prompt: "a splendid day at the fair with a hot dog cart on fire, watercolor, trending on artstation",
      RN50x16: false,
      RN50x64: false,
      RN50x101: false,
      tv_scale: 0,
      sat_scale: 0,
      skip_augs: false,
      ViTL14_336: false,
      init_scale: 1000,
      skip_steps: 10,
      range_scale: 150,
      cutn_batches: 4,
      display_rate: 20,
      target_scale: 20000,
      diffusion_model: "512x512_diffusion_uncond_finetune_008100",
      clip_guidance_scale: 5000,
      use_secondary_model: true,
      diffusion_sampling_mode: "plms"
    }
  }
);
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/disco-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "nightmareai/disco-diffusion:3db339922ea7421159874c71c20123079fa9c696849fb7a84da283ca5a9d5904",
    input={
        "RN50": False,
        "RN101": True,
        "steps": 100,
        "width": 1280,
        "RN50x4": False,
        "ViTB16": False,
        "ViTB32": True,
        "ViTL14": True,
        "height": 768,
        "prompt": "a splendid day at the fair with a hot dog cart on fire, watercolor, trending on artstation",
        "RN50x16": False,
        "RN50x64": False,
        "RN50x101": False,
        "tv_scale": 0,
        "sat_scale": 0,
        "skip_augs": False,
        "ViTL14_336": False,
        "init_scale": 1000,
        "skip_steps": 10,
        "range_scale": 150,
        "cutn_batches": 4,
        "display_rate": 20,
        "target_scale": 20000,
        "diffusion_model": "512x512_diffusion_uncond_finetune_008100",
        "clip_guidance_scale": 5000,
        "use_secondary_model": True,
        "diffusion_sampling_mode": "plms"
    }
)

# The nightmareai/disco-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/disco-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/disco-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": "3db339922ea7421159874c71c20123079fa9c696849fb7a84da283ca5a9d5904",
    "input": {
      "RN50": false,
      "RN101": true,
      "steps": 100,
      "width": 1280,
      "RN50x4": false,
      "ViTB16": false,
      "ViTB32": true,
      "ViTL14": true,
      "height": 768,
      "prompt": "a splendid day at the fair with a hot dog cart on fire, watercolor, trending on artstation",
      "RN50x16": false,
      "RN50x64": false,
      "RN50x101": false,
      "tv_scale": 0,
      "sat_scale": 0,
      "skip_augs": false,
      "ViTL14_336": false,
      "init_scale": 1000,
      "skip_steps": 10,
      "range_scale": 150,
      "cutn_batches": 4,
      "display_rate": 20,
      "target_scale": 20000,
      "diffusion_model": "512x512_diffusion_uncond_finetune_008100",
      "clip_guidance_scale": 5000,
      "use_secondary_model": true,
      "diffusion_sampling_mode": "plms"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-07-10T17:49:56.102752Z",
  "created_at": "2022-07-10T17:38:39.033607Z",
  "data_removed": false,
  "error": null,
  "id": "ffhmt2midvhq7g4vqkc6hwodjy",
  "input": {
    "RN50": false,
    "RN101": true,
    "steps": 100,
    "width": 1280,
    "ViTB16": false,
    "ViTB32": true,
    "ViTL14": true,
    "height": 768,
    "prompt": "a splendid day at the fair with a hot dog cart on fire, watercolor, trending on artstation",
    "init_scale": 1000,
    "skip_steps": 10,
    "range_scale": 150,
    "cutn_batches": 4,
    "display_rate": 20,
    "target_scale": 20000,
    "diffusion_model": "512x512_diffusion_uncond_finetune_008100",
    "clip_guidance_scale": 5000,
    "use_secondary_model": true,
    "diffusion_sampling_mode": "plms"
  },
  "logs": "2022-07-10 17:38:39.134 | INFO     | dd:start_run:2224 - 💼 1 jobs found.\n2022-07-10 17:38:39.135 | INFO     | dd:start_run:2236 - ⚒️ Session 3016cd34-a976-4120-bea9-ab4f516bcb1b started...\n2022-07-10 17:38:39.136 | INFO     | dd:start_run:2239 - 💼 Processing job 1 of 1...\n2022-07-10 17:38:39.136 | INFO     | dd:start_run:2242 - 🌲 Setting TORCH_HOME environment variable to /root/.cache/disco-diffusion...\n2022-07-10 17:38:39.137 | INFO     | dd:processBatch:2329 - 🌱 Randomly using seed: 2061879424\n2022-07-10 17:38:39.138 | INFO     | dd:free_mem:71 - Clearing CUDA cache on cuda:0...\n2022-07-10 17:38:39.138 | INFO     | dd:do_run:1190 - 💻 Starting Run: 5c946cae-4a65-4e82-93d4-c75d5ac763d8(0) at frame 0\n2022-07-10 17:38:39.138 | INFO     | dd:clipLoad:1182 - 🤖 Loading model 'ViT-B/32'...\n2022-07-10 17:38:48.730 | INFO     | dd:clipLoad:1182 - 🤖 Loading model 'ViT-L/14'...\n2022-07-10 17:39:03.368 | INFO     | dd:clipLoad:1182 - 🤖 Loading model 'RN101'...\n2022-07-10 17:39:08.345 | INFO     | dd:do_run:1216 - 🤖 Loading secondary model...\n2022-07-10 17:39:08.651 | INFO     | dd:do_run:1222 - 🤖 Loading LPIPS...\n/root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead.\n  warnings.warn(\n/root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.\n  warnings.warn(msg)\n\u001b[2K\n2022-07-10 17:39:14.258 | INFO     | dd:disco:1502 - timestep_respacing : ddim100 | diffusion_steps: 1000\n2022-07-10 17:39:14.259 | INFO     | dd:prepModels:1054 - Prepping models...\n2022-07-10 17:39:28.494 | INFO     | dd:disco:1532 - Running job '2c1c3bcc-ee12-444a-bca3-97f8b27af298'...\n2022-07-10 17:39:28.495 | INFO     | dd:disco:1545 - 🌱 Seed used: 2061879424\n2022-07-10 17:39:28.506 | INFO     | dd:disco:1571 - Frame 0 📝 Prompt: ['a splendid day at the fair with a hot dog cart on fire, watercolor, trending on artstation']\n\u001b[2K\n\u001b[2K\n\u001b[2K\nBatches:   0%|          | 0/1 [00:00<?, ?it/s]\nOutput()\n2022-07-10 17:39:30.302 | INFO     | dd:free_mem:71 - Clearing CUDA cache on cuda:0...\n\n\n  0%|          | 0/90 [00:00<?, ?it/s]\u001b[A\n\n\nBatch 0, step 0, output 0:\n\u001b[A\n\n\u001b[2K\n\u001b[2K\n<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37B50>\n  0%|          | 0/90 [00:15<?, ?it/s]\u001b[A\n\n  1%|          | 1/90 [00:15<22:56, 15.47s/it]\u001b[A\n\n  2%|▏         | 2/90 [00:21<14:34,  9.94s/it]\u001b[A\n\n  3%|▎         | 3/90 [00:27<11:53,  8.20s/it]\u001b[A\n\n  4%|▍         | 4/90 [00:33<10:37,  7.41s/it]\u001b[A\n\n  6%|▌         | 5/90 [00:40<09:54,  7.00s/it]\u001b[A\n\n  7%|▋         | 6/90 [00:46<09:28,  6.77s/it]\u001b[A\n\n  8%|▊         | 7/90 [00:52<09:11,  6.65s/it]\u001b[A\n\n  9%|▉         | 8/90 [00:59<09:01,  6.60s/it]\u001b[A\n\n 10%|█         | 9/90 [01:05<08:53,  6.59s/it]\u001b[A\n\n 11%|█         | 10/90 [01:12<08:47,  6.59s/it]\u001b[A\n\n 12%|█▏        | 11/90 [01:19<08:41,  6.60s/it]\u001b[A\n\n 13%|█▎        | 12/90 [01:25<08:35,  6.61s/it]\u001b[A\n\n 14%|█▍        | 13/90 [01:32<08:29,  6.62s/it]\u001b[A\n\n 16%|█▌        | 14/90 [01:39<08:23,  6.62s/it]\u001b[A\n\n 17%|█▋        | 15/90 [01:45<08:15,  6.61s/it]\u001b[A\n\n 18%|█▊        | 16/90 [01:52<08:07,  6.59s/it]\u001b[A\n\n 19%|█▉        | 17/90 [01:58<07:59,  6.56s/it]\u001b[A\n\n 20%|██        | 18/90 [02:05<07:51,  6.55s/it]\u001b[A\n\n 21%|██        | 19/90 [02:11<07:44,  6.55s/it]\u001b[A\n\n 22%|██▏       | 20/90 [02:18<07:38,  6.55s/it]\u001b[A\n\n\nBatch 0, step 20, output 0:\n\u001b[A\n\n\u001b[2K\n\u001b[2K\n<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37AF0>\n 22%|██▏       | 20/90 [02:24<07:38,  6.55s/it]\u001b[A\n\n 23%|██▎       | 21/90 [02:25<07:46,  6.76s/it]\u001b[A\n\n 24%|██▍       | 22/90 [02:32<07:35,  6.70s/it]\u001b[A\n\n 26%|██▌       | 23/90 [02:38<07:26,  6.66s/it]\u001b[A\n\n 27%|██▋       | 24/90 [02:45<07:18,  6.64s/it]\u001b[A\n\n 28%|██▊       | 25/90 [02:51<07:10,  6.63s/it]\u001b[A\n\n 29%|██▉       | 26/90 [02:58<07:03,  6.61s/it]\u001b[A\n\n 30%|███       | 27/90 [03:05<06:56,  6.61s/it]\u001b[A\n\n 31%|███       | 28/90 [03:11<06:49,  6.60s/it]\u001b[A\n\n 32%|███▏      | 29/90 [03:18<06:41,  6.59s/it]\u001b[A\n\n 33%|███▎      | 30/90 [03:24<06:34,  6.58s/it]\u001b[A\n\n 34%|███▍      | 31/90 [03:31<06:32,  6.66s/it]\u001b[A\n\n 36%|███▌      | 32/90 [03:38<06:29,  6.72s/it]\u001b[A\n\n 37%|███▋      | 33/90 [03:45<06:25,  6.76s/it]\u001b[A\n\n 38%|███▊      | 34/90 [03:52<06:20,  6.79s/it]\u001b[A\n\n 39%|███▉      | 35/90 [03:58<06:14,  6.81s/it]\u001b[A\n\n 40%|████      | 36/90 [04:05<06:08,  6.82s/it]\u001b[A\n\n 41%|████      | 37/90 [04:12<06:01,  6.82s/it]\u001b[A\n\n 42%|████▏     | 38/90 [04:19<05:55,  6.84s/it]\u001b[A\n\n 43%|████▎     | 39/90 [04:26<05:49,  6.86s/it]\u001b[A\n\nBatch 0, step 40, output 0:\n 44%|████▍     | 40/90 [04:33<05:43,  6.86s/it]\u001b[A\n\n\n\u001b[A\n\n\u001b[2K\n\u001b[2K\n<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37B50>\n 44%|████▍     | 40/90 [04:40<05:43,  6.86s/it]\u001b[A\n\n 46%|████▌     | 41/90 [04:40<05:45,  7.06s/it]\u001b[A\n\n 47%|████▋     | 42/90 [04:47<05:35,  6.99s/it]\u001b[A\n\n 48%|████▊     | 43/90 [04:54<05:26,  6.95s/it]\u001b[A\n\n 49%|████▉     | 44/90 [05:01<05:18,  6.92s/it]\u001b[A\n\n 50%|█████     | 45/90 [05:08<05:10,  6.89s/it]\u001b[A\n\n 51%|█████     | 46/90 [05:15<05:02,  6.88s/it]\u001b[A\n\n 52%|█████▏    | 47/90 [05:21<04:55,  6.88s/it]\u001b[A\n\n 53%|█████▎    | 48/90 [05:28<04:48,  6.88s/it]\u001b[A\n\n 54%|█████▍    | 49/90 [05:35<04:42,  6.89s/it]\u001b[A\n\n 56%|█████▌    | 50/90 [05:42<04:35,  6.89s/it]\u001b[A\n\n 57%|█████▋    | 51/90 [05:49<04:28,  6.89s/it]\u001b[A\n\n 58%|█████▊    | 52/90 [05:56<04:21,  6.89s/it]\u001b[A\n\n 59%|█████▉    | 53/90 [06:03<04:15,  6.90s/it]\u001b[A\n\n 60%|██████    | 54/90 [06:10<04:08,  6.89s/it]\u001b[A\n\n 61%|██████    | 55/90 [06:17<04:00,  6.88s/it]\u001b[A\n\n 62%|██████▏   | 56/90 [06:23<03:53,  6.86s/it]\u001b[A\n\n 63%|██████▎   | 57/90 [06:30<03:46,  6.86s/it]\u001b[A\n\n 64%|██████▍   | 58/90 [06:37<03:39,  6.87s/it]\u001b[A\n\n 66%|██████▌   | 59/90 [06:44<03:32,  6.87s/it]\u001b[A\n\n 67%|██████▋   | 60/90 [06:51<03:26,  6.87s/it]\u001b[A\n\n\nBatch 0, step 60, output 0:\n\u001b[A\n\n\u001b[2K\n\u001b[2K\n<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37C10>\n 67%|██████▋   | 60/90 [06:58<03:26,  6.87s/it]\u001b[A\n\n 68%|██████▊   | 61/90 [06:58<03:25,  7.07s/it]\u001b[A\n\n 69%|██████▉   | 62/90 [07:05<03:16,  7.00s/it]\u001b[A\n\n 70%|███████   | 63/90 [07:12<03:08,  6.97s/it]\u001b[A\n\n 71%|███████   | 64/90 [07:19<03:00,  6.94s/it]\u001b[A\n\n 72%|███████▏  | 65/90 [07:26<02:53,  6.93s/it]\u001b[A\n\n 73%|███████▎  | 66/90 [07:33<02:46,  6.92s/it]\u001b[A\n\n 74%|███████▍  | 67/90 [07:40<02:38,  6.91s/it]\u001b[A\n\n 76%|███████▌  | 68/90 [07:47<02:31,  6.90s/it]\u001b[A\n\n 77%|███████▋  | 69/90 [07:53<02:24,  6.89s/it]\u001b[A\n\n 78%|███████▊  | 70/90 [08:00<02:17,  6.89s/it]\u001b[A\n\n 79%|███████▉  | 71/90 [08:07<02:10,  6.87s/it]\u001b[A\n\n 80%|████████  | 72/90 [08:14<02:03,  6.87s/it]\u001b[A\n\n 81%|████████  | 73/90 [08:21<01:56,  6.87s/it]\u001b[A\n\n 82%|████████▏ | 74/90 [08:28<01:49,  6.86s/it]\u001b[A\n\n 83%|████████▎ | 75/90 [08:35<01:42,  6.86s/it]\u001b[A\n\n 84%|████████▍ | 76/90 [08:41<01:35,  6.86s/it]\u001b[A\n\n 86%|████████▌ | 77/90 [08:48<01:29,  6.85s/it]\u001b[A\n\n 87%|████████▋ | 78/90 [08:55<01:22,  6.85s/it]\u001b[A\n\n 88%|████████▊ | 79/90 [09:02<01:15,  6.85s/it]\u001b[A\n\n 89%|████████▉ | 80/90 [09:09<01:08,  6.86s/it]\u001b[A\nBatch 0, step 80, output 0:\n\n\n\u001b[A\n\n\u001b[2K\n\u001b[2K\n<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37B50>\n 89%|████████▉ | 80/90 [09:16<01:08,  6.86s/it]\u001b[A\n\n 90%|█████████ | 81/90 [09:16<01:03,  7.03s/it]\u001b[A\n\n 91%|█████████ | 82/90 [09:23<00:55,  6.97s/it]\u001b[A\n\n 92%|█████████▏| 83/90 [09:30<00:48,  6.93s/it]\u001b[A\n\n 93%|█████████▎| 84/90 [09:37<00:41,  6.91s/it]\u001b[A\n\n 94%|█████████▍| 85/90 [09:44<00:34,  6.89s/it]\u001b[A\n\n 96%|█████████▌| 86/90 [09:51<00:27,  6.88s/it]\u001b[A\n\n 97%|█████████▋| 87/90 [09:57<00:20,  6.88s/it]\u001b[A\n\n 98%|█████████▊| 88/90 [10:04<00:13,  6.88s/it]\u001b[A\n\n 99%|█████████▉| 89/90 [10:11<00:06,  6.89s/it]\u001b[A\n\n\nBatch 0, step 89, output 0:\n\u001b[A\n\n\u001b[2K\n\u001b[2K\n<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37A60>\n 99%|█████████▉| 89/90 [10:18<00:06,  6.89s/it]\u001b[A2022-07-10 17:49:49.335 | INFO     | dd:disco:1820 - Image render completed.\n2022-07-10 17:49:49.736 | INFO     | dd:disco:1840 - Image saved to '/src/images_out/5c946cae-4a65-4e82-93d4-c75d5ac763d8/5c946cae-4a65-4e82-93d4-c75d5ac763d8(0)_0.png'\n\n\n100%|██████████| 90/90 [10:19<00:00,  7.15s/it]\u001b[A\n100%|██████████| 90/90 [10:19<00:00,  6.88s/it]\n2022-07-10 17:49:49.737 | INFO     | dd:free_mem:71 - Clearing CUDA cache on cuda:0...\n2022-07-10 17:49:49.738 | SUCCESS  | dd:start_run:2245 - ✅ Session 3016cd34-a976-4120-bea9-ab4f516bcb1b finished by user.\n2022-07-10 17:49:49.738 | DEBUG    | dd:sendSMS:2530 - Not sending SMS\n2022-07-10 17:49:49.738 | INFO     | dd:free_mem:71 - Clearing CUDA cache on cuda:0...",
  "metrics": {
    "predict_time": 676.842882,
    "total_time": 677.069145
  },
  "output": [
    "https://replicate.delivery/mgxm/7871aabb-1e03-4fb4-b7fc-9bee49b5e884/progress.png",
    "https://replicate.delivery/mgxm/c5227933-7026-480f-91e8-5b15e78f01d0/progress.png",
    "https://replicate.delivery/mgxm/f31bd350-4cfa-4e0b-8915-0e8f56c087e5/progress.png",
    "https://replicate.delivery/mgxm/8f95d8e3-51ea-482e-9312-baa02335a122/progress.png",
    "https://replicate.delivery/mgxm/c9c26b18-04cb-4f5c-9753-e783ff5cb437/progress.png",
    "https://replicate.delivery/mgxm/d84bb6fc-96a6-4ab4-b811-cb8f8ff715e5/progress.png",
    "https://replicate.delivery/mgxm/38ef3c75-8a67-4b00-829e-b8d4a1e51b16/progress.png"
  ],
  "started_at": "2022-07-10T17:38:39.259870Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ffhmt2midvhq7g4vqkc6hwodjy",
    "cancel": "https://api.replicate.com/v1/predictions/ffhmt2midvhq7g4vqkc6hwodjy/cancel"
  },
  "version": "3db339922ea7421159874c71c20123079fa9c696849fb7a84da283ca5a9d5904"
}

Generated in

11 minutes 17 seconds

Tweak itReport

2022-07-10 17:38:39.134 | INFO     | dd:start_run:2224 - 💼 1 jobs found.
2022-07-10 17:38:39.135 | INFO     | dd:start_run:2236 - ⚒️ Session 3016cd34-a976-4120-bea9-ab4f516bcb1b started...
2022-07-10 17:38:39.136 | INFO     | dd:start_run:2239 - 💼 Processing job 1 of 1...
2022-07-10 17:38:39.136 | INFO     | dd:start_run:2242 - 🌲 Setting TORCH_HOME environment variable to /root/.cache/disco-diffusion...
2022-07-10 17:38:39.137 | INFO     | dd:processBatch:2329 - 🌱 Randomly using seed: 2061879424
2022-07-10 17:38:39.138 | INFO     | dd:free_mem:71 - Clearing CUDA cache on cuda:0...
2022-07-10 17:38:39.138 | INFO     | dd:do_run:1190 - 💻 Starting Run: 5c946cae-4a65-4e82-93d4-c75d5ac763d8(0) at frame 0
2022-07-10 17:38:39.138 | INFO     | dd:clipLoad:1182 - 🤖 Loading model 'ViT-B/32'...
2022-07-10 17:38:48.730 | INFO     | dd:clipLoad:1182 - 🤖 Loading model 'ViT-L/14'...
2022-07-10 17:39:03.368 | INFO     | dd:clipLoad:1182 - 🤖 Loading model 'RN101'...
2022-07-10 17:39:08.345 | INFO     | dd:do_run:1216 - 🤖 Loading secondary model...
2022-07-10 17:39:08.651 | INFO     | dd:do_run:1222 - 🤖 Loading LPIPS...
/root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead.
  warnings.warn(
/root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

2022-07-10 17:39:14.258 | INFO     | dd:disco:1502 - timestep_respacing : ddim100 | diffusion_steps: 1000
2022-07-10 17:39:14.259 | INFO     | dd:prepModels:1054 - Prepping models...
2022-07-10 17:39:28.494 | INFO     | dd:disco:1532 - Running job '2c1c3bcc-ee12-444a-bca3-97f8b27af298'...
2022-07-10 17:39:28.495 | INFO     | dd:disco:1545 - 🌱 Seed used: 2061879424
2022-07-10 17:39:28.506 | INFO     | dd:disco:1571 - Frame 0 📝 Prompt: ['a splendid day at the fair with a hot dog cart on fire, watercolor, trending on artstation']



Batches:   0%|          | 0/1 [00:00<?, ?it/s]
Output()
2022-07-10 17:39:30.302 | INFO     | dd:free_mem:71 - Clearing CUDA cache on cuda:0...


  0%|          | 0/90 [00:00<?, ?it/s]


Batch 0, step 0, output 0:




<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37B50>
  0%|          | 0/90 [00:15<?, ?it/s]

  1%|          | 1/90 [00:15<22:56, 15.47s/it]

  2%|▏         | 2/90 [00:21<14:34,  9.94s/it]

  3%|▎         | 3/90 [00:27<11:53,  8.20s/it]

  4%|▍         | 4/90 [00:33<10:37,  7.41s/it]

  6%|▌         | 5/90 [00:40<09:54,  7.00s/it]

  7%|▋         | 6/90 [00:46<09:28,  6.77s/it]

  8%|▊         | 7/90 [00:52<09:11,  6.65s/it]

  9%|▉         | 8/90 [00:59<09:01,  6.60s/it]

 10%|█         | 9/90 [01:05<08:53,  6.59s/it]

 11%|█         | 10/90 [01:12<08:47,  6.59s/it]

 12%|█▏        | 11/90 [01:19<08:41,  6.60s/it]

 13%|█▎        | 12/90 [01:25<08:35,  6.61s/it]

 14%|█▍        | 13/90 [01:32<08:29,  6.62s/it]

 16%|█▌        | 14/90 [01:39<08:23,  6.62s/it]

 17%|█▋        | 15/90 [01:45<08:15,  6.61s/it]

 18%|█▊        | 16/90 [01:52<08:07,  6.59s/it]

 19%|█▉        | 17/90 [01:58<07:59,  6.56s/it]

 20%|██        | 18/90 [02:05<07:51,  6.55s/it]

 21%|██        | 19/90 [02:11<07:44,  6.55s/it]

 22%|██▏       | 20/90 [02:18<07:38,  6.55s/it]


Batch 0, step 20, output 0:




<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37AF0>
 22%|██▏       | 20/90 [02:24<07:38,  6.55s/it]

 23%|██▎       | 21/90 [02:25<07:46,  6.76s/it]

 24%|██▍       | 22/90 [02:32<07:35,  6.70s/it]

 26%|██▌       | 23/90 [02:38<07:26,  6.66s/it]

 27%|██▋       | 24/90 [02:45<07:18,  6.64s/it]

 28%|██▊       | 25/90 [02:51<07:10,  6.63s/it]

 29%|██▉       | 26/90 [02:58<07:03,  6.61s/it]

 30%|███       | 27/90 [03:05<06:56,  6.61s/it]

 31%|███       | 28/90 [03:11<06:49,  6.60s/it]

 32%|███▏      | 29/90 [03:18<06:41,  6.59s/it]

 33%|███▎      | 30/90 [03:24<06:34,  6.58s/it]

 34%|███▍      | 31/90 [03:31<06:32,  6.66s/it]

 36%|███▌      | 32/90 [03:38<06:29,  6.72s/it]

 37%|███▋      | 33/90 [03:45<06:25,  6.76s/it]

 38%|███▊      | 34/90 [03:52<06:20,  6.79s/it]

 39%|███▉      | 35/90 [03:58<06:14,  6.81s/it]

 40%|████      | 36/90 [04:05<06:08,  6.82s/it]

 41%|████      | 37/90 [04:12<06:01,  6.82s/it]

 42%|████▏     | 38/90 [04:19<05:55,  6.84s/it]

 43%|████▎     | 39/90 [04:26<05:49,  6.86s/it]

Batch 0, step 40, output 0:
 44%|████▍     | 40/90 [04:33<05:43,  6.86s/it]






<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37B50>
 44%|████▍     | 40/90 [04:40<05:43,  6.86s/it]

 46%|████▌     | 41/90 [04:40<05:45,  7.06s/it]

 47%|████▋     | 42/90 [04:47<05:35,  6.99s/it]

 48%|████▊     | 43/90 [04:54<05:26,  6.95s/it]

 49%|████▉     | 44/90 [05:01<05:18,  6.92s/it]

 50%|█████     | 45/90 [05:08<05:10,  6.89s/it]

 51%|█████     | 46/90 [05:15<05:02,  6.88s/it]

 52%|█████▏    | 47/90 [05:21<04:55,  6.88s/it]

 53%|█████▎    | 48/90 [05:28<04:48,  6.88s/it]

 54%|█████▍    | 49/90 [05:35<04:42,  6.89s/it]

 56%|█████▌    | 50/90 [05:42<04:35,  6.89s/it]

 57%|█████▋    | 51/90 [05:49<04:28,  6.89s/it]

 58%|█████▊    | 52/90 [05:56<04:21,  6.89s/it]

 59%|█████▉    | 53/90 [06:03<04:15,  6.90s/it]

 60%|██████    | 54/90 [06:10<04:08,  6.89s/it]

 61%|██████    | 55/90 [06:17<04:00,  6.88s/it]

 62%|██████▏   | 56/90 [06:23<03:53,  6.86s/it]

 63%|██████▎   | 57/90 [06:30<03:46,  6.86s/it]

 64%|██████▍   | 58/90 [06:37<03:39,  6.87s/it]

 66%|██████▌   | 59/90 [06:44<03:32,  6.87s/it]

 67%|██████▋   | 60/90 [06:51<03:26,  6.87s/it]


Batch 0, step 60, output 0:




<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37C10>
 67%|██████▋   | 60/90 [06:58<03:26,  6.87s/it]

 68%|██████▊   | 61/90 [06:58<03:25,  7.07s/it]

 69%|██████▉   | 62/90 [07:05<03:16,  7.00s/it]

 70%|███████   | 63/90 [07:12<03:08,  6.97s/it]

 71%|███████   | 64/90 [07:19<03:00,  6.94s/it]

 72%|███████▏  | 65/90 [07:26<02:53,  6.93s/it]

 73%|███████▎  | 66/90 [07:33<02:46,  6.92s/it]

 74%|███████▍  | 67/90 [07:40<02:38,  6.91s/it]

 76%|███████▌  | 68/90 [07:47<02:31,  6.90s/it]

 77%|███████▋  | 69/90 [07:53<02:24,  6.89s/it]

 78%|███████▊  | 70/90 [08:00<02:17,  6.89s/it]

 79%|███████▉  | 71/90 [08:07<02:10,  6.87s/it]

 80%|████████  | 72/90 [08:14<02:03,  6.87s/it]

 81%|████████  | 73/90 [08:21<01:56,  6.87s/it]

 82%|████████▏ | 74/90 [08:28<01:49,  6.86s/it]

 83%|████████▎ | 75/90 [08:35<01:42,  6.86s/it]

 84%|████████▍ | 76/90 [08:41<01:35,  6.86s/it]

 86%|████████▌ | 77/90 [08:48<01:29,  6.85s/it]

 87%|████████▋ | 78/90 [08:55<01:22,  6.85s/it]

 88%|████████▊ | 79/90 [09:02<01:15,  6.85s/it]

 89%|████████▉ | 80/90 [09:09<01:08,  6.86s/it]
Batch 0, step 80, output 0:






<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37B50>
 89%|████████▉ | 80/90 [09:16<01:08,  6.86s/it]

 90%|█████████ | 81/90 [09:16<01:03,  7.03s/it]

 91%|█████████ | 82/90 [09:23<00:55,  6.97s/it]

 92%|█████████▏| 83/90 [09:30<00:48,  6.93s/it]

 93%|█████████▎| 84/90 [09:37<00:41,  6.91s/it]

 94%|█████████▍| 85/90 [09:44<00:34,  6.89s/it]

 96%|█████████▌| 86/90 [09:51<00:27,  6.88s/it]

 97%|█████████▋| 87/90 [09:57<00:20,  6.88s/it]

 98%|█████████▊| 88/90 [10:04<00:13,  6.88s/it]

 99%|█████████▉| 89/90 [10:11<00:06,  6.89s/it]


Batch 0, step 89, output 0:




<PIL.Image.Image image mode=RGB size=1280x768 at 0x7F64E7D37A60>
 99%|█████████▉| 89/90 [10:18<00:06,  6.89s/it]2022-07-10 17:49:49.335 | INFO     | dd:disco:1820 - Image render completed.
2022-07-10 17:49:49.736 | INFO     | dd:disco:1840 - Image saved to '/src/images_out/5c946cae-4a65-4e82-93d4-c75d5ac763d8/5c946cae-4a65-4e82-93d4-c75d5ac763d8(0)_0.png'


100%|██████████| 90/90 [10:19<00:00,  7.15s/it]
100%|██████████| 90/90 [10:19<00:00,  6.88s/it]
2022-07-10 17:49:49.737 | INFO     | dd:free_mem:71 - Clearing CUDA cache on cuda:0...
2022-07-10 17:49:49.738 | SUCCESS  | dd:start_run:2245 - ✅ Session 3016cd34-a976-4120-bea9-ab4f516bcb1b finished by user.
2022-07-10 17:49:49.738 | DEBUG    | dd:sendSMS:2530 - Not sending SMS
2022-07-10 17:49:49.738 | INFO     | dd:free_mem:71 - Clearing CUDA cache on cuda:0...