You're looking at a specific version of this model. Jump to the model overview.
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=laion-ai/ongo
or set up a project from scratch
Install Replicate’s Node.js client library:
npm install replicateSet 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 laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"laion-ai/ongo:818c3886693975754e0d8962fa51bd967c8a4a332e123a6099086f08d068c49f",
{
input: {
seed: -1,
steps: 100,
width: 256,
height: 256,
prompt: "concept art of 2001 a space odyssey",
negative: "",
batch_size: 6,
guidance_scale: 5,
aesthetic_rating: 9,
aesthetic_weight: 0.5,
init_skip_fraction: 0
}
}
);
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 replicateSet 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 replicateRun laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"laion-ai/ongo:818c3886693975754e0d8962fa51bd967c8a4a332e123a6099086f08d068c49f",
input={
"seed": -1,
"steps": 100,
"width": 256,
"height": 256,
"prompt": "concept art of 2001 a space odyssey",
"negative": "",
"batch_size": 6,
"guidance_scale": 5,
"aesthetic_rating": 9,
"aesthetic_weight": 0.5,
"init_skip_fraction": 0
}
)
# The laion-ai/ongo 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/laion-ai/ongo/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 laion-ai/ongo 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": "818c3886693975754e0d8962fa51bd967c8a4a332e123a6099086f08d068c49f",
"input": {
"seed": -1,
"steps": 100,
"width": 256,
"height": 256,
"prompt": "concept art of 2001 a space odyssey",
"negative": "",
"batch_size": 6,
"guidance_scale": 5,
"aesthetic_rating": 9,
"aesthetic_weight": 0.5,
"init_skip_fraction": 0
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:
brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/laion-ai/ongo@sha256:818c3886693975754e0d8962fa51bd967c8a4a332e123a6099086f08d068c49f \
-i 'seed=-1' \
-i 'steps=100' \
-i 'width=256' \
-i 'height=256' \
-i 'prompt="concept art of 2001 a space odyssey"' \
-i 'negative=""' \
-i 'batch_size=6' \
-i 'guidance_scale=5' \
-i 'aesthetic_rating=9' \
-i 'aesthetic_weight=0.5' \
-i 'init_skip_fraction=0'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/laion-ai/ongo@sha256:818c3886693975754e0d8962fa51bd967c8a4a332e123a6099086f08d068c49fcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": -1, "steps": 100, "width": 256, "height": 256, "prompt": "concept art of 2001 a space odyssey", "negative": "", "batch_size": 6, "guidance_scale": 5, "aesthetic_rating": 9, "aesthetic_weight": 0.5, "init_skip_fraction": 0 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Add a payment method to run this model.
Sign in with GitHub
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2022-06-05T03:36:03.637035Z",
"created_at": "2022-06-05T03:34:28.572215Z",
"data_removed": false,
"error": null,
"id": "6kabc6ksanea7nadevmu26n5uy",
"input": {
"seed": -1,
"steps": "100",
"width": 256,
"height": 256,
"prompt": "concept art of 2001 a space odyssey",
"batch_size": "6",
"guidance_scale": 5,
"aesthetic_rating": 9,
"aesthetic_weight": 0.5
},
"logs": "Encoding text with BERT\nEncoding text with CLIP\nUsing aesthetic embedding 9 with weight 0.5\nLoading image\nUsing inpaint model but no image is provided. Initializing with zeros.\nPacking CLIP and BERT embeddings into kwargs\nRunning diffusion...\n\n0it [00:00, ?it/s]\n\n 0%| | 0/100 [00:00<?, ?it/s]\u001b[A\n1it [00:02, 2.77s/it]\n\n 1%| | 1/100 [00:02<04:34, 2.77s/it]\u001b[A\n2it [00:04, 2.19s/it]\n\n 2%|▏ | 2/100 [00:04<03:34, 2.19s/it]\u001b[A\n3it [00:06, 2.00s/it]\n\n 3%|▎ | 3/100 [00:06<03:14, 2.00s/it]\u001b[A\n4it [00:06, 1.39s/it]\n\n 4%|▍ | 4/100 [00:06<02:13, 1.39s/it]\u001b[A\n5it [00:07, 1.05s/it]\n\n 5%|▌ | 5/100 [00:07<01:39, 1.05s/it]\u001b[A\n6it [00:08, 1.18s/it]\n\n 6%|▌ | 6/100 [00:08<01:50, 1.18s/it]\u001b[A\n7it [00:09, 1.07it/s]\n\n 7%|▋ | 7/100 [00:09<01:26, 1.07it/s]\u001b[A\n8it [00:09, 1.28it/s]\n\n 8%|▊ | 8/100 [00:09<01:11, 1.28it/s]\u001b[A\n9it [00:09, 1.48it/s]\n\n 9%|▉ | 9/100 [00:09<01:01, 1.48it/s]\u001b[A\n10it [00:10, 1.65it/s]\n\n 10%|█ | 10/100 [00:10<00:54, 1.65it/s]\u001b[A\n11it [00:11, 1.17it/s]\n\n 11%|█ | 11/100 [00:11<01:15, 1.17it/s]\u001b[A\n12it [00:12, 1.38it/s]\n\n 12%|█▏ | 12/100 [00:12<01:03, 1.38it/s]\u001b[A\n13it [00:12, 1.56it/s]\n\n 13%|█▎ | 13/100 [00:12<00:55, 1.56it/s]\u001b[A\n14it [00:13, 1.72it/s]\n\n 14%|█▍ | 14/100 [00:13<00:50, 1.72it/s]\u001b[A\n15it [00:13, 1.85it/s]\n\n 15%|█▌ | 15/100 [00:13<00:45, 1.85it/s]\u001b[A\n16it [00:15, 1.25it/s]\n\n 16%|█▌ | 16/100 [00:15<01:07, 1.25it/s]\u001b[A\n17it [00:15, 1.45it/s]\n\n 17%|█▋ | 17/100 [00:15<00:57, 1.45it/s]\u001b[A\n18it [00:15, 1.62it/s]\n\n 18%|█▊ | 18/100 [00:15<00:50, 1.62it/s]\u001b[A\n19it [00:16, 1.77it/s]\n\n 19%|█▉ | 19/100 [00:16<00:45, 1.77it/s]\u001b[A\n20it [00:16, 1.89it/s]\n\n 20%|██ | 20/100 [00:16<00:42, 1.89it/s]\u001b[A\n21it [00:18, 1.26it/s]\n\n 21%|██ | 21/100 [00:18<01:02, 1.26it/s]\u001b[A\n22it [00:18, 1.46it/s]\n\n 22%|██▏ | 22/100 [00:18<00:53, 1.46it/s]\u001b[A\n23it [00:19, 1.64it/s]\n\n 23%|██▎ | 23/100 [00:19<00:47, 1.64it/s]\u001b[A\n24it [00:19, 1.78it/s]\n\n 24%|██▍ | 24/100 [00:19<00:42, 1.78it/s]\u001b[A\n25it [00:19, 1.90it/s]\n\n 25%|██▌ | 25/100 [00:19<00:39, 1.90it/s]\u001b[A\n26it [00:21, 1.27it/s]\n\n 26%|██▌ | 26/100 [00:21<00:58, 1.27it/s]\u001b[A\n27it [00:21, 1.47it/s]\n\n 27%|██▋ | 27/100 [00:21<00:49, 1.47it/s]\u001b[A\n28it [00:22, 1.64it/s]\n\n 28%|██▊ | 28/100 [00:22<00:43, 1.64it/s]\u001b[A\n29it [00:22, 1.79it/s]\n\n 29%|██▉ | 29/100 [00:22<00:39, 1.79it/s]\u001b[A\n30it [00:23, 1.90it/s]\n\n 30%|███ | 30/100 [00:23<00:36, 1.90it/s]\u001b[A\n31it [00:24, 1.27it/s]\n\n 31%|███ | 31/100 [00:24<00:54, 1.27it/s]\u001b[A\n32it [00:24, 1.47it/s]\n\n 32%|███▏ | 32/100 [00:24<00:46, 1.47it/s]\u001b[A\n33it [00:25, 1.65it/s]\n\n 33%|███▎ | 33/100 [00:25<00:40, 1.65it/s]\u001b[A\n34it [00:25, 1.79it/s]\n\n 34%|███▍ | 34/100 [00:25<00:36, 1.79it/s]\u001b[A\n35it [00:26, 1.91it/s]\n\n 35%|███▌ | 35/100 [00:26<00:34, 1.91it/s]\u001b[A\n36it [00:27, 1.28it/s]\n\n 36%|███▌ | 36/100 [00:27<00:49, 1.28it/s]\u001b[A\n37it [00:28, 1.48it/s]\n\n 37%|███▋ | 37/100 [00:28<00:42, 1.48it/s]\u001b[A\n38it [00:28, 1.65it/s]\n\n 38%|███▊ | 38/100 [00:28<00:37, 1.65it/s]\u001b[A\n39it [00:28, 1.79it/s]\n\n 39%|███▉ | 39/100 [00:28<00:34, 1.79it/s]\u001b[A\n40it [00:29, 1.91it/s]\n\n 40%|████ | 40/100 [00:29<00:31, 1.91it/s]\u001b[A\n41it [00:30, 1.28it/s]\n\n 41%|████ | 41/100 [00:30<00:46, 1.28it/s]\u001b[A\n42it [00:31, 1.48it/s]\n\n 42%|████▏ | 42/100 [00:31<00:39, 1.48it/s]\u001b[A\n43it [00:31, 1.65it/s]\n\n 43%|████▎ | 43/100 [00:31<00:34, 1.65it/s]\u001b[A\n44it [00:32, 1.80it/s]\n\n 44%|████▍ | 44/100 [00:32<00:31, 1.80it/s]\u001b[A\n45it [00:32, 1.92it/s]\n\n 45%|████▌ | 45/100 [00:32<00:28, 1.92it/s]\u001b[A\n46it [00:33, 1.29it/s]\n\n 46%|████▌ | 46/100 [00:33<00:41, 1.29it/s]\u001b[A\n47it [00:34, 1.49it/s]\n\n 47%|████▋ | 47/100 [00:34<00:35, 1.49it/s]\u001b[A\n48it [00:34, 1.66it/s]\n\n 48%|████▊ | 48/100 [00:34<00:31, 1.66it/s]\u001b[A\n49it [00:35, 1.80it/s]\n\n 49%|████▉ | 49/100 [00:35<00:28, 1.80it/s]\u001b[A\n50it [00:35, 1.92it/s]\n\n 50%|█████ | 50/100 [00:35<00:26, 1.92it/s]\u001b[A\n51it [00:37, 1.29it/s]\n\n 51%|█████ | 51/100 [00:37<00:37, 1.29it/s]\u001b[A\n52it [00:37, 1.49it/s]\n\n 52%|█████▏ | 52/100 [00:37<00:32, 1.49it/s]\u001b[A\n53it [00:37, 1.66it/s]\n\n 53%|█████▎ | 53/100 [00:37<00:28, 1.66it/s]\u001b[A\n54it [00:38, 1.80it/s]\n\n 54%|█████▍ | 54/100 [00:38<00:25, 1.80it/s]\u001b[A\n55it [00:38, 1.92it/s]\n\n 55%|█████▌ | 55/100 [00:38<00:23, 1.92it/s]\u001b[A\n56it [00:40, 1.29it/s]\n\n 56%|█████▌ | 56/100 [00:40<00:34, 1.29it/s]\u001b[A\n57it [00:40, 1.49it/s]\n\n 57%|█████▋ | 57/100 [00:40<00:28, 1.49it/s]\u001b[A\n58it [00:41, 1.66it/s]\n\n 58%|█████▊ | 58/100 [00:41<00:25, 1.66it/s]\u001b[A\n59it [00:41, 1.80it/s]\n\n 59%|█████▉ | 59/100 [00:41<00:22, 1.80it/s]\u001b[A\n60it [00:41, 1.92it/s]\n\n 60%|██████ | 60/100 [00:41<00:20, 1.92it/s]\u001b[A\n61it [00:43, 1.29it/s]\n\n 61%|██████ | 61/100 [00:43<00:30, 1.29it/s]\u001b[A\n62it [00:43, 1.49it/s]\n\n 62%|██████▏ | 62/100 [00:43<00:25, 1.49it/s]\u001b[A\n63it [00:44, 1.66it/s]\n\n 63%|██████▎ | 63/100 [00:44<00:22, 1.66it/s]\u001b[A\n64it [00:44, 1.80it/s]\n\n 64%|██████▍ | 64/100 [00:44<00:20, 1.80it/s]\u001b[A\n65it [00:45, 1.91it/s]\n\n 65%|██████▌ | 65/100 [00:45<00:18, 1.91it/s]\u001b[A\n66it [00:46, 1.30it/s]\n\n 66%|██████▌ | 66/100 [00:46<00:26, 1.30it/s]\u001b[A\n67it [00:46, 1.50it/s]\n\n 67%|██████▋ | 67/100 [00:46<00:22, 1.50it/s]\u001b[A\n68it [00:47, 1.67it/s]\n\n 68%|██████▊ | 68/100 [00:47<00:19, 1.67it/s]\u001b[A\n69it [00:47, 1.80it/s]\n\n 69%|██████▉ | 69/100 [00:47<00:17, 1.80it/s]\u001b[A\n70it [00:48, 1.92it/s]\n\n 70%|███████ | 70/100 [00:48<00:15, 1.92it/s]\u001b[A\n71it [00:49, 1.31it/s]\n\n 71%|███████ | 71/100 [00:49<00:22, 1.31it/s]\u001b[A\n72it [00:49, 1.50it/s]\n\n 72%|███████▏ | 72/100 [00:49<00:18, 1.50it/s]\u001b[A\n73it [00:50, 1.67it/s]\n\n 73%|███████▎ | 73/100 [00:50<00:16, 1.67it/s]\u001b[A\n74it [00:50, 1.81it/s]\n\n 74%|███████▍ | 74/100 [00:50<00:14, 1.81it/s]\u001b[A\n75it [00:51, 1.92it/s]\n\n 75%|███████▌ | 75/100 [00:51<00:13, 1.92it/s]\u001b[A\n76it [00:52, 1.31it/s]\n\n 76%|███████▌ | 76/100 [00:52<00:18, 1.31it/s]\u001b[A\n77it [00:53, 1.50it/s]\n\n 77%|███████▋ | 77/100 [00:53<00:15, 1.50it/s]\u001b[A\n78it [00:53, 1.67it/s]\n\n 78%|███████▊ | 78/100 [00:53<00:13, 1.67it/s]\u001b[A\n79it [00:53, 1.81it/s]\n\n 79%|███████▉ | 79/100 [00:53<00:11, 1.81it/s]\u001b[A\n80it [00:54, 1.92it/s]\n\n 80%|████████ | 80/100 [00:54<00:10, 1.92it/s]\u001b[A\n81it [00:55, 1.31it/s]\n\n 81%|████████ | 81/100 [00:55<00:14, 1.31it/s]\u001b[A\n82it [00:56, 1.50it/s]\n\n 82%|████████▏ | 82/100 [00:56<00:11, 1.50it/s]\u001b[A\n83it [00:56, 1.67it/s]\n\n 83%|████████▎ | 83/100 [00:56<00:10, 1.67it/s]\u001b[A\n84it [00:57, 1.81it/s]\n\n 84%|████████▍ | 84/100 [00:57<00:08, 1.81it/s]\u001b[A\n85it [00:57, 1.92it/s]\n\n 85%|████████▌ | 85/100 [00:57<00:07, 1.92it/s]\u001b[A\n86it [00:58, 1.31it/s]\n\n 86%|████████▌ | 86/100 [00:58<00:10, 1.31it/s]\u001b[A\n87it [00:59, 1.50it/s]\n\n 87%|████████▋ | 87/100 [00:59<00:08, 1.50it/s]\u001b[A\n88it [00:59, 1.67it/s]\n\n 88%|████████▊ | 88/100 [00:59<00:07, 1.67it/s]\u001b[A\n89it [01:00, 1.81it/s]\n\n 89%|████████▉ | 89/100 [01:00<00:06, 1.81it/s]\u001b[A\n90it [01:00, 1.92it/s]\n\n 90%|█████████ | 90/100 [01:00<00:05, 1.92it/s]\u001b[A\n91it [01:01, 1.31it/s]\n\n 91%|█████████ | 91/100 [01:01<00:06, 1.31it/s]\u001b[A\n92it [01:02, 1.50it/s]\n\n 92%|█████████▏| 92/100 [01:02<00:05, 1.50it/s]\u001b[A\n93it [01:02, 1.67it/s]\n\n 93%|█████████▎| 93/100 [01:02<00:04, 1.67it/s]\u001b[A\n94it [01:03, 1.81it/s]\n\n 94%|█████████▍| 94/100 [01:03<00:03, 1.81it/s]\u001b[A\n95it [01:03, 1.92it/s]\n\n 95%|█████████▌| 95/100 [01:03<00:02, 1.92it/s]\u001b[A\n96it [01:05, 1.31it/s]\n\n 96%|█████████▌| 96/100 [01:05<00:03, 1.31it/s]\u001b[A\n97it [01:05, 1.50it/s]\n\n 97%|█████████▋| 97/100 [01:05<00:01, 1.50it/s]\u001b[A\n98it [01:05, 1.67it/s]\n\n 98%|█████████▊| 98/100 [01:05<00:01, 1.67it/s]\u001b[A\n99it [01:06, 1.81it/s]\n\n 99%|█████████▉| 99/100 [01:06<00:00, 1.81it/s]\u001b[A\n100it [01:06, 1.92it/s]\n\n100%|██████████| 100/100 [01:06<00:00, 1.92it/s]\u001b[A\n100%|██████████| 100/100 [01:06<00:00, 1.50it/s]\n\n100it [01:06, 1.50it/s]\nFinished generating with seed 908426086",
"metrics": {
"predict_time": 66.684719,
"total_time": 95.06482
},
"output": [
"https://replicate.delivery/mgxm/c3b85c9f-2379-452d-9444-360434a46063/current.png",
"https://replicate.delivery/mgxm/6d513e79-b821-43bd-b38f-2ef04e553481/current.png",
"https://replicate.delivery/mgxm/0508cbd9-faff-49eb-abd2-41f780fc9ed0/current.png",
"https://replicate.delivery/mgxm/4515a81a-0f34-42b2-b556-34ad34d39829/current.png",
"https://replicate.delivery/mgxm/ca3c00a8-8044-4bc0-9689-cde38208eaf3/current.png",
"https://replicate.delivery/mgxm/146f83cc-a695-4f23-ae64-7d4fe2d331af/current.png",
"https://replicate.delivery/mgxm/386db86e-62ae-4243-a417-61241d5fc73e/current.png",
"https://replicate.delivery/mgxm/94c6bb97-70fd-4204-84a9-1cdf63c08ba4/current.png",
"https://replicate.delivery/mgxm/02cd7c03-0cc5-4227-b0c9-57d24da85a45/current.png",
"https://replicate.delivery/mgxm/b3df1532-2f9b-407f-8ba7-d6eff10cc130/current.png",
"https://replicate.delivery/mgxm/b259525a-e173-4b66-9d54-3e48f4dc38a5/current.png",
"https://replicate.delivery/mgxm/6321ce0a-a12d-4af6-b1ee-aa909c18d06a/current.png",
"https://replicate.delivery/mgxm/a2e5acd9-d3f3-4dc9-afc4-7d7b60d1afea/current.png",
"https://replicate.delivery/mgxm/8c29c99e-3d60-46d4-9a26-80bd0c044370/current.png",
"https://replicate.delivery/mgxm/820e410f-8dee-47a0-9d1b-6f55175df408/current.png",
"https://replicate.delivery/mgxm/096e0167-6367-44ff-ae40-39f69fe6fdf1/current.png",
"https://replicate.delivery/mgxm/d589bde0-815a-4208-85f2-836519230b0e/current.png",
"https://replicate.delivery/mgxm/19d247fd-f4d9-4a08-ba0d-940c576df30e/current.png",
"https://replicate.delivery/mgxm/602aa48e-28d0-4900-9036-cc3d7f0f6a75/current.png",
"https://replicate.delivery/mgxm/8edd85e6-7963-4d20-b282-5030b79e732c/current.png"
],
"started_at": "2022-06-05T03:34:56.952316Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/6kabc6ksanea7nadevmu26n5uy",
"cancel": "https://api.replicate.com/v1/predictions/6kabc6ksanea7nadevmu26n5uy/cancel"
},
"version": "818c3886693975754e0d8962fa51bd967c8a4a332e123a6099086f08d068c49f"
}Generated in
Encoding text with BERT
Encoding text with CLIP
Using aesthetic embedding 9 with weight 0.5
Loading image
Using inpaint model but no image is provided. Initializing with zeros.
Packing CLIP and BERT embeddings into kwargs
Running diffusion...
0it [00:00, ?it/s]
0%| | 0/100 [00:00<?, ?it/s]
1it [00:02, 2.77s/it]
1%| | 1/100 [00:02<04:34, 2.77s/it]
2it [00:04, 2.19s/it]
2%|▏ | 2/100 [00:04<03:34, 2.19s/it]
3it [00:06, 2.00s/it]
3%|▎ | 3/100 [00:06<03:14, 2.00s/it]
4it [00:06, 1.39s/it]
4%|▍ | 4/100 [00:06<02:13, 1.39s/it]
5it [00:07, 1.05s/it]
5%|▌ | 5/100 [00:07<01:39, 1.05s/it]
6it [00:08, 1.18s/it]
6%|▌ | 6/100 [00:08<01:50, 1.18s/it]
7it [00:09, 1.07it/s]
7%|▋ | 7/100 [00:09<01:26, 1.07it/s]
8it [00:09, 1.28it/s]
8%|▊ | 8/100 [00:09<01:11, 1.28it/s]
9it [00:09, 1.48it/s]
9%|▉ | 9/100 [00:09<01:01, 1.48it/s]
10it [00:10, 1.65it/s]
10%|█ | 10/100 [00:10<00:54, 1.65it/s]
11it [00:11, 1.17it/s]
11%|█ | 11/100 [00:11<01:15, 1.17it/s]
12it [00:12, 1.38it/s]
12%|█▏ | 12/100 [00:12<01:03, 1.38it/s]
13it [00:12, 1.56it/s]
13%|█▎ | 13/100 [00:12<00:55, 1.56it/s]
14it [00:13, 1.72it/s]
14%|█▍ | 14/100 [00:13<00:50, 1.72it/s]
15it [00:13, 1.85it/s]
15%|█▌ | 15/100 [00:13<00:45, 1.85it/s]
16it [00:15, 1.25it/s]
16%|█▌ | 16/100 [00:15<01:07, 1.25it/s]
17it [00:15, 1.45it/s]
17%|█▋ | 17/100 [00:15<00:57, 1.45it/s]
18it [00:15, 1.62it/s]
18%|█▊ | 18/100 [00:15<00:50, 1.62it/s]
19it [00:16, 1.77it/s]
19%|█▉ | 19/100 [00:16<00:45, 1.77it/s]
20it [00:16, 1.89it/s]
20%|██ | 20/100 [00:16<00:42, 1.89it/s]
21it [00:18, 1.26it/s]
21%|██ | 21/100 [00:18<01:02, 1.26it/s]
22it [00:18, 1.46it/s]
22%|██▏ | 22/100 [00:18<00:53, 1.46it/s]
23it [00:19, 1.64it/s]
23%|██▎ | 23/100 [00:19<00:47, 1.64it/s]
24it [00:19, 1.78it/s]
24%|██▍ | 24/100 [00:19<00:42, 1.78it/s]
25it [00:19, 1.90it/s]
25%|██▌ | 25/100 [00:19<00:39, 1.90it/s]
26it [00:21, 1.27it/s]
26%|██▌ | 26/100 [00:21<00:58, 1.27it/s]
27it [00:21, 1.47it/s]
27%|██▋ | 27/100 [00:21<00:49, 1.47it/s]
28it [00:22, 1.64it/s]
28%|██▊ | 28/100 [00:22<00:43, 1.64it/s]
29it [00:22, 1.79it/s]
29%|██▉ | 29/100 [00:22<00:39, 1.79it/s]
30it [00:23, 1.90it/s]
30%|███ | 30/100 [00:23<00:36, 1.90it/s]
31it [00:24, 1.27it/s]
31%|███ | 31/100 [00:24<00:54, 1.27it/s]
32it [00:24, 1.47it/s]
32%|███▏ | 32/100 [00:24<00:46, 1.47it/s]
33it [00:25, 1.65it/s]
33%|███▎ | 33/100 [00:25<00:40, 1.65it/s]
34it [00:25, 1.79it/s]
34%|███▍ | 34/100 [00:25<00:36, 1.79it/s]
35it [00:26, 1.91it/s]
35%|███▌ | 35/100 [00:26<00:34, 1.91it/s]
36it [00:27, 1.28it/s]
36%|███▌ | 36/100 [00:27<00:49, 1.28it/s]
37it [00:28, 1.48it/s]
37%|███▋ | 37/100 [00:28<00:42, 1.48it/s]
38it [00:28, 1.65it/s]
38%|███▊ | 38/100 [00:28<00:37, 1.65it/s]
39it [00:28, 1.79it/s]
39%|███▉ | 39/100 [00:28<00:34, 1.79it/s]
40it [00:29, 1.91it/s]
40%|████ | 40/100 [00:29<00:31, 1.91it/s]
41it [00:30, 1.28it/s]
41%|████ | 41/100 [00:30<00:46, 1.28it/s]
42it [00:31, 1.48it/s]
42%|████▏ | 42/100 [00:31<00:39, 1.48it/s]
43it [00:31, 1.65it/s]
43%|████▎ | 43/100 [00:31<00:34, 1.65it/s]
44it [00:32, 1.80it/s]
44%|████▍ | 44/100 [00:32<00:31, 1.80it/s]
45it [00:32, 1.92it/s]
45%|████▌ | 45/100 [00:32<00:28, 1.92it/s]
46it [00:33, 1.29it/s]
46%|████▌ | 46/100 [00:33<00:41, 1.29it/s]
47it [00:34, 1.49it/s]
47%|████▋ | 47/100 [00:34<00:35, 1.49it/s]
48it [00:34, 1.66it/s]
48%|████▊ | 48/100 [00:34<00:31, 1.66it/s]
49it [00:35, 1.80it/s]
49%|████▉ | 49/100 [00:35<00:28, 1.80it/s]
50it [00:35, 1.92it/s]
50%|█████ | 50/100 [00:35<00:26, 1.92it/s]
51it [00:37, 1.29it/s]
51%|█████ | 51/100 [00:37<00:37, 1.29it/s]
52it [00:37, 1.49it/s]
52%|█████▏ | 52/100 [00:37<00:32, 1.49it/s]
53it [00:37, 1.66it/s]
53%|█████▎ | 53/100 [00:37<00:28, 1.66it/s]
54it [00:38, 1.80it/s]
54%|█████▍ | 54/100 [00:38<00:25, 1.80it/s]
55it [00:38, 1.92it/s]
55%|█████▌ | 55/100 [00:38<00:23, 1.92it/s]
56it [00:40, 1.29it/s]
56%|█████▌ | 56/100 [00:40<00:34, 1.29it/s]
57it [00:40, 1.49it/s]
57%|█████▋ | 57/100 [00:40<00:28, 1.49it/s]
58it [00:41, 1.66it/s]
58%|█████▊ | 58/100 [00:41<00:25, 1.66it/s]
59it [00:41, 1.80it/s]
59%|█████▉ | 59/100 [00:41<00:22, 1.80it/s]
60it [00:41, 1.92it/s]
60%|██████ | 60/100 [00:41<00:20, 1.92it/s]
61it [00:43, 1.29it/s]
61%|██████ | 61/100 [00:43<00:30, 1.29it/s]
62it [00:43, 1.49it/s]
62%|██████▏ | 62/100 [00:43<00:25, 1.49it/s]
63it [00:44, 1.66it/s]
63%|██████▎ | 63/100 [00:44<00:22, 1.66it/s]
64it [00:44, 1.80it/s]
64%|██████▍ | 64/100 [00:44<00:20, 1.80it/s]
65it [00:45, 1.91it/s]
65%|██████▌ | 65/100 [00:45<00:18, 1.91it/s]
66it [00:46, 1.30it/s]
66%|██████▌ | 66/100 [00:46<00:26, 1.30it/s]
67it [00:46, 1.50it/s]
67%|██████▋ | 67/100 [00:46<00:22, 1.50it/s]
68it [00:47, 1.67it/s]
68%|██████▊ | 68/100 [00:47<00:19, 1.67it/s]
69it [00:47, 1.80it/s]
69%|██████▉ | 69/100 [00:47<00:17, 1.80it/s]
70it [00:48, 1.92it/s]
70%|███████ | 70/100 [00:48<00:15, 1.92it/s]
71it [00:49, 1.31it/s]
71%|███████ | 71/100 [00:49<00:22, 1.31it/s]
72it [00:49, 1.50it/s]
72%|███████▏ | 72/100 [00:49<00:18, 1.50it/s]
73it [00:50, 1.67it/s]
73%|███████▎ | 73/100 [00:50<00:16, 1.67it/s]
74it [00:50, 1.81it/s]
74%|███████▍ | 74/100 [00:50<00:14, 1.81it/s]
75it [00:51, 1.92it/s]
75%|███████▌ | 75/100 [00:51<00:13, 1.92it/s]
76it [00:52, 1.31it/s]
76%|███████▌ | 76/100 [00:52<00:18, 1.31it/s]
77it [00:53, 1.50it/s]
77%|███████▋ | 77/100 [00:53<00:15, 1.50it/s]
78it [00:53, 1.67it/s]
78%|███████▊ | 78/100 [00:53<00:13, 1.67it/s]
79it [00:53, 1.81it/s]
79%|███████▉ | 79/100 [00:53<00:11, 1.81it/s]
80it [00:54, 1.92it/s]
80%|████████ | 80/100 [00:54<00:10, 1.92it/s]
81it [00:55, 1.31it/s]
81%|████████ | 81/100 [00:55<00:14, 1.31it/s]
82it [00:56, 1.50it/s]
82%|████████▏ | 82/100 [00:56<00:11, 1.50it/s]
83it [00:56, 1.67it/s]
83%|████████▎ | 83/100 [00:56<00:10, 1.67it/s]
84it [00:57, 1.81it/s]
84%|████████▍ | 84/100 [00:57<00:08, 1.81it/s]
85it [00:57, 1.92it/s]
85%|████████▌ | 85/100 [00:57<00:07, 1.92it/s]
86it [00:58, 1.31it/s]
86%|████████▌ | 86/100 [00:58<00:10, 1.31it/s]
87it [00:59, 1.50it/s]
87%|████████▋ | 87/100 [00:59<00:08, 1.50it/s]
88it [00:59, 1.67it/s]
88%|████████▊ | 88/100 [00:59<00:07, 1.67it/s]
89it [01:00, 1.81it/s]
89%|████████▉ | 89/100 [01:00<00:06, 1.81it/s]
90it [01:00, 1.92it/s]
90%|█████████ | 90/100 [01:00<00:05, 1.92it/s]
91it [01:01, 1.31it/s]
91%|█████████ | 91/100 [01:01<00:06, 1.31it/s]
92it [01:02, 1.50it/s]
92%|█████████▏| 92/100 [01:02<00:05, 1.50it/s]
93it [01:02, 1.67it/s]
93%|█████████▎| 93/100 [01:02<00:04, 1.67it/s]
94it [01:03, 1.81it/s]
94%|█████████▍| 94/100 [01:03<00:03, 1.81it/s]
95it [01:03, 1.92it/s]
95%|█████████▌| 95/100 [01:03<00:02, 1.92it/s]
96it [01:05, 1.31it/s]
96%|█████████▌| 96/100 [01:05<00:03, 1.31it/s]
97it [01:05, 1.50it/s]
97%|█████████▋| 97/100 [01:05<00:01, 1.50it/s]
98it [01:05, 1.67it/s]
98%|█████████▊| 98/100 [01:05<00:01, 1.67it/s]
99it [01:06, 1.81it/s]
99%|█████████▉| 99/100 [01:06<00:00, 1.81it/s]
100it [01:06, 1.92it/s]
100%|██████████| 100/100 [01:06<00:00, 1.92it/s]
100%|██████████| 100/100 [01:06<00:00, 1.50it/s]
100it [01:06, 1.50it/s]
Finished generating with seed 908426086