laion-ai / erlich

Generate a logo using text.

Cold

Public
349.3K runs
T4
GitHub
License

Run with an API

Playground API Examples README Versions

Prediction

laion-ai/erlich:d937c50007a1cacbdbd1e0a71ccaeac2b383a20f5579ea9b3f5ad46fcb2e2607

Model

laion-ai/erlich:d937c500

r5koa5tzs5f3fgrwdtek55uoaq

Status

Succeeded

Source

Web

Hardware

–

Total duration

2m 20s

Created

about 3 years ago

Input

seed: "-1"
steps: "75"
width: "256"
height: "256"
prompt: led zeppelin
batch_size: "6"
guidance_scale: "5"
aesthetic_rating: 9
aesthetic_weight: 0.5

{
  "seed": "-1",
  "steps": "75",
  "width": "256",
  "height": "256",
  "prompt": "led zeppelin",
  "batch_size": "6",
  "guidance_scale": "5",
  "aesthetic_rating": 9,
  "aesthetic_weight": 0.5
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "laion-ai/erlich:d937c50007a1cacbdbd1e0a71ccaeac2b383a20f5579ea9b3f5ad46fcb2e2607",
  {
    input: {
      seed: "-1",
      steps: "75",
      width: "256",
      height: "256",
      prompt: "led zeppelin",
      batch_size: "6",
      guidance_scale: "5",
      aesthetic_rating: 9,
      aesthetic_weight: 0.5
    }
  }
);

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

Import the client:

import replicate

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "laion-ai/erlich:d937c50007a1cacbdbd1e0a71ccaeac2b383a20f5579ea9b3f5ad46fcb2e2607",
    input={
        "seed": "-1",
        "steps": "75",
        "width": "256",
        "height": "256",
        "prompt": "led zeppelin",
        "batch_size": "6",
        "guidance_scale": "5",
        "aesthetic_rating": 9,
        "aesthetic_weight": 0.5
    }
)

# The laion-ai/erlich 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/erlich/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run laion-ai/erlich 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": "laion-ai/erlich:d937c50007a1cacbdbd1e0a71ccaeac2b383a20f5579ea9b3f5ad46fcb2e2607",
    "input": {
      "seed": "-1",
      "steps": "75",
      "width": "256",
      "height": "256",
      "prompt": "led zeppelin",
      "batch_size": "6",
      "guidance_scale": "5",
      "aesthetic_rating": 9,
      "aesthetic_weight": 0.5
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-06-24T23:10:32.870474Z",
  "created_at": "2022-06-24T23:08:13.014348Z",
  "data_removed": false,
  "error": null,
  "id": "r5koa5tzs5f3fgrwdtek55uoaq",
  "input": {
    "seed": "-1",
    "steps": "75",
    "width": "256",
    "height": "256",
    "prompt": "led zeppelin",
    "batch_size": "6",
    "guidance_scale": "5",
    "aesthetic_rating": 9,
    "aesthetic_weight": 0.5
  },
  "logs": "Using seed 944961095\nRunning simulation for led zeppelin\nEncoding text embeddings with led zeppelin dimensions\nUsing aesthetic embedding 9 with weight 0.5\nUsing inpaint model but no image is provided. Initializing with zeros.\nRunning diffusion...\n\n0it [00:00, ?it/s]\n\nTimestep 0 - saving sample\n  0%|          | 0/75 [00:00<?, ?it/s]\u001b[A\n1it [00:03,  3.27s/it]\n\n  1%|▏         | 1/75 [00:03<04:02,  3.27s/it]\u001b[A\n2it [00:05,  2.83s/it]\n\n  3%|▎         | 2/75 [00:05<03:26,  2.83s/it]\u001b[A\n3it [00:08,  2.69s/it]\n\n  4%|▍         | 3/75 [00:08<03:13,  2.69s/it]\u001b[A\n4it [00:08,  1.88s/it]\n\n  5%|▌         | 4/75 [00:08<02:13,  1.88s/it]\u001b[A\n5it [00:09,  1.43s/it]\n\n  7%|▋         | 5/75 [00:09<01:39,  1.43s/it]\u001b[A\n6it [00:10,  1.16s/it]\n\n  8%|▊         | 6/75 [00:10<01:19,  1.16s/it]\u001b[A\n7it [00:10,  1.01it/s]\n\n  9%|▉         | 7/75 [00:10<01:07,  1.01it/s]\u001b[A\n8it [00:11,  1.14it/s]\n\n 11%|█         | 8/75 [00:11<00:58,  1.14it/s]\u001b[A\n9it [00:12,  1.25it/s]\n\n 12%|█▏        | 9/75 [00:12<00:52,  1.25it/s]\u001b[A\n10it [00:12,  1.34it/s]\n\nTimestep 10 - saving sample\n 13%|█▎        | 10/75 [00:12<00:48,  1.34it/s]\u001b[A\n11it [00:14,  1.08it/s]\n\n 15%|█▍        | 11/75 [00:14<00:59,  1.08it/s]\u001b[A\n12it [00:14,  1.20it/s]\n\n 16%|█▌        | 12/75 [00:14<00:52,  1.20it/s]\u001b[A\n13it [00:15,  1.29it/s]\n\n 17%|█▋        | 13/75 [00:15<00:48,  1.29it/s]\u001b[A\n14it [00:15,  1.36it/s]\n\n 19%|█▊        | 14/75 [00:15<00:44,  1.36it/s]\u001b[A\n15it [00:16,  1.42it/s]\n\n 20%|██        | 15/75 [00:16<00:42,  1.42it/s]\u001b[A\n16it [00:17,  1.46it/s]\n\n 21%|██▏       | 16/75 [00:17<00:40,  1.46it/s]\u001b[A\n17it [00:17,  1.49it/s]\n\n 23%|██▎       | 17/75 [00:17<00:38,  1.49it/s]\u001b[A\n18it [00:18,  1.51it/s]\n\n 24%|██▍       | 18/75 [00:18<00:37,  1.51it/s]\u001b[A\n19it [00:19,  1.53it/s]\n\n 25%|██▌       | 19/75 [00:19<00:36,  1.53it/s]\u001b[A\n20it [00:19,  1.54it/s]\n\nTimestep 20 - saving sample\n 27%|██▋       | 20/75 [00:19<00:35,  1.54it/s]\u001b[A\n21it [00:21,  1.17it/s]\n\n 28%|██▊       | 21/75 [00:21<00:46,  1.17it/s]\u001b[A\n22it [00:21,  1.27it/s]\n\n 29%|██▉       | 22/75 [00:21<00:41,  1.27it/s]\u001b[A\n23it [00:22,  1.35it/s]\n\n 31%|███       | 23/75 [00:22<00:38,  1.35it/s]\u001b[A\n24it [00:23,  1.41it/s]\n\n 32%|███▏      | 24/75 [00:23<00:36,  1.41it/s]\u001b[A\n25it [00:23,  1.45it/s]\n\n 33%|███▎      | 25/75 [00:23<00:34,  1.45it/s]\u001b[A\n26it [00:24,  1.48it/s]\n\n 35%|███▍      | 26/75 [00:24<00:33,  1.48it/s]\u001b[A\n27it [00:24,  1.51it/s]\n\n 36%|███▌      | 27/75 [00:24<00:31,  1.51it/s]\u001b[A\n28it [00:25,  1.52it/s]\n\n 37%|███▋      | 28/75 [00:25<00:30,  1.52it/s]\u001b[A\n29it [00:26,  1.53it/s]\n\n 39%|███▊      | 29/75 [00:26<00:30,  1.53it/s]\u001b[A\n30it [00:26,  1.54it/s]\n\nTimestep 30 - saving sample\n 40%|████      | 30/75 [00:26<00:29,  1.54it/s]\u001b[A\n31it [00:28,  1.16it/s]\n\n 41%|████▏     | 31/75 [00:28<00:37,  1.16it/s]\u001b[A\n32it [00:28,  1.27it/s]\n\n 43%|████▎     | 32/75 [00:28<00:33,  1.27it/s]\u001b[A\n33it [00:29,  1.34it/s]\n\n 44%|████▍     | 33/75 [00:29<00:31,  1.34it/s]\u001b[A\n34it [00:30,  1.40it/s]\n\n 45%|████▌     | 34/75 [00:30<00:29,  1.40it/s]\u001b[A\n35it [00:30,  1.44it/s]\n\n 47%|████▋     | 35/75 [00:30<00:27,  1.44it/s]\u001b[A\n36it [00:31,  1.47it/s]\n\n 48%|████▊     | 36/75 [00:31<00:26,  1.47it/s]\u001b[A\n37it [00:32,  1.49it/s]\n\n 49%|████▉     | 37/75 [00:32<00:25,  1.49it/s]\u001b[A\n38it [00:32,  1.51it/s]\n\n 51%|█████     | 38/75 [00:32<00:24,  1.51it/s]\u001b[A\n39it [00:33,  1.52it/s]\n\n 52%|█████▏    | 39/75 [00:33<00:23,  1.52it/s]\u001b[A\n40it [00:34,  1.52it/s]\n\nTimestep 40 - saving sample\n 53%|█████▎    | 40/75 [00:34<00:22,  1.52it/s]\u001b[A\n41it [00:35,  1.16it/s]\n\n 55%|█████▍    | 41/75 [00:35<00:29,  1.16it/s]\u001b[A\n42it [00:36,  1.26it/s]\n\n 56%|█████▌    | 42/75 [00:36<00:26,  1.26it/s]\u001b[A\n43it [00:36,  1.33it/s]\n\n 57%|█████▋    | 43/75 [00:36<00:24,  1.33it/s]\u001b[A\n44it [00:37,  1.39it/s]\n\n 59%|█████▊    | 44/75 [00:37<00:22,  1.39it/s]\u001b[A\n45it [00:37,  1.43it/s]\n\n 60%|██████    | 45/75 [00:37<00:20,  1.43it/s]\u001b[A\n46it [00:38,  1.46it/s]\n\n 61%|██████▏   | 46/75 [00:38<00:19,  1.46it/s]\u001b[A\n47it [00:39,  1.49it/s]\n\n 63%|██████▎   | 47/75 [00:39<00:18,  1.49it/s]\u001b[A\n48it [00:39,  1.50it/s]\n\n 64%|██████▍   | 48/75 [00:39<00:17,  1.50it/s]\u001b[A\n49it [00:40,  1.51it/s]\n\n 65%|██████▌   | 49/75 [00:40<00:17,  1.51it/s]\u001b[A\n50it [00:41,  1.52it/s]\n\nTimestep 50 - saving sample\n 67%|██████▋   | 50/75 [00:41<00:16,  1.52it/s]\u001b[A\n51it [00:42,  1.15it/s]\n\n 68%|██████▊   | 51/75 [00:42<00:20,  1.15it/s]\u001b[A\n52it [00:43,  1.25it/s]\n\n 69%|██████▉   | 52/75 [00:43<00:18,  1.25it/s]\u001b[A\n53it [00:43,  1.32it/s]\n\n 71%|███████   | 53/75 [00:43<00:16,  1.32it/s]\u001b[A\n54it [00:44,  1.38it/s]\n\n 72%|███████▏  | 54/75 [00:44<00:15,  1.38it/s]\u001b[A\n55it [00:45,  1.42it/s]\n\n 73%|███████▎  | 55/75 [00:45<00:14,  1.42it/s]\u001b[A\n56it [00:45,  1.45it/s]\n\n 75%|███████▍  | 56/75 [00:45<00:13,  1.45it/s]\u001b[A\n57it [00:46,  1.47it/s]\n\n 76%|███████▌  | 57/75 [00:46<00:12,  1.47it/s]\u001b[A\n58it [00:47,  1.48it/s]\n\n 77%|███████▋  | 58/75 [00:47<00:11,  1.48it/s]\u001b[A\n59it [00:47,  1.49it/s]\n\n 79%|███████▊  | 59/75 [00:47<00:10,  1.49it/s]\u001b[A\n60it [00:48,  1.50it/s]\n\nTimestep 60 - saving sample\n 80%|████████  | 60/75 [00:48<00:10,  1.50it/s]\u001b[A\n61it [00:49,  1.14it/s]\n\n 81%|████████▏ | 61/75 [00:49<00:12,  1.14it/s]\u001b[A\n62it [00:50,  1.24it/s]\n\n 83%|████████▎ | 62/75 [00:50<00:10,  1.24it/s]\u001b[A\n63it [00:51,  1.31it/s]\n\n 84%|████████▍ | 63/75 [00:51<00:09,  1.31it/s]\u001b[A\n64it [00:51,  1.37it/s]\n\n 85%|████████▌ | 64/75 [00:51<00:08,  1.37it/s]\u001b[A\n65it [00:52,  1.41it/s]\n\n 87%|████████▋ | 65/75 [00:52<00:07,  1.41it/s]\u001b[A\n66it [00:53,  1.44it/s]\n\n 88%|████████▊ | 66/75 [00:53<00:06,  1.44it/s]\u001b[A\n67it [00:53,  1.46it/s]\n\n 89%|████████▉ | 67/75 [00:53<00:05,  1.46it/s]\u001b[A\n68it [00:54,  1.48it/s]\n\n 91%|█████████ | 68/75 [00:54<00:04,  1.48it/s]\u001b[A\n69it [00:55,  1.49it/s]\n\n 92%|█████████▏| 69/75 [00:55<00:04,  1.49it/s]\u001b[A\n70it [00:55,  1.49it/s]\n\nTimestep 70 - saving sample\n 93%|█████████▎| 70/75 [00:55<00:03,  1.49it/s]\u001b[A\n71it [00:57,  1.14it/s]\n\n 95%|█████████▍| 71/75 [00:57<00:03,  1.14it/s]\u001b[A\n72it [00:57,  1.23it/s]\n\n 96%|█████████▌| 72/75 [00:57<00:02,  1.23it/s]\u001b[A\n73it [00:58,  1.30it/s]\n\n 97%|█████████▋| 73/75 [00:58<00:01,  1.30it/s]\u001b[A\n74it [00:59,  1.35it/s]\n\nTimestep 74 - saving final sample\n 99%|█████████▊| 74/75 [00:59<00:00,  1.35it/s]\u001b[A\n75it [01:00,  1.08it/s]\n\n100%|██████████| 75/75 [01:00<00:00,  1.08it/s]\u001b[A\n100%|██████████| 75/75 [01:00<00:00,  1.24it/s]\n\n75it [01:00,  1.24it/s]",
  "metrics": {
    "predict_time": 65.193993,
    "total_time": 139.856126
  },
  "output": [
    [
      "https://replicate.delivery/mgxm/1c498631-870c-406a-a025-bd149a463551/current_0.jpg",
      "https://replicate.delivery/mgxm/c65d0815-8da5-4e57-ae3f-56e2fa20cc3b/current_1.jpg",
      "https://replicate.delivery/mgxm/7d0656ed-c8bd-449a-b83f-65acf63e480e/current_2.jpg",
      "https://replicate.delivery/mgxm/85af7b2d-2945-4053-8e19-1f5c1d9f0d8e/current_3.jpg",
      "https://replicate.delivery/mgxm/73d89b4c-85c0-4dc7-90d6-2af31c4d12d6/current_4.jpg",
      "https://replicate.delivery/mgxm/70a1f94a-7feb-4144-8f8f-b8f7885a45d5/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/93a73cd7-47ed-459f-993a-88dbc29964e5/current_0.jpg",
      "https://replicate.delivery/mgxm/bd67f2bd-eda5-4956-85ea-b986b357f494/current_1.jpg",
      "https://replicate.delivery/mgxm/ab80dc75-39b0-49cd-893b-e7cfeb8c2a33/current_2.jpg",
      "https://replicate.delivery/mgxm/c8191fda-2adc-409c-b2d4-e29789c922bc/current_3.jpg",
      "https://replicate.delivery/mgxm/f690645f-b280-4994-83d9-832bdf8f1026/current_4.jpg",
      "https://replicate.delivery/mgxm/5d0038e7-b396-425e-b6b4-91ecca23557e/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/e135163c-cb3a-4fbe-94c7-caf75d6db47c/current_0.jpg",
      "https://replicate.delivery/mgxm/b7afaf95-4914-4758-beaa-9702ccb53789/current_1.jpg",
      "https://replicate.delivery/mgxm/9c50cfe9-6e34-438f-9458-5273b8857a80/current_2.jpg",
      "https://replicate.delivery/mgxm/bb45d61f-a21a-448c-9f8f-cebb1f584027/current_3.jpg",
      "https://replicate.delivery/mgxm/4286d049-0421-485b-a3bf-0f083a90109e/current_4.jpg",
      "https://replicate.delivery/mgxm/90d75832-bca1-40de-aee8-e4f10c88c6f7/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/53a8fa12-d2d5-43e3-9a6d-20a9a2488ca3/current_0.jpg",
      "https://replicate.delivery/mgxm/2ce8e69b-090e-46db-92db-aad501731b87/current_1.jpg",
      "https://replicate.delivery/mgxm/d14e461c-3e86-4a38-b98f-4fccf00e0fb6/current_2.jpg",
      "https://replicate.delivery/mgxm/7f3edbda-8b9f-42ef-8117-a06059e08030/current_3.jpg",
      "https://replicate.delivery/mgxm/0c1eee6f-6f69-46ad-8358-47046615d451/current_4.jpg",
      "https://replicate.delivery/mgxm/0f1e3303-17bd-4824-9bca-c8edd322dfa8/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/354c4f6c-a88e-4d03-8a38-f3f25fb0e052/current_0.jpg",
      "https://replicate.delivery/mgxm/38eb771a-bd17-4c81-a3ab-2afe79e67ebe/current_1.jpg",
      "https://replicate.delivery/mgxm/494e5fb6-bb40-4c18-adf2-48a7829b58d4/current_2.jpg",
      "https://replicate.delivery/mgxm/9e0e5ba1-1229-450a-ba0d-cfd7bddc859f/current_3.jpg",
      "https://replicate.delivery/mgxm/b43a919b-6199-488d-8660-4ad5e953484f/current_4.jpg",
      "https://replicate.delivery/mgxm/ec53f571-93b0-40dd-9815-19e32edf4ec0/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/48a41eeb-8ec7-46a5-9609-d52a4ab9e0ad/current_0.jpg",
      "https://replicate.delivery/mgxm/20eead7c-6784-494f-ac09-3a053ebecccf/current_1.jpg",
      "https://replicate.delivery/mgxm/0d1723bd-4fbd-4b48-bdc2-9b0847dd5629/current_2.jpg",
      "https://replicate.delivery/mgxm/639d1511-db2c-4a39-981c-e04f110ac9aa/current_3.jpg",
      "https://replicate.delivery/mgxm/82c793a2-049b-49b6-aee4-83353a58e5fe/current_4.jpg",
      "https://replicate.delivery/mgxm/3403739f-9b8c-4325-aee5-7f8300a082a2/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/0b0c0cb0-0253-41e6-a72c-291fa4549932/current_0.jpg",
      "https://replicate.delivery/mgxm/887ec673-0193-44e5-baba-4ea780be1d61/current_1.jpg",
      "https://replicate.delivery/mgxm/deb9caf9-3cc1-4d25-b3a0-d9c2f9d4446e/current_2.jpg",
      "https://replicate.delivery/mgxm/c6c296bf-412c-4695-8f34-88033bfe5153/current_3.jpg",
      "https://replicate.delivery/mgxm/f19a5dd3-ed7b-4984-bf89-c14f81e55666/current_4.jpg",
      "https://replicate.delivery/mgxm/8fe70da1-ad6c-4b5e-92b5-a7182bb53399/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/0b779308-36e1-4e34-934e-a645ac188ea5/current_0.jpg",
      "https://replicate.delivery/mgxm/29e2b21e-cb35-4c97-9a81-05b0ebb69dbc/current_1.jpg",
      "https://replicate.delivery/mgxm/ed43ed37-1f8e-4722-a724-436ed31fec2e/current_2.jpg",
      "https://replicate.delivery/mgxm/1b69fc21-4c6c-45e7-bacf-de6d4eafa1a1/current_3.jpg",
      "https://replicate.delivery/mgxm/ec2da6cc-b784-4c8e-b58c-d9d3951a62c3/current_4.jpg",
      "https://replicate.delivery/mgxm/298a98ee-8d1f-470d-aa1d-c7d0c81155a4/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/ff49fa28-6ed5-4979-b165-a12796dde961/current_0.jpg",
      "https://replicate.delivery/mgxm/6b4639d8-4f12-486e-9c7c-624eaa2a74c8/current_1.jpg",
      "https://replicate.delivery/mgxm/ed075811-c996-4512-a7b4-1d3c2832a4b8/current_2.jpg",
      "https://replicate.delivery/mgxm/d4ac32a4-fa9a-4c7c-b38a-8cce7510e272/current_3.jpg",
      "https://replicate.delivery/mgxm/3a533a0f-9ba3-4363-b7cb-a8be42d8caa5/current_4.jpg",
      "https://replicate.delivery/mgxm/a5be196c-457c-4878-ac36-cb06275b8bbc/current_5.jpg"
    ]
  ],
  "started_at": "2022-06-24T23:09:27.676481Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/r5koa5tzs5f3fgrwdtek55uoaq",
    "cancel": "https://api.replicate.com/v1/predictions/r5koa5tzs5f3fgrwdtek55uoaq/cancel"
  },
  "version": "d937c50007a1cacbdbd1e0a71ccaeac2b383a20f5579ea9b3f5ad46fcb2e2607"
}

Generated in

65.2 seconds

Tweak it ShareReport

Using seed 944961095
Running simulation for led zeppelin
Encoding text embeddings with led zeppelin dimensions
Using aesthetic embedding 9 with weight 0.5
Using inpaint model but no image is provided. Initializing with zeros.
Running diffusion...

0it [00:00, ?it/s]

Timestep 0 - saving sample
  0%|          | 0/75 [00:00<?, ?it/s]
1it [00:03,  3.27s/it]

  1%|▏         | 1/75 [00:03<04:02,  3.27s/it]
2it [00:05,  2.83s/it]

  3%|▎         | 2/75 [00:05<03:26,  2.83s/it]
3it [00:08,  2.69s/it]

  4%|▍         | 3/75 [00:08<03:13,  2.69s/it]
4it [00:08,  1.88s/it]

  5%|▌         | 4/75 [00:08<02:13,  1.88s/it]
5it [00:09,  1.43s/it]

  7%|▋         | 5/75 [00:09<01:39,  1.43s/it]
6it [00:10,  1.16s/it]

  8%|▊         | 6/75 [00:10<01:19,  1.16s/it]
7it [00:10,  1.01it/s]

  9%|▉         | 7/75 [00:10<01:07,  1.01it/s]
8it [00:11,  1.14it/s]

 11%|█         | 8/75 [00:11<00:58,  1.14it/s]
9it [00:12,  1.25it/s]

 12%|█▏        | 9/75 [00:12<00:52,  1.25it/s]
10it [00:12,  1.34it/s]

Timestep 10 - saving sample
 13%|█▎        | 10/75 [00:12<00:48,  1.34it/s]
11it [00:14,  1.08it/s]

 15%|█▍        | 11/75 [00:14<00:59,  1.08it/s]
12it [00:14,  1.20it/s]

 16%|█▌        | 12/75 [00:14<00:52,  1.20it/s]
13it [00:15,  1.29it/s]

 17%|█▋        | 13/75 [00:15<00:48,  1.29it/s]
14it [00:15,  1.36it/s]

 19%|█▊        | 14/75 [00:15<00:44,  1.36it/s]
15it [00:16,  1.42it/s]

 20%|██        | 15/75 [00:16<00:42,  1.42it/s]
16it [00:17,  1.46it/s]

 21%|██▏       | 16/75 [00:17<00:40,  1.46it/s]
17it [00:17,  1.49it/s]

 23%|██▎       | 17/75 [00:17<00:38,  1.49it/s]
18it [00:18,  1.51it/s]

 24%|██▍       | 18/75 [00:18<00:37,  1.51it/s]
19it [00:19,  1.53it/s]

 25%|██▌       | 19/75 [00:19<00:36,  1.53it/s]
20it [00:19,  1.54it/s]

Timestep 20 - saving sample
 27%|██▋       | 20/75 [00:19<00:35,  1.54it/s]
21it [00:21,  1.17it/s]

 28%|██▊       | 21/75 [00:21<00:46,  1.17it/s]
22it [00:21,  1.27it/s]

 29%|██▉       | 22/75 [00:21<00:41,  1.27it/s]
23it [00:22,  1.35it/s]

 31%|███       | 23/75 [00:22<00:38,  1.35it/s]
24it [00:23,  1.41it/s]

 32%|███▏      | 24/75 [00:23<00:36,  1.41it/s]
25it [00:23,  1.45it/s]

 33%|███▎      | 25/75 [00:23<00:34,  1.45it/s]
26it [00:24,  1.48it/s]

 35%|███▍      | 26/75 [00:24<00:33,  1.48it/s]
27it [00:24,  1.51it/s]

 36%|███▌      | 27/75 [00:24<00:31,  1.51it/s]
28it [00:25,  1.52it/s]

 37%|███▋      | 28/75 [00:25<00:30,  1.52it/s]
29it [00:26,  1.53it/s]

 39%|███▊      | 29/75 [00:26<00:30,  1.53it/s]
30it [00:26,  1.54it/s]

Timestep 30 - saving sample
 40%|████      | 30/75 [00:26<00:29,  1.54it/s]
31it [00:28,  1.16it/s]

 41%|████▏     | 31/75 [00:28<00:37,  1.16it/s]
32it [00:28,  1.27it/s]

 43%|████▎     | 32/75 [00:28<00:33,  1.27it/s]
33it [00:29,  1.34it/s]

 44%|████▍     | 33/75 [00:29<00:31,  1.34it/s]
34it [00:30,  1.40it/s]

 45%|████▌     | 34/75 [00:30<00:29,  1.40it/s]
35it [00:30,  1.44it/s]

 47%|████▋     | 35/75 [00:30<00:27,  1.44it/s]
36it [00:31,  1.47it/s]

 48%|████▊     | 36/75 [00:31<00:26,  1.47it/s]
37it [00:32,  1.49it/s]

 49%|████▉     | 37/75 [00:32<00:25,  1.49it/s]
38it [00:32,  1.51it/s]

 51%|█████     | 38/75 [00:32<00:24,  1.51it/s]
39it [00:33,  1.52it/s]

 52%|█████▏    | 39/75 [00:33<00:23,  1.52it/s]
40it [00:34,  1.52it/s]

Timestep 40 - saving sample
 53%|█████▎    | 40/75 [00:34<00:22,  1.52it/s]
41it [00:35,  1.16it/s]

 55%|█████▍    | 41/75 [00:35<00:29,  1.16it/s]
42it [00:36,  1.26it/s]

 56%|█████▌    | 42/75 [00:36<00:26,  1.26it/s]
43it [00:36,  1.33it/s]

 57%|█████▋    | 43/75 [00:36<00:24,  1.33it/s]
44it [00:37,  1.39it/s]

 59%|█████▊    | 44/75 [00:37<00:22,  1.39it/s]
45it [00:37,  1.43it/s]

 60%|██████    | 45/75 [00:37<00:20,  1.43it/s]
46it [00:38,  1.46it/s]

 61%|██████▏   | 46/75 [00:38<00:19,  1.46it/s]
47it [00:39,  1.49it/s]

 63%|██████▎   | 47/75 [00:39<00:18,  1.49it/s]
48it [00:39,  1.50it/s]

 64%|██████▍   | 48/75 [00:39<00:17,  1.50it/s]
49it [00:40,  1.51it/s]

 65%|██████▌   | 49/75 [00:40<00:17,  1.51it/s]
50it [00:41,  1.52it/s]

Timestep 50 - saving sample
 67%|██████▋   | 50/75 [00:41<00:16,  1.52it/s]
51it [00:42,  1.15it/s]

 68%|██████▊   | 51/75 [00:42<00:20,  1.15it/s]
52it [00:43,  1.25it/s]

 69%|██████▉   | 52/75 [00:43<00:18,  1.25it/s]
53it [00:43,  1.32it/s]

 71%|███████   | 53/75 [00:43<00:16,  1.32it/s]
54it [00:44,  1.38it/s]

 72%|███████▏  | 54/75 [00:44<00:15,  1.38it/s]
55it [00:45,  1.42it/s]

 73%|███████▎  | 55/75 [00:45<00:14,  1.42it/s]
56it [00:45,  1.45it/s]

 75%|███████▍  | 56/75 [00:45<00:13,  1.45it/s]
57it [00:46,  1.47it/s]

 76%|███████▌  | 57/75 [00:46<00:12,  1.47it/s]
58it [00:47,  1.48it/s]

 77%|███████▋  | 58/75 [00:47<00:11,  1.48it/s]
59it [00:47,  1.49it/s]

 79%|███████▊  | 59/75 [00:47<00:10,  1.49it/s]
60it [00:48,  1.50it/s]

Timestep 60 - saving sample
 80%|████████  | 60/75 [00:48<00:10,  1.50it/s]
61it [00:49,  1.14it/s]

 81%|████████▏ | 61/75 [00:49<00:12,  1.14it/s]
62it [00:50,  1.24it/s]

 83%|████████▎ | 62/75 [00:50<00:10,  1.24it/s]
63it [00:51,  1.31it/s]

 84%|████████▍ | 63/75 [00:51<00:09,  1.31it/s]
64it [00:51,  1.37it/s]

 85%|████████▌ | 64/75 [00:51<00:08,  1.37it/s]
65it [00:52,  1.41it/s]

 87%|████████▋ | 65/75 [00:52<00:07,  1.41it/s]
66it [00:53,  1.44it/s]

 88%|████████▊ | 66/75 [00:53<00:06,  1.44it/s]
67it [00:53,  1.46it/s]

 89%|████████▉ | 67/75 [00:53<00:05,  1.46it/s]
68it [00:54,  1.48it/s]

 91%|█████████ | 68/75 [00:54<00:04,  1.48it/s]
69it [00:55,  1.49it/s]

 92%|█████████▏| 69/75 [00:55<00:04,  1.49it/s]
70it [00:55,  1.49it/s]

Timestep 70 - saving sample
 93%|█████████▎| 70/75 [00:55<00:03,  1.49it/s]
71it [00:57,  1.14it/s]

 95%|█████████▍| 71/75 [00:57<00:03,  1.14it/s]
72it [00:57,  1.23it/s]

 96%|█████████▌| 72/75 [00:57<00:02,  1.23it/s]
73it [00:58,  1.30it/s]

 97%|█████████▋| 73/75 [00:58<00:01,  1.30it/s]
74it [00:59,  1.35it/s]

Timestep 74 - saving final sample
 99%|█████████▊| 74/75 [00:59<00:00,  1.35it/s]
75it [01:00,  1.08it/s]

100%|██████████| 75/75 [01:00<00:00,  1.08it/s]
100%|██████████| 75/75 [01:00<00:00,  1.24it/s]

75it [01:00,  1.24it/s]

Prediction

laion-ai/erlich:d937c50007a1cacbdbd1e0a71ccaeac2b383a20f5579ea9b3f5ad46fcb2e2607

Model

laion-ai/erlich:d937c500

v2onktt7yjalpglsu4apogpcnm

Status

Succeeded

Source

Web

Hardware

–

Total duration

Created

about 3 years ago

Input

seed: "-1"
steps: "75"
width: "256"
height: "256"
prompt: pink floyd
batch_size: "6"
guidance_scale: "5"
aesthetic_rating: 9
aesthetic_weight: 0.5

{
  "seed": "-1",
  "steps": "75",
  "width": "256",
  "height": "256",
  "prompt": "pink floyd",
  "batch_size": "6",
  "guidance_scale": "5",
  "aesthetic_rating": 9,
  "aesthetic_weight": 0.5
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "laion-ai/erlich:d937c50007a1cacbdbd1e0a71ccaeac2b383a20f5579ea9b3f5ad46fcb2e2607",
  {
    input: {
      seed: "-1",
      steps: "75",
      width: "256",
      height: "256",
      prompt: "pink floyd",
      batch_size: "6",
      guidance_scale: "5",
      aesthetic_rating: 9,
      aesthetic_weight: 0.5
    }
  }
);

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

Import the client:

import replicate

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "laion-ai/erlich:d937c50007a1cacbdbd1e0a71ccaeac2b383a20f5579ea9b3f5ad46fcb2e2607",
    input={
        "seed": "-1",
        "steps": "75",
        "width": "256",
        "height": "256",
        "prompt": "pink floyd",
        "batch_size": "6",
        "guidance_scale": "5",
        "aesthetic_rating": 9,
        "aesthetic_weight": 0.5
    }
)

# The laion-ai/erlich 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/erlich/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run laion-ai/erlich 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": "laion-ai/erlich:d937c50007a1cacbdbd1e0a71ccaeac2b383a20f5579ea9b3f5ad46fcb2e2607",
    "input": {
      "seed": "-1",
      "steps": "75",
      "width": "256",
      "height": "256",
      "prompt": "pink floyd",
      "batch_size": "6",
      "guidance_scale": "5",
      "aesthetic_rating": 9,
      "aesthetic_weight": 0.5
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-06-24T23:17:04.794145Z",
  "created_at": "2022-06-24T23:14:03.423862Z",
  "data_removed": false,
  "error": null,
  "id": "v2onktt7yjalpglsu4apogpcnm",
  "input": {
    "seed": "-1",
    "steps": "75",
    "width": "256",
    "height": "256",
    "prompt": "pink floyd",
    "batch_size": "6",
    "guidance_scale": "5",
    "aesthetic_rating": 9,
    "aesthetic_weight": 0.5
  },
  "logs": "Using seed 2401128644\nRunning simulation for pink floyd\nEncoding text embeddings with pink floyd dimensions\nUsing aesthetic embedding 9 with weight 0.5\nUsing inpaint model but no image is provided. Initializing with zeros.\nRunning diffusion...\n\n0it [00:00, ?it/s]\n\nTimestep 0 - saving sample\n  0%|          | 0/75 [00:00<?, ?it/s]\u001b[A\n1it [00:03,  3.37s/it]\n\n  1%|▏         | 1/75 [00:03<04:09,  3.37s/it]\u001b[A\n2it [00:05,  2.90s/it]\n\n  3%|▎         | 2/75 [00:05<03:32,  2.90s/it]\u001b[A\n3it [00:08,  2.76s/it]\n\n  4%|▍         | 3/75 [00:08<03:18,  2.76s/it]\u001b[A\n4it [00:09,  1.93s/it]\n\n  5%|▌         | 4/75 [00:09<02:16,  1.93s/it]\u001b[A\n5it [00:09,  1.47s/it]\n\n  7%|▋         | 5/75 [00:09<01:42,  1.47s/it]\u001b[A\n6it [00:10,  1.19s/it]\n\n  8%|▊         | 6/75 [00:10<01:22,  1.19s/it]\u001b[A\n7it [00:11,  1.01s/it]\n\n  9%|▉         | 7/75 [00:11<01:08,  1.01s/it]\u001b[A\n8it [00:11,  1.11it/s]\n\n 11%|█         | 8/75 [00:11<01:00,  1.11it/s]\u001b[A\n9it [00:12,  1.22it/s]\n\n 12%|█▏        | 9/75 [00:12<00:54,  1.22it/s]\u001b[A\n10it [00:13,  1.30it/s]\n\nTimestep 10 - saving sample\n 13%|█▎        | 10/75 [00:13<00:49,  1.30it/s]\u001b[A\n11it [00:14,  1.05it/s]\n\n 15%|█▍        | 11/75 [00:14<01:00,  1.05it/s]\u001b[A\n12it [00:15,  1.17it/s]\n\n 16%|█▌        | 12/75 [00:15<00:53,  1.17it/s]\u001b[A\n13it [00:15,  1.26it/s]\n\n 17%|█▋        | 13/75 [00:15<00:49,  1.26it/s]\u001b[A\n14it [00:16,  1.33it/s]\n\n 19%|█▊        | 14/75 [00:16<00:45,  1.33it/s]\u001b[A\n15it [00:17,  1.38it/s]\n\n 20%|██        | 15/75 [00:17<00:43,  1.38it/s]\u001b[A\n16it [00:17,  1.42it/s]\n\n 21%|██▏       | 16/75 [00:17<00:41,  1.42it/s]\u001b[A\n17it [00:18,  1.45it/s]\n\n 23%|██▎       | 17/75 [00:18<00:40,  1.45it/s]\u001b[A\n18it [00:19,  1.47it/s]\n\n 24%|██▍       | 18/75 [00:19<00:38,  1.47it/s]\u001b[A\n19it [00:19,  1.48it/s]\n\n 25%|██▌       | 19/75 [00:19<00:37,  1.48it/s]\u001b[A\n20it [00:20,  1.49it/s]\n\nTimestep 20 - saving sample\n 27%|██▋       | 20/75 [00:20<00:36,  1.49it/s]\u001b[A\n21it [00:21,  1.14it/s]\n\n 28%|██▊       | 21/75 [00:21<00:47,  1.14it/s]\u001b[A\n22it [00:22,  1.24it/s]\n\n 29%|██▉       | 22/75 [00:22<00:42,  1.24it/s]\u001b[A\n23it [00:23,  1.31it/s]\n\n 31%|███       | 23/75 [00:23<00:39,  1.31it/s]\u001b[A\n24it [00:23,  1.37it/s]\n\n 32%|███▏      | 24/75 [00:23<00:37,  1.37it/s]\u001b[A\n25it [00:24,  1.41it/s]\n\n 33%|███▎      | 25/75 [00:24<00:35,  1.41it/s]\u001b[A\n26it [00:24,  1.44it/s]\n\n 35%|███▍      | 26/75 [00:24<00:34,  1.44it/s]\u001b[A\n27it [00:25,  1.46it/s]\n\n 36%|███▌      | 27/75 [00:25<00:32,  1.46it/s]\u001b[A\n28it [00:26,  1.48it/s]\n\n 37%|███▋      | 28/75 [00:26<00:31,  1.48it/s]\u001b[A\n29it [00:26,  1.49it/s]\n\n 39%|███▊      | 29/75 [00:26<00:30,  1.49it/s]\u001b[A\n30it [00:27,  1.50it/s]\n\nTimestep 30 - saving sample\n 40%|████      | 30/75 [00:27<00:30,  1.50it/s]\u001b[A\n31it [00:28,  1.14it/s]\n\n 41%|████▏     | 31/75 [00:28<00:38,  1.14it/s]\u001b[A\n32it [00:29,  1.23it/s]\n\n 43%|████▎     | 32/75 [00:29<00:34,  1.23it/s]\u001b[A\n33it [00:30,  1.30it/s]\n\n 44%|████▍     | 33/75 [00:30<00:32,  1.30it/s]\u001b[A\n34it [00:30,  1.36it/s]\n\n 45%|████▌     | 34/75 [00:30<00:30,  1.36it/s]\u001b[A\n35it [00:31,  1.40it/s]\n\n 47%|████▋     | 35/75 [00:31<00:28,  1.40it/s]\u001b[A\n36it [00:32,  1.43it/s]\n\n 48%|████▊     | 36/75 [00:32<00:27,  1.43it/s]\u001b[A\n37it [00:32,  1.45it/s]\n\n 49%|████▉     | 37/75 [00:32<00:26,  1.45it/s]\u001b[A\n38it [00:33,  1.47it/s]\n\n 51%|█████     | 38/75 [00:33<00:25,  1.47it/s]\u001b[A\n39it [00:34,  1.47it/s]\n\n 52%|█████▏    | 39/75 [00:34<00:24,  1.47it/s]\u001b[A\n40it [00:34,  1.48it/s]\n\nTimestep 40 - saving sample\n 53%|█████▎    | 40/75 [00:34<00:23,  1.48it/s]\u001b[A\n41it [00:36,  1.11it/s]\n\n 55%|█████▍    | 41/75 [00:36<00:30,  1.11it/s]\u001b[A\n42it [00:37,  1.21it/s]\n\n 56%|█████▌    | 42/75 [00:37<00:27,  1.21it/s]\u001b[A\n43it [00:37,  1.28it/s]\n\n 57%|█████▋    | 43/75 [00:37<00:25,  1.28it/s]\u001b[A\n44it [00:38,  1.33it/s]\n\n 59%|█████▊    | 44/75 [00:38<00:23,  1.33it/s]\u001b[A\n45it [00:39,  1.38it/s]\n\n 60%|██████    | 45/75 [00:39<00:21,  1.38it/s]\u001b[A\n46it [00:39,  1.41it/s]\n\n 61%|██████▏   | 46/75 [00:39<00:20,  1.41it/s]\u001b[A\n47it [00:40,  1.43it/s]\n\n 63%|██████▎   | 47/75 [00:40<00:19,  1.43it/s]\u001b[A\n48it [00:41,  1.45it/s]\n\n 64%|██████▍   | 48/75 [00:41<00:18,  1.45it/s]\u001b[A\n49it [00:41,  1.46it/s]\n\n 65%|██████▌   | 49/75 [00:41<00:17,  1.46it/s]\u001b[A\n50it [00:42,  1.46it/s]\n\nTimestep 50 - saving sample\n 67%|██████▋   | 50/75 [00:42<00:17,  1.46it/s]\u001b[A\n51it [00:44,  1.00s/it]\n\n 68%|██████▊   | 51/75 [00:44<00:24,  1.00s/it]\u001b[A\n52it [00:44,  1.12it/s]\n\n 69%|██████▉   | 52/75 [00:44<00:20,  1.12it/s]\u001b[A\n53it [00:45,  1.21it/s]\n\n 71%|███████   | 53/75 [00:45<00:18,  1.21it/s]\u001b[A\n54it [00:46,  1.28it/s]\n\n 72%|███████▏  | 54/75 [00:46<00:16,  1.28it/s]\u001b[A\n55it [00:46,  1.34it/s]\n\n 73%|███████▎  | 55/75 [00:46<00:14,  1.34it/s]\u001b[A\n56it [00:47,  1.38it/s]\n\n 75%|███████▍  | 56/75 [00:47<00:13,  1.38it/s]\u001b[A\n57it [00:48,  1.41it/s]\n\n 76%|███████▌  | 57/75 [00:48<00:12,  1.41it/s]\u001b[A\n58it [00:48,  1.43it/s]\n\n 77%|███████▋  | 58/75 [00:48<00:11,  1.43it/s]\u001b[A\n59it [00:49,  1.45it/s]\n\n 79%|███████▊  | 59/75 [00:49<00:11,  1.45it/s]\u001b[A\n60it [00:50,  1.46it/s]\n\nTimestep 60 - saving sample\n 80%|████████  | 60/75 [00:50<00:10,  1.46it/s]\u001b[A\n61it [00:51,  1.03it/s]\n\n 81%|████████▏ | 61/75 [00:51<00:13,  1.03it/s]\u001b[A\n62it [00:52,  1.14it/s]\n\n 83%|████████▎ | 62/75 [00:52<00:11,  1.14it/s]\u001b[A\n63it [00:53,  1.22it/s]\n\n 84%|████████▍ | 63/75 [00:53<00:09,  1.22it/s]\u001b[A\n64it [00:53,  1.28it/s]\n\n 85%|████████▌ | 64/75 [00:53<00:08,  1.28it/s]\u001b[A\n65it [00:54,  1.34it/s]\n\n 87%|████████▋ | 65/75 [00:54<00:07,  1.34it/s]\u001b[A\n66it [00:55,  1.37it/s]\n\n 88%|████████▊ | 66/75 [00:55<00:06,  1.37it/s]\u001b[A\n67it [00:55,  1.39it/s]\n\n 89%|████████▉ | 67/75 [00:55<00:05,  1.39it/s]\u001b[A\n68it [00:56,  1.42it/s]\n\n 91%|█████████ | 68/75 [00:56<00:04,  1.42it/s]\u001b[A\n69it [00:57,  1.43it/s]\n\n 92%|█████████▏| 69/75 [00:57<00:04,  1.43it/s]\u001b[A\n70it [00:57,  1.44it/s]\n\nTimestep 70 - saving sample\n 93%|█████████▎| 70/75 [00:57<00:03,  1.44it/s]\u001b[A\n71it [00:59,  1.02it/s]\n\n 95%|█████████▍| 71/75 [00:59<00:03,  1.02it/s]\u001b[A\n72it [01:00,  1.14it/s]\n\n 96%|█████████▌| 72/75 [01:00<00:02,  1.14it/s]\u001b[A\n73it [01:00,  1.20it/s]\n\n 97%|█████████▋| 73/75 [01:00<00:01,  1.20it/s]\u001b[A\n74it [01:01,  1.26it/s]\n\nTimestep 74 - saving final sample\n 99%|█████████▊| 74/75 [01:01<00:00,  1.26it/s]\u001b[A\n75it [01:03,  1.06s/it]\n\n100%|██████████| 75/75 [01:03<00:00,  1.06s/it]\u001b[A\n100%|██████████| 75/75 [01:03<00:00,  1.18it/s]\n\n75it [01:03,  1.18it/s]",
  "metrics": {
    "predict_time": 68.094431,
    "total_time": 181.370283
  },
  "output": [
    [
      "https://replicate.delivery/mgxm/db5f4b35-ec70-4659-b915-ed3994f15f5b/current_0.jpg",
      "https://replicate.delivery/mgxm/031638d7-e18d-4b9c-ab74-88b81a52f87d/current_1.jpg",
      "https://replicate.delivery/mgxm/42bc7b01-ec71-40e2-82ba-86430b43cc34/current_2.jpg",
      "https://replicate.delivery/mgxm/77295f24-2599-4b9e-a7c0-90b22d1d5f94/current_3.jpg",
      "https://replicate.delivery/mgxm/a9c9d85c-7643-40bb-b907-7974a0fd3254/current_4.jpg",
      "https://replicate.delivery/mgxm/ff59763d-2ec0-4cec-8b33-4b0a154ff7d6/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/ce97a926-ab91-45dd-82af-09869de41048/current_0.jpg",
      "https://replicate.delivery/mgxm/c16273ae-ce9c-44c9-b236-63fbae22aaca/current_1.jpg",
      "https://replicate.delivery/mgxm/e4419965-98d7-44cd-a24f-23a1986f2a75/current_2.jpg",
      "https://replicate.delivery/mgxm/62832539-8338-4e7a-b4ae-f45d7cf84555/current_3.jpg",
      "https://replicate.delivery/mgxm/9d4ac715-5fe2-4915-b76f-220238a2ecac/current_4.jpg",
      "https://replicate.delivery/mgxm/7596c11e-2b1e-4d85-b8e2-42142db4d2a9/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/d906a739-239a-4df8-9b90-5ed76cdd3df0/current_0.jpg",
      "https://replicate.delivery/mgxm/42dca56c-b4ff-4cce-b8d4-6fd56c3f10fd/current_1.jpg",
      "https://replicate.delivery/mgxm/8bdeba9c-9a99-4852-ba2a-606b6f03b72c/current_2.jpg",
      "https://replicate.delivery/mgxm/26342173-0d0e-4a0e-bb4e-e51c4dfc3926/current_3.jpg",
      "https://replicate.delivery/mgxm/da58b363-eecd-47f5-ae1e-7e9301970130/current_4.jpg",
      "https://replicate.delivery/mgxm/132c0086-560a-43f9-9dcd-bebff2733832/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/3320b654-4f60-4c42-a457-22398cb15f82/current_0.jpg",
      "https://replicate.delivery/mgxm/9f27a862-f46d-4d4e-8a69-f8ab89b92927/current_1.jpg",
      "https://replicate.delivery/mgxm/c86c8885-37f3-42d0-be32-9cd8d9bcde48/current_2.jpg",
      "https://replicate.delivery/mgxm/2f2c13e0-7c90-4c01-aa29-4f1c3d7f031e/current_3.jpg",
      "https://replicate.delivery/mgxm/5066a84f-8058-4cc8-ae48-cf6fe35df93c/current_4.jpg",
      "https://replicate.delivery/mgxm/c2f15f02-c3de-4711-982e-65347e3cc559/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/e46d2fff-66f5-473c-838c-2e816e3a18be/current_0.jpg",
      "https://replicate.delivery/mgxm/0561ae73-07d1-4203-b45e-76025909509c/current_1.jpg",
      "https://replicate.delivery/mgxm/7c3c5bb6-e0c3-4a61-9537-552a94176350/current_2.jpg",
      "https://replicate.delivery/mgxm/77bcf163-98b2-4ef4-b31d-684a652d92ed/current_3.jpg",
      "https://replicate.delivery/mgxm/1b8d3cdc-63e9-4707-a8df-a0af4a63e798/current_4.jpg",
      "https://replicate.delivery/mgxm/929d7ab3-97d9-4b50-b3ab-a35dde593af0/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/acb7bb06-6444-4352-b570-8d2a84b95442/current_0.jpg",
      "https://replicate.delivery/mgxm/5fb0e81d-feb9-4ad3-bfb3-140af12c5a83/current_1.jpg",
      "https://replicate.delivery/mgxm/70b7cb09-e777-41e2-ab3c-0d6cb429ff2e/current_2.jpg",
      "https://replicate.delivery/mgxm/740a1f1f-597e-4202-9fb5-1442e326b16d/current_3.jpg",
      "https://replicate.delivery/mgxm/ad78e4cc-1604-4523-a35b-f564313adb90/current_4.jpg",
      "https://replicate.delivery/mgxm/5cad09f2-8259-4ec8-9f1a-c32451f3ad2d/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/25932139-98f0-4a41-a5c6-d4246d6c8e6e/current_0.jpg",
      "https://replicate.delivery/mgxm/6318cb0e-8e7f-4687-9182-b51f8761d484/current_1.jpg",
      "https://replicate.delivery/mgxm/77a9daf1-215d-477d-b85f-c863ea622b9a/current_2.jpg",
      "https://replicate.delivery/mgxm/053e9908-fd68-4dbc-a232-7ffa5bdb5177/current_3.jpg",
      "https://replicate.delivery/mgxm/877084f3-eec4-44f6-b260-bff7d380cf55/current_4.jpg",
      "https://replicate.delivery/mgxm/14610c57-8793-4af2-939b-f42381a9d696/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/1017e565-c8ee-49bf-be72-e22b2a6caf17/current_0.jpg",
      "https://replicate.delivery/mgxm/781ad353-f9d5-414a-b8ae-98a91545dacb/current_1.jpg",
      "https://replicate.delivery/mgxm/24a1dfa5-badb-4691-b1e1-91a92bad990a/current_2.jpg",
      "https://replicate.delivery/mgxm/0fa7a63b-2c69-47a1-9ae7-e39b5ddcb279/current_3.jpg",
      "https://replicate.delivery/mgxm/9b6c2b82-94fd-44cf-82f8-97eb69129c18/current_4.jpg",
      "https://replicate.delivery/mgxm/fb97992a-3439-480c-9bf0-1d8e5f80fa5d/current_5.jpg"
    ],
    [
      "https://replicate.delivery/mgxm/4355028d-e9a6-4471-8111-b98c510242bd/current_0.jpg",
      "https://replicate.delivery/mgxm/f9b14f53-9436-447b-847e-0019da6bfe34/current_1.jpg",
      "https://replicate.delivery/mgxm/2ff36ef0-30fb-466d-959d-6b0aa348b99f/current_2.jpg",
      "https://replicate.delivery/mgxm/2784e100-e50b-47b0-bfcf-5f23de2821a4/current_3.jpg",
      "https://replicate.delivery/mgxm/1573f979-53e4-49d4-9746-d1d3ad02f1c7/current_4.jpg",
      "https://replicate.delivery/mgxm/fba54869-9b0a-44eb-880b-33ddb7fe3501/current_5.jpg"
    ]
  ],
  "started_at": "2022-06-24T23:15:56.699714Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/v2onktt7yjalpglsu4apogpcnm",
    "cancel": "https://api.replicate.com/v1/predictions/v2onktt7yjalpglsu4apogpcnm/cancel"
  },
  "version": "d937c50007a1cacbdbd1e0a71ccaeac2b383a20f5579ea9b3f5ad46fcb2e2607"
}

Generated in

68.1 seconds

Tweak it ShareReport

Using seed 2401128644
Running simulation for pink floyd
Encoding text embeddings with pink floyd dimensions
Using aesthetic embedding 9 with weight 0.5
Using inpaint model but no image is provided. Initializing with zeros.
Running diffusion...

0it [00:00, ?it/s]

Timestep 0 - saving sample
  0%|          | 0/75 [00:00<?, ?it/s]
1it [00:03,  3.37s/it]

  1%|▏         | 1/75 [00:03<04:09,  3.37s/it]
2it [00:05,  2.90s/it]

  3%|▎         | 2/75 [00:05<03:32,  2.90s/it]
3it [00:08,  2.76s/it]

  4%|▍         | 3/75 [00:08<03:18,  2.76s/it]
4it [00:09,  1.93s/it]

  5%|▌         | 4/75 [00:09<02:16,  1.93s/it]
5it [00:09,  1.47s/it]

  7%|▋         | 5/75 [00:09<01:42,  1.47s/it]
6it [00:10,  1.19s/it]

  8%|▊         | 6/75 [00:10<01:22,  1.19s/it]
7it [00:11,  1.01s/it]

  9%|▉         | 7/75 [00:11<01:08,  1.01s/it]
8it [00:11,  1.11it/s]

 11%|█         | 8/75 [00:11<01:00,  1.11it/s]
9it [00:12,  1.22it/s]

 12%|█▏        | 9/75 [00:12<00:54,  1.22it/s]
10it [00:13,  1.30it/s]

Timestep 10 - saving sample
 13%|█▎        | 10/75 [00:13<00:49,  1.30it/s]
11it [00:14,  1.05it/s]

 15%|█▍        | 11/75 [00:14<01:00,  1.05it/s]
12it [00:15,  1.17it/s]

 16%|█▌        | 12/75 [00:15<00:53,  1.17it/s]
13it [00:15,  1.26it/s]

 17%|█▋        | 13/75 [00:15<00:49,  1.26it/s]
14it [00:16,  1.33it/s]

 19%|█▊        | 14/75 [00:16<00:45,  1.33it/s]
15it [00:17,  1.38it/s]

 20%|██        | 15/75 [00:17<00:43,  1.38it/s]
16it [00:17,  1.42it/s]

 21%|██▏       | 16/75 [00:17<00:41,  1.42it/s]
17it [00:18,  1.45it/s]

 23%|██▎       | 17/75 [00:18<00:40,  1.45it/s]
18it [00:19,  1.47it/s]

 24%|██▍       | 18/75 [00:19<00:38,  1.47it/s]
19it [00:19,  1.48it/s]

 25%|██▌       | 19/75 [00:19<00:37,  1.48it/s]
20it [00:20,  1.49it/s]

Timestep 20 - saving sample
 27%|██▋       | 20/75 [00:20<00:36,  1.49it/s]
21it [00:21,  1.14it/s]

 28%|██▊       | 21/75 [00:21<00:47,  1.14it/s]
22it [00:22,  1.24it/s]

 29%|██▉       | 22/75 [00:22<00:42,  1.24it/s]
23it [00:23,  1.31it/s]

 31%|███       | 23/75 [00:23<00:39,  1.31it/s]
24it [00:23,  1.37it/s]

 32%|███▏      | 24/75 [00:23<00:37,  1.37it/s]
25it [00:24,  1.41it/s]

 33%|███▎      | 25/75 [00:24<00:35,  1.41it/s]
26it [00:24,  1.44it/s]

 35%|███▍      | 26/75 [00:24<00:34,  1.44it/s]
27it [00:25,  1.46it/s]

 36%|███▌      | 27/75 [00:25<00:32,  1.46it/s]
28it [00:26,  1.48it/s]

 37%|███▋      | 28/75 [00:26<00:31,  1.48it/s]
29it [00:26,  1.49it/s]

 39%|███▊      | 29/75 [00:26<00:30,  1.49it/s]
30it [00:27,  1.50it/s]

Timestep 30 - saving sample
 40%|████      | 30/75 [00:27<00:30,  1.50it/s]
31it [00:28,  1.14it/s]

 41%|████▏     | 31/75 [00:28<00:38,  1.14it/s]
32it [00:29,  1.23it/s]

 43%|████▎     | 32/75 [00:29<00:34,  1.23it/s]
33it [00:30,  1.30it/s]

 44%|████▍     | 33/75 [00:30<00:32,  1.30it/s]
34it [00:30,  1.36it/s]

 45%|████▌     | 34/75 [00:30<00:30,  1.36it/s]
35it [00:31,  1.40it/s]

 47%|████▋     | 35/75 [00:31<00:28,  1.40it/s]
36it [00:32,  1.43it/s]

 48%|████▊     | 36/75 [00:32<00:27,  1.43it/s]
37it [00:32,  1.45it/s]

 49%|████▉     | 37/75 [00:32<00:26,  1.45it/s]
38it [00:33,  1.47it/s]

 51%|█████     | 38/75 [00:33<00:25,  1.47it/s]
39it [00:34,  1.47it/s]

 52%|█████▏    | 39/75 [00:34<00:24,  1.47it/s]
40it [00:34,  1.48it/s]

Timestep 40 - saving sample
 53%|█████▎    | 40/75 [00:34<00:23,  1.48it/s]
41it [00:36,  1.11it/s]

 55%|█████▍    | 41/75 [00:36<00:30,  1.11it/s]
42it [00:37,  1.21it/s]

 56%|█████▌    | 42/75 [00:37<00:27,  1.21it/s]
43it [00:37,  1.28it/s]

 57%|█████▋    | 43/75 [00:37<00:25,  1.28it/s]
44it [00:38,  1.33it/s]

 59%|█████▊    | 44/75 [00:38<00:23,  1.33it/s]
45it [00:39,  1.38it/s]

 60%|██████    | 45/75 [00:39<00:21,  1.38it/s]
46it [00:39,  1.41it/s]

 61%|██████▏   | 46/75 [00:39<00:20,  1.41it/s]
47it [00:40,  1.43it/s]

 63%|██████▎   | 47/75 [00:40<00:19,  1.43it/s]
48it [00:41,  1.45it/s]

 64%|██████▍   | 48/75 [00:41<00:18,  1.45it/s]
49it [00:41,  1.46it/s]

 65%|██████▌   | 49/75 [00:41<00:17,  1.46it/s]
50it [00:42,  1.46it/s]

Timestep 50 - saving sample
 67%|██████▋   | 50/75 [00:42<00:17,  1.46it/s]
51it [00:44,  1.00s/it]

 68%|██████▊   | 51/75 [00:44<00:24,  1.00s/it]
52it [00:44,  1.12it/s]

 69%|██████▉   | 52/75 [00:44<00:20,  1.12it/s]
53it [00:45,  1.21it/s]

 71%|███████   | 53/75 [00:45<00:18,  1.21it/s]
54it [00:46,  1.28it/s]

 72%|███████▏  | 54/75 [00:46<00:16,  1.28it/s]
55it [00:46,  1.34it/s]

 73%|███████▎  | 55/75 [00:46<00:14,  1.34it/s]
56it [00:47,  1.38it/s]

 75%|███████▍  | 56/75 [00:47<00:13,  1.38it/s]
57it [00:48,  1.41it/s]

 76%|███████▌  | 57/75 [00:48<00:12,  1.41it/s]
58it [00:48,  1.43it/s]

 77%|███████▋  | 58/75 [00:48<00:11,  1.43it/s]
59it [00:49,  1.45it/s]

 79%|███████▊  | 59/75 [00:49<00:11,  1.45it/s]
60it [00:50,  1.46it/s]

Timestep 60 - saving sample
 80%|████████  | 60/75 [00:50<00:10,  1.46it/s]
61it [00:51,  1.03it/s]

 81%|████████▏ | 61/75 [00:51<00:13,  1.03it/s]
62it [00:52,  1.14it/s]

 83%|████████▎ | 62/75 [00:52<00:11,  1.14it/s]
63it [00:53,  1.22it/s]

 84%|████████▍ | 63/75 [00:53<00:09,  1.22it/s]
64it [00:53,  1.28it/s]

 85%|████████▌ | 64/75 [00:53<00:08,  1.28it/s]
65it [00:54,  1.34it/s]

 87%|████████▋ | 65/75 [00:54<00:07,  1.34it/s]
66it [00:55,  1.37it/s]

 88%|████████▊ | 66/75 [00:55<00:06,  1.37it/s]
67it [00:55,  1.39it/s]

 89%|████████▉ | 67/75 [00:55<00:05,  1.39it/s]
68it [00:56,  1.42it/s]

 91%|█████████ | 68/75 [00:56<00:04,  1.42it/s]
69it [00:57,  1.43it/s]

 92%|█████████▏| 69/75 [00:57<00:04,  1.43it/s]
70it [00:57,  1.44it/s]

Timestep 70 - saving sample
 93%|█████████▎| 70/75 [00:57<00:03,  1.44it/s]
71it [00:59,  1.02it/s]

 95%|█████████▍| 71/75 [00:59<00:03,  1.02it/s]
72it [01:00,  1.14it/s]

 96%|█████████▌| 72/75 [01:00<00:02,  1.14it/s]
73it [01:00,  1.20it/s]

 97%|█████████▋| 73/75 [01:00<00:01,  1.20it/s]
74it [01:01,  1.26it/s]

Timestep 74 - saving final sample
 99%|█████████▊| 74/75 [01:01<00:00,  1.26it/s]
75it [01:03,  1.06s/it]

100%|██████████| 75/75 [01:03<00:00,  1.06s/it]
100%|██████████| 75/75 [01:03<00:00,  1.18it/s]

75it [01:03,  1.18it/s]

Prediction

laion-ai/erlich:548faf80d48dec72e11457b7368015ed9232f66d6e4ee2619de2c871a8085449

Model

laion-ai/erlich:548faf80

gpzwvhiwhbelpml3lpgdtarcmy

Status

Succeeded

Source

Web

Hardware

–

Total duration

16.4s

Created

about 3 years ago

Input

seed: "-1"
steps: "50"
width: "256"
height: "256"
prompt: low poly "laion" logo of a lion-symbol. psychedlic colors.
batch_size: "4"
guidance_scale: "5"
aesthetic_rating: 9
aesthetic_weight: 0.1

{
  "seed": "-1",
  "steps": "50",
  "width": "256",
  "height": "256",
  "prompt": "low poly \"laion\" logo of a lion-symbol. psychedlic colors.",
  "batch_size": "4",
  "guidance_scale": "5",
  "aesthetic_rating": 9,
  "aesthetic_weight": 0.1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "laion-ai/erlich:548faf80d48dec72e11457b7368015ed9232f66d6e4ee2619de2c871a8085449",
  {
    input: {
      seed: "-1",
      steps: "50",
      width: "256",
      height: "256",
      prompt: "low poly \"laion\" logo of a lion-symbol. psychedlic colors.",
      batch_size: "4",
      guidance_scale: "5",
      aesthetic_rating: 9,
      aesthetic_weight: 0.1
    }
  }
);

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

Import the client:

import replicate

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "laion-ai/erlich:548faf80d48dec72e11457b7368015ed9232f66d6e4ee2619de2c871a8085449",
    input={
        "seed": "-1",
        "steps": "50",
        "width": "256",
        "height": "256",
        "prompt": "low poly \"laion\" logo of a lion-symbol. psychedlic colors.",
        "batch_size": "4",
        "guidance_scale": "5",
        "aesthetic_rating": 9,
        "aesthetic_weight": 0.1
    }
)

# The laion-ai/erlich 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/erlich/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run laion-ai/erlich 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": "laion-ai/erlich:548faf80d48dec72e11457b7368015ed9232f66d6e4ee2619de2c871a8085449",
    "input": {
      "seed": "-1",
      "steps": "50",
      "width": "256",
      "height": "256",
      "prompt": "low poly \\"laion\\" logo of a lion-symbol. psychedlic colors.",
      "batch_size": "4",
      "guidance_scale": "5",
      "aesthetic_rating": 9,
      "aesthetic_weight": 0.1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-06-28T15:12:36.833287Z",
  "created_at": "2022-06-28T15:12:20.418454Z",
  "data_removed": false,
  "error": null,
  "id": "gpzwvhiwhbelpml3lpgdtarcmy",
  "input": {
    "seed": "-1",
    "steps": "50",
    "width": "256",
    "height": "256",
    "prompt": "low poly \"laion\" logo of a lion-symbol. psychedlic colors.",
    "batch_size": "4",
    "guidance_scale": "5",
    "aesthetic_rating": 9,
    "aesthetic_weight": 0.1
  },
  "logs": "Using seed 3576313590\nRunning simulation for low poly \"laion\" logo of a lion-symbol. psychedlic colors.\nEncoding text embeddings with low poly \"laion\" logo of a lion-symbol. psychedlic colors. dimensions\nUsing aesthetic embedding 9 with weight 0.1\nUsing inpaint model but no image is provided. Initializing with zeros.\nRunning diffusion...\n\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:45,  1.07it/s]\n  4%|▍         | 2/50 [00:01<00:43,  1.11it/s]\n  6%|▌         | 3/50 [00:02<00:41,  1.12it/s]\n  8%|▊         | 4/50 [00:02<00:28,  1.60it/s]\n 10%|█         | 5/50 [00:03<00:21,  2.09it/s]\n 12%|█▏        | 6/50 [00:03<00:17,  2.56it/s]\n 14%|█▍        | 7/50 [00:03<00:14,  2.99it/s]\n 16%|█▌        | 8/50 [00:03<00:12,  3.35it/s]\n 18%|█▊        | 9/50 [00:04<00:11,  3.65it/s]\n 20%|██        | 10/50 [00:04<00:10,  3.87it/s]\n 22%|██▏       | 11/50 [00:04<00:09,  4.05it/s]\n 24%|██▍       | 12/50 [00:04<00:09,  4.19it/s]\n 26%|██▌       | 13/50 [00:04<00:08,  4.29it/s]\n 28%|██▊       | 14/50 [00:05<00:08,  4.37it/s]\n 30%|███       | 15/50 [00:05<00:07,  4.42it/s]\n 32%|███▏      | 16/50 [00:05<00:07,  4.46it/s]\n 34%|███▍      | 17/50 [00:05<00:07,  4.49it/s]\n 36%|███▌      | 18/50 [00:05<00:07,  4.49it/s]\n 38%|███▊      | 19/50 [00:06<00:06,  4.49it/s]\n 40%|████      | 20/50 [00:06<00:06,  4.49it/s]\n 42%|████▏     | 21/50 [00:06<00:06,  4.51it/s]\n 44%|████▍     | 22/50 [00:06<00:06,  4.50it/s]\n 46%|████▌     | 23/50 [00:07<00:05,  4.50it/s]\n 48%|████▊     | 24/50 [00:07<00:05,  4.49it/s]\n 50%|█████     | 25/50 [00:07<00:05,  4.49it/s]\n 52%|█████▏    | 26/50 [00:07<00:05,  4.50it/s]\n 54%|█████▍    | 27/50 [00:07<00:05,  4.50it/s]\n 56%|█████▌    | 28/50 [00:08<00:04,  4.50it/s]\n 58%|█████▊    | 29/50 [00:08<00:04,  4.49it/s]\n 60%|██████    | 30/50 [00:08<00:04,  4.49it/s]\n 62%|██████▏   | 31/50 [00:08<00:04,  4.49it/s]\n 64%|██████▍   | 32/50 [00:09<00:04,  4.49it/s]\n 66%|██████▌   | 33/50 [00:09<00:03,  4.49it/s]\n 68%|██████▊   | 34/50 [00:09<00:03,  4.48it/s]\n 70%|███████   | 35/50 [00:09<00:03,  4.47it/s]\n 72%|███████▏  | 36/50 [00:10<00:03,  4.47it/s]\n 74%|███████▍  | 37/50 [00:10<00:02,  4.48it/s]\n 76%|███████▌  | 38/50 [00:10<00:02,  4.48it/s]\n 78%|███████▊  | 39/50 [00:10<00:02,  4.48it/s]\n 80%|████████  | 40/50 [00:10<00:02,  4.48it/s]\n 82%|████████▏ | 41/50 [00:11<00:02,  4.49it/s]\n 84%|████████▍ | 42/50 [00:11<00:01,  4.48it/s]\n 86%|████████▌ | 43/50 [00:11<00:01,  4.48it/s]\n 88%|████████▊ | 44/50 [00:11<00:01,  4.47it/s]\n 90%|█████████ | 45/50 [00:12<00:01,  4.46it/s]\n 92%|█████████▏| 46/50 [00:12<00:00,  4.46it/s]\n 94%|█████████▍| 47/50 [00:12<00:00,  4.46it/s]\n 96%|█████████▌| 48/50 [00:12<00:00,  4.46it/s]\nSaving final sample/s\n 98%|█████████▊| 49/50 [00:12<00:00,  4.46it/s]\n100%|██████████| 50/50 [00:13<00:00,  3.01it/s]\n100%|██████████| 50/50 [00:13<00:00,  3.71it/s]",
  "metrics": {
    "predict_time": 16.233225,
    "total_time": 16.414833
  },
  "output": [
    [
      "https://replicate.delivery/mgxm/40bce360-eb75-44c9-b8e7-217fe0f33232/current_0.png",
      "https://replicate.delivery/mgxm/67f76b4e-51d4-4f4a-8773-38ccdee9dfb8/current_1.png",
      "https://replicate.delivery/mgxm/3fd90365-5592-463c-80d6-c51394fc0cc3/current_2.png",
      "https://replicate.delivery/mgxm/2ef9cafb-d92f-4154-b2be-69f4a9bec09a/current_3.png"
    ]
  ],
  "started_at": "2022-06-28T15:12:20.600062Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/gpzwvhiwhbelpml3lpgdtarcmy",
    "cancel": "https://api.replicate.com/v1/predictions/gpzwvhiwhbelpml3lpgdtarcmy/cancel"
  },
  "version": "548faf80d48dec72e11457b7368015ed9232f66d6e4ee2619de2c871a8085449"
}

Generated in

16.2 seconds

Tweak it ShareReport

Using seed 3576313590
Running simulation for low poly "laion" logo of a lion-symbol. psychedlic colors.
Encoding text embeddings with low poly "laion" logo of a lion-symbol. psychedlic colors. dimensions
Using aesthetic embedding 9 with weight 0.1
Using inpaint model but no image is provided. Initializing with zeros.
Running diffusion...

  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:45,  1.07it/s]
  4%|▍         | 2/50 [00:01<00:43,  1.11it/s]
  6%|▌         | 3/50 [00:02<00:41,  1.12it/s]
  8%|▊         | 4/50 [00:02<00:28,  1.60it/s]
 10%|█         | 5/50 [00:03<00:21,  2.09it/s]
 12%|█▏        | 6/50 [00:03<00:17,  2.56it/s]
 14%|█▍        | 7/50 [00:03<00:14,  2.99it/s]
 16%|█▌        | 8/50 [00:03<00:12,  3.35it/s]
 18%|█▊        | 9/50 [00:04<00:11,  3.65it/s]
 20%|██        | 10/50 [00:04<00:10,  3.87it/s]
 22%|██▏       | 11/50 [00:04<00:09,  4.05it/s]
 24%|██▍       | 12/50 [00:04<00:09,  4.19it/s]
 26%|██▌       | 13/50 [00:04<00:08,  4.29it/s]
 28%|██▊       | 14/50 [00:05<00:08,  4.37it/s]
 30%|███       | 15/50 [00:05<00:07,  4.42it/s]
 32%|███▏      | 16/50 [00:05<00:07,  4.46it/s]
 34%|███▍      | 17/50 [00:05<00:07,  4.49it/s]
 36%|███▌      | 18/50 [00:05<00:07,  4.49it/s]
 38%|███▊      | 19/50 [00:06<00:06,  4.49it/s]
 40%|████      | 20/50 [00:06<00:06,  4.49it/s]
 42%|████▏     | 21/50 [00:06<00:06,  4.51it/s]
 44%|████▍     | 22/50 [00:06<00:06,  4.50it/s]
 46%|████▌     | 23/50 [00:07<00:05,  4.50it/s]
 48%|████▊     | 24/50 [00:07<00:05,  4.49it/s]
 50%|█████     | 25/50 [00:07<00:05,  4.49it/s]
 52%|█████▏    | 26/50 [00:07<00:05,  4.50it/s]
 54%|█████▍    | 27/50 [00:07<00:05,  4.50it/s]
 56%|█████▌    | 28/50 [00:08<00:04,  4.50it/s]
 58%|█████▊    | 29/50 [00:08<00:04,  4.49it/s]
 60%|██████    | 30/50 [00:08<00:04,  4.49it/s]
 62%|██████▏   | 31/50 [00:08<00:04,  4.49it/s]
 64%|██████▍   | 32/50 [00:09<00:04,  4.49it/s]
 66%|██████▌   | 33/50 [00:09<00:03,  4.49it/s]
 68%|██████▊   | 34/50 [00:09<00:03,  4.48it/s]
 70%|███████   | 35/50 [00:09<00:03,  4.47it/s]
 72%|███████▏  | 36/50 [00:10<00:03,  4.47it/s]
 74%|███████▍  | 37/50 [00:10<00:02,  4.48it/s]
 76%|███████▌  | 38/50 [00:10<00:02,  4.48it/s]
 78%|███████▊  | 39/50 [00:10<00:02,  4.48it/s]
 80%|████████  | 40/50 [00:10<00:02,  4.48it/s]
 82%|████████▏ | 41/50 [00:11<00:02,  4.49it/s]
 84%|████████▍ | 42/50 [00:11<00:01,  4.48it/s]
 86%|████████▌ | 43/50 [00:11<00:01,  4.48it/s]
 88%|████████▊ | 44/50 [00:11<00:01,  4.47it/s]
 90%|█████████ | 45/50 [00:12<00:01,  4.46it/s]
 92%|█████████▏| 46/50 [00:12<00:00,  4.46it/s]
 94%|█████████▍| 47/50 [00:12<00:00,  4.46it/s]
 96%|█████████▌| 48/50 [00:12<00:00,  4.46it/s]
Saving final sample/s
 98%|█████████▊| 49/50 [00:12<00:00,  4.46it/s]
100%|██████████| 50/50 [00:13<00:00,  3.01it/s]
100%|██████████| 50/50 [00:13<00:00,  3.71it/s]

Prediction

laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa

Model

laion-ai/erlich:a51ce279

2d56rgiq4vcphcvzi6xeerciny

Status

Succeeded

Source

Web

Hardware

–

Total duration

32.7s

Created

about 3 years ago

Input

seed: "-1"
steps: "75"
width: "256"
height: "256"
prompt: stranger things
batch_size: "6"
guidance_scale: "5"
aesthetic_rating: 9
aesthetic_weight: 0.5

{
  "seed": "-1",
  "steps": "75",
  "width": "256",
  "height": "256",
  "prompt": "stranger things",
  "batch_size": "6",
  "guidance_scale": "5",
  "aesthetic_rating": 9,
  "aesthetic_weight": 0.5
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
  {
    input: {
      seed: "-1",
      steps: "75",
      width: "256",
      height: "256",
      prompt: "stranger things",
      batch_size: "6",
      guidance_scale: "5",
      aesthetic_rating: 9,
      aesthetic_weight: 0.5
    }
  }
);

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

Import the client:

import replicate

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
    input={
        "seed": "-1",
        "steps": "75",
        "width": "256",
        "height": "256",
        "prompt": "stranger things",
        "batch_size": "6",
        "guidance_scale": "5",
        "aesthetic_rating": 9,
        "aesthetic_weight": 0.5
    }
)

# The laion-ai/erlich 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/erlich/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run laion-ai/erlich 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": "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
    "input": {
      "seed": "-1",
      "steps": "75",
      "width": "256",
      "height": "256",
      "prompt": "stranger things",
      "batch_size": "6",
      "guidance_scale": "5",
      "aesthetic_rating": 9,
      "aesthetic_weight": 0.5
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-07-10T10:30:50.098614Z",
  "created_at": "2022-07-10T10:30:17.358982Z",
  "data_removed": false,
  "error": null,
  "id": "2d56rgiq4vcphcvzi6xeerciny",
  "input": {
    "seed": "-1",
    "steps": "75",
    "width": "256",
    "height": "256",
    "prompt": "stranger things",
    "batch_size": "6",
    "guidance_scale": "5",
    "aesthetic_rating": 9,
    "aesthetic_weight": 0.5
  },
  "logs": "Using seed 3269048179\nRunning simulation for stranger things\nEncoding text embeddings with stranger things dimensions\nUsing aesthetic embedding 9 with weight 0.5\nRunning diffusion...\n\n  0%|          | 0/75 [00:00<?, ?it/s]\n  1%|▏         | 1/75 [00:01<01:33,  1.26s/it]\n  3%|▎         | 2/75 [00:02<01:30,  1.25s/it]\n  4%|▍         | 3/75 [00:03<01:29,  1.24s/it]\n  5%|▌         | 4/75 [00:04<01:01,  1.15it/s]\n  7%|▋         | 5/75 [00:04<00:47,  1.49it/s]\n  8%|▊         | 6/75 [00:04<00:37,  1.82it/s]\n  9%|▉         | 7/75 [00:04<00:31,  2.13it/s]\n 11%|█         | 8/75 [00:05<00:28,  2.37it/s]\n 12%|█▏        | 9/75 [00:05<00:25,  2.58it/s]\n 13%|█▎        | 10/75 [00:05<00:23,  2.74it/s]\n 15%|█▍        | 11/75 [00:06<00:22,  2.86it/s]\n 16%|█▌        | 12/75 [00:06<00:21,  2.94it/s]\n 17%|█▋        | 13/75 [00:06<00:20,  3.01it/s]\n 19%|█▊        | 14/75 [00:07<00:19,  3.06it/s]\n 20%|██        | 15/75 [00:07<00:19,  3.07it/s]\n 21%|██▏       | 16/75 [00:07<00:19,  3.09it/s]\n 23%|██▎       | 17/75 [00:08<00:18,  3.12it/s]\n 24%|██▍       | 18/75 [00:08<00:18,  3.11it/s]\n 25%|██▌       | 19/75 [00:08<00:17,  3.12it/s]\n 27%|██▋       | 20/75 [00:09<00:17,  3.12it/s]\n 28%|██▊       | 21/75 [00:09<00:17,  3.14it/s]\n 29%|██▉       | 22/75 [00:09<00:17,  3.11it/s]\n 31%|███       | 23/75 [00:10<00:16,  3.12it/s]\n 32%|███▏      | 24/75 [00:10<00:16,  3.11it/s]\n 33%|███▎      | 25/75 [00:10<00:16,  3.09it/s]\n 35%|███▍      | 26/75 [00:11<00:15,  3.10it/s]\n 36%|███▌      | 27/75 [00:11<00:15,  3.09it/s]\n 37%|███▋      | 28/75 [00:11<00:15,  3.08it/s]\n 39%|███▊      | 29/75 [00:12<00:14,  3.08it/s]\n 40%|████      | 30/75 [00:12<00:14,  3.08it/s]\n 41%|████▏     | 31/75 [00:12<00:14,  3.07it/s]\n 43%|████▎     | 32/75 [00:12<00:14,  3.06it/s]\n 44%|████▍     | 33/75 [00:13<00:13,  3.07it/s]\n 45%|████▌     | 34/75 [00:13<00:13,  3.07it/s]\n 47%|████▋     | 35/75 [00:13<00:13,  3.06it/s]\n 48%|████▊     | 36/75 [00:14<00:12,  3.06it/s]\n 49%|████▉     | 37/75 [00:14<00:12,  3.05it/s]\n 51%|█████     | 38/75 [00:14<00:12,  3.03it/s]\n 52%|█████▏    | 39/75 [00:15<00:11,  3.03it/s]\n 53%|█████▎    | 40/75 [00:15<00:11,  3.03it/s]\n 55%|█████▍    | 41/75 [00:15<00:11,  3.02it/s]\n 56%|█████▌    | 42/75 [00:16<00:10,  3.02it/s]\n 57%|█████▋    | 43/75 [00:16<00:10,  3.02it/s]\n 59%|█████▊    | 44/75 [00:16<00:10,  3.01it/s]\n 60%|██████    | 45/75 [00:17<00:10,  2.99it/s]\n 61%|██████▏   | 46/75 [00:17<00:09,  3.01it/s]\n 63%|██████▎   | 47/75 [00:17<00:09,  3.01it/s]\n 64%|██████▍   | 48/75 [00:18<00:09,  3.00it/s]\n 65%|██████▌   | 49/75 [00:18<00:08,  2.99it/s]\n 67%|██████▋   | 50/75 [00:18<00:08,  2.98it/s]\n 68%|██████▊   | 51/75 [00:19<00:08,  2.97it/s]\n 69%|██████▉   | 52/75 [00:19<00:07,  2.98it/s]\n 71%|███████   | 53/75 [00:19<00:07,  2.97it/s]\n 72%|███████▏  | 54/75 [00:20<00:07,  2.96it/s]\n 73%|███████▎  | 55/75 [00:20<00:06,  2.97it/s]\n 75%|███████▍  | 56/75 [00:20<00:06,  2.97it/s]\n 76%|███████▌  | 57/75 [00:21<00:06,  2.96it/s]\n 77%|███████▋  | 58/75 [00:21<00:05,  2.97it/s]\n 79%|███████▊  | 59/75 [00:22<00:05,  2.95it/s]\n 80%|████████  | 60/75 [00:22<00:05,  2.94it/s]\n 81%|████████▏ | 61/75 [00:22<00:04,  2.95it/s]\n 83%|████████▎ | 62/75 [00:23<00:04,  2.95it/s]\n 84%|████████▍ | 63/75 [00:23<00:04,  2.94it/s]\n 85%|████████▌ | 64/75 [00:23<00:03,  2.95it/s]\n 87%|████████▋ | 65/75 [00:24<00:03,  2.94it/s]\n 88%|████████▊ | 66/75 [00:24<00:03,  2.93it/s]\n 89%|████████▉ | 67/75 [00:24<00:02,  2.93it/s]\n 91%|█████████ | 68/75 [00:25<00:02,  2.94it/s]\n 92%|█████████▏| 69/75 [00:25<00:02,  2.93it/s]\n 93%|█████████▎| 70/75 [00:25<00:01,  2.93it/s]\n 95%|█████████▍| 71/75 [00:26<00:01,  2.93it/s]\n 96%|█████████▌| 72/75 [00:26<00:01,  2.93it/s]\n 97%|█████████▋| 73/75 [00:26<00:00,  2.94it/s]\n 99%|█████████▊| 74/75 [00:27<00:00,  2.94it/s]\n100%|██████████| 75/75 [00:27<00:00,  2.93it/s]\n100%|██████████| 75/75 [00:27<00:00,  2.73it/s]\nSaving final sample/s",
  "metrics": {
    "predict_time": 32.566438,
    "total_time": 32.739632
  },
  "output": [
    [
      "https://replicate.delivery/mgxm/3b5a16cc-52e4-47fb-ac9b-c945c60b14d6/current_0.png",
      "https://replicate.delivery/mgxm/6678501a-2111-47e7-924c-981497bd7a6d/current_1.png",
      "https://replicate.delivery/mgxm/ff3c2321-566e-4bd2-8fec-d943eadc58dd/current_2.png",
      "https://replicate.delivery/mgxm/36b570a4-8859-423d-9175-3b0b6920d8da/current_3.png",
      "https://replicate.delivery/mgxm/8075cd49-2169-444a-a346-c9d1b6a49f54/current_4.png",
      "https://replicate.delivery/mgxm/8d77d879-4084-4204-a9e9-a98306aeb251/current_5.png"
    ]
  ],
  "started_at": "2022-07-10T10:30:17.532176Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/2d56rgiq4vcphcvzi6xeerciny",
    "cancel": "https://api.replicate.com/v1/predictions/2d56rgiq4vcphcvzi6xeerciny/cancel"
  },
  "version": "a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa"
}

Generated in

32.6 seconds

Tweak it ShareReport

Using seed 3269048179
Running simulation for stranger things
Encoding text embeddings with stranger things dimensions
Using aesthetic embedding 9 with weight 0.5
Running diffusion...

  0%|          | 0/75 [00:00<?, ?it/s]
  1%|▏         | 1/75 [00:01<01:33,  1.26s/it]
  3%|▎         | 2/75 [00:02<01:30,  1.25s/it]
  4%|▍         | 3/75 [00:03<01:29,  1.24s/it]
  5%|▌         | 4/75 [00:04<01:01,  1.15it/s]
  7%|▋         | 5/75 [00:04<00:47,  1.49it/s]
  8%|▊         | 6/75 [00:04<00:37,  1.82it/s]
  9%|▉         | 7/75 [00:04<00:31,  2.13it/s]
 11%|█         | 8/75 [00:05<00:28,  2.37it/s]
 12%|█▏        | 9/75 [00:05<00:25,  2.58it/s]
 13%|█▎        | 10/75 [00:05<00:23,  2.74it/s]
 15%|█▍        | 11/75 [00:06<00:22,  2.86it/s]
 16%|█▌        | 12/75 [00:06<00:21,  2.94it/s]
 17%|█▋        | 13/75 [00:06<00:20,  3.01it/s]
 19%|█▊        | 14/75 [00:07<00:19,  3.06it/s]
 20%|██        | 15/75 [00:07<00:19,  3.07it/s]
 21%|██▏       | 16/75 [00:07<00:19,  3.09it/s]
 23%|██▎       | 17/75 [00:08<00:18,  3.12it/s]
 24%|██▍       | 18/75 [00:08<00:18,  3.11it/s]
 25%|██▌       | 19/75 [00:08<00:17,  3.12it/s]
 27%|██▋       | 20/75 [00:09<00:17,  3.12it/s]
 28%|██▊       | 21/75 [00:09<00:17,  3.14it/s]
 29%|██▉       | 22/75 [00:09<00:17,  3.11it/s]
 31%|███       | 23/75 [00:10<00:16,  3.12it/s]
 32%|███▏      | 24/75 [00:10<00:16,  3.11it/s]
 33%|███▎      | 25/75 [00:10<00:16,  3.09it/s]
 35%|███▍      | 26/75 [00:11<00:15,  3.10it/s]
 36%|███▌      | 27/75 [00:11<00:15,  3.09it/s]
 37%|███▋      | 28/75 [00:11<00:15,  3.08it/s]
 39%|███▊      | 29/75 [00:12<00:14,  3.08it/s]
 40%|████      | 30/75 [00:12<00:14,  3.08it/s]
 41%|████▏     | 31/75 [00:12<00:14,  3.07it/s]
 43%|████▎     | 32/75 [00:12<00:14,  3.06it/s]
 44%|████▍     | 33/75 [00:13<00:13,  3.07it/s]
 45%|████▌     | 34/75 [00:13<00:13,  3.07it/s]
 47%|████▋     | 35/75 [00:13<00:13,  3.06it/s]
 48%|████▊     | 36/75 [00:14<00:12,  3.06it/s]
 49%|████▉     | 37/75 [00:14<00:12,  3.05it/s]
 51%|█████     | 38/75 [00:14<00:12,  3.03it/s]
 52%|█████▏    | 39/75 [00:15<00:11,  3.03it/s]
 53%|█████▎    | 40/75 [00:15<00:11,  3.03it/s]
 55%|█████▍    | 41/75 [00:15<00:11,  3.02it/s]
 56%|█████▌    | 42/75 [00:16<00:10,  3.02it/s]
 57%|█████▋    | 43/75 [00:16<00:10,  3.02it/s]
 59%|█████▊    | 44/75 [00:16<00:10,  3.01it/s]
 60%|██████    | 45/75 [00:17<00:10,  2.99it/s]
 61%|██████▏   | 46/75 [00:17<00:09,  3.01it/s]
 63%|██████▎   | 47/75 [00:17<00:09,  3.01it/s]
 64%|██████▍   | 48/75 [00:18<00:09,  3.00it/s]
 65%|██████▌   | 49/75 [00:18<00:08,  2.99it/s]
 67%|██████▋   | 50/75 [00:18<00:08,  2.98it/s]
 68%|██████▊   | 51/75 [00:19<00:08,  2.97it/s]
 69%|██████▉   | 52/75 [00:19<00:07,  2.98it/s]
 71%|███████   | 53/75 [00:19<00:07,  2.97it/s]
 72%|███████▏  | 54/75 [00:20<00:07,  2.96it/s]
 73%|███████▎  | 55/75 [00:20<00:06,  2.97it/s]
 75%|███████▍  | 56/75 [00:20<00:06,  2.97it/s]
 76%|███████▌  | 57/75 [00:21<00:06,  2.96it/s]
 77%|███████▋  | 58/75 [00:21<00:05,  2.97it/s]
 79%|███████▊  | 59/75 [00:22<00:05,  2.95it/s]
 80%|████████  | 60/75 [00:22<00:05,  2.94it/s]
 81%|████████▏ | 61/75 [00:22<00:04,  2.95it/s]
 83%|████████▎ | 62/75 [00:23<00:04,  2.95it/s]
 84%|████████▍ | 63/75 [00:23<00:04,  2.94it/s]
 85%|████████▌ | 64/75 [00:23<00:03,  2.95it/s]
 87%|████████▋ | 65/75 [00:24<00:03,  2.94it/s]
 88%|████████▊ | 66/75 [00:24<00:03,  2.93it/s]
 89%|████████▉ | 67/75 [00:24<00:02,  2.93it/s]
 91%|█████████ | 68/75 [00:25<00:02,  2.94it/s]
 92%|█████████▏| 69/75 [00:25<00:02,  2.93it/s]
 93%|█████████▎| 70/75 [00:25<00:01,  2.93it/s]
 95%|█████████▍| 71/75 [00:26<00:01,  2.93it/s]
 96%|█████████▌| 72/75 [00:26<00:01,  2.93it/s]
 97%|█████████▋| 73/75 [00:26<00:00,  2.94it/s]
 99%|█████████▊| 74/75 [00:27<00:00,  2.94it/s]
100%|██████████| 75/75 [00:27<00:00,  2.93it/s]
100%|██████████| 75/75 [00:27<00:00,  2.73it/s]
Saving final sample/s

Prediction

laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa

Model

laion-ai/erlich:a51ce279

6ur4mbq6bvgq7ahfr6yiywsqbi

Status

Succeeded

Source

Web

Hardware

–

Total duration

40.3s

Created

about 3 years ago

Input

seed: "-1"
steps: "100"
width: "256"
height: "256"
prompt: stranger things
batch_size: "6"
guidance_scale: "5"
aesthetic_rating: 9
aesthetic_weight: 0.1

{
  "seed": "-1",
  "steps": "100",
  "width": "256",
  "height": "256",
  "prompt": "stranger things",
  "batch_size": "6",
  "guidance_scale": "5",
  "aesthetic_rating": 9,
  "aesthetic_weight": 0.1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
  {
    input: {
      seed: "-1",
      steps: "100",
      width: "256",
      height: "256",
      prompt: "stranger things",
      batch_size: "6",
      guidance_scale: "5",
      aesthetic_rating: 9,
      aesthetic_weight: 0.1
    }
  }
);

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

Import the client:

import replicate

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
    input={
        "seed": "-1",
        "steps": "100",
        "width": "256",
        "height": "256",
        "prompt": "stranger things",
        "batch_size": "6",
        "guidance_scale": "5",
        "aesthetic_rating": 9,
        "aesthetic_weight": 0.1
    }
)

# The laion-ai/erlich 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/erlich/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run laion-ai/erlich 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": "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
    "input": {
      "seed": "-1",
      "steps": "100",
      "width": "256",
      "height": "256",
      "prompt": "stranger things",
      "batch_size": "6",
      "guidance_scale": "5",
      "aesthetic_rating": 9,
      "aesthetic_weight": 0.1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-07-10T10:32:07.773099Z",
  "created_at": "2022-07-10T10:31:27.474112Z",
  "data_removed": false,
  "error": null,
  "id": "6ur4mbq6bvgq7ahfr6yiywsqbi",
  "input": {
    "seed": "-1",
    "steps": "100",
    "width": "256",
    "height": "256",
    "prompt": "stranger things",
    "batch_size": "6",
    "guidance_scale": "5",
    "aesthetic_rating": 9,
    "aesthetic_weight": 0.1
  },
  "logs": "Using seed 2877705998\nRunning simulation for stranger things\nEncoding text embeddings with stranger things dimensions\nUsing aesthetic embedding 9 with weight 0.1\nRunning diffusion...\n\n  0%|          | 0/100 [00:00<?, ?it/s]\n  1%|          | 1/100 [00:01<02:03,  1.25s/it]\n  2%|▏         | 2/100 [00:02<02:00,  1.23s/it]\n  3%|▎         | 3/100 [00:03<01:59,  1.23s/it]\n  4%|▍         | 4/100 [00:04<01:23,  1.16it/s]\n  5%|▌         | 5/100 [00:04<01:03,  1.50it/s]\n  6%|▌         | 6/100 [00:04<00:50,  1.84it/s]\n  7%|▋         | 7/100 [00:04<00:43,  2.15it/s]\n  8%|▊         | 8/100 [00:05<00:38,  2.41it/s]\n  9%|▉         | 9/100 [00:05<00:34,  2.61it/s]\n 10%|█         | 10/100 [00:05<00:32,  2.78it/s]\n 11%|█         | 11/100 [00:06<00:30,  2.91it/s]\n 12%|█▏        | 12/100 [00:06<00:29,  3.00it/s]\n 13%|█▎        | 13/100 [00:06<00:28,  3.06it/s]\n 14%|█▍        | 14/100 [00:07<00:27,  3.11it/s]\n 15%|█▌        | 15/100 [00:07<00:27,  3.15it/s]\n 16%|█▌        | 16/100 [00:07<00:26,  3.16it/s]\n 17%|█▋        | 17/100 [00:08<00:26,  3.17it/s]\n 18%|█▊        | 18/100 [00:08<00:25,  3.18it/s]\n 19%|█▉        | 19/100 [00:08<00:25,  3.18it/s]\n 20%|██        | 20/100 [00:08<00:25,  3.18it/s]\n 21%|██        | 21/100 [00:09<00:24,  3.18it/s]\n 22%|██▏       | 22/100 [00:09<00:24,  3.17it/s]\n 23%|██▎       | 23/100 [00:09<00:24,  3.18it/s]\n 24%|██▍       | 24/100 [00:10<00:23,  3.17it/s]\n 25%|██▌       | 25/100 [00:10<00:23,  3.17it/s]\n 26%|██▌       | 26/100 [00:10<00:23,  3.18it/s]\n 27%|██▋       | 27/100 [00:11<00:23,  3.17it/s]\n 28%|██▊       | 28/100 [00:11<00:22,  3.17it/s]\n 29%|██▉       | 29/100 [00:11<00:22,  3.15it/s]\n 30%|███       | 30/100 [00:12<00:22,  3.16it/s]\n 31%|███       | 31/100 [00:12<00:21,  3.17it/s]\n 32%|███▏      | 32/100 [00:12<00:21,  3.15it/s]\n 33%|███▎      | 33/100 [00:13<00:21,  3.16it/s]\n 34%|███▍      | 34/100 [00:13<00:20,  3.16it/s]\n 35%|███▌      | 35/100 [00:13<00:20,  3.14it/s]\n 36%|███▌      | 36/100 [00:14<00:20,  3.15it/s]\n 37%|███▋      | 37/100 [00:14<00:20,  3.14it/s]\n 38%|███▊      | 38/100 [00:14<00:19,  3.13it/s]\n 39%|███▉      | 39/100 [00:14<00:19,  3.12it/s]\n 40%|████      | 40/100 [00:15<00:19,  3.12it/s]\n 41%|████      | 41/100 [00:15<00:18,  3.14it/s]\n 42%|████▏     | 42/100 [00:15<00:18,  3.13it/s]\n 43%|████▎     | 43/100 [00:16<00:18,  3.11it/s]\n 44%|████▍     | 44/100 [00:16<00:17,  3.11it/s]\n 45%|████▌     | 45/100 [00:16<00:17,  3.10it/s]\n 46%|████▌     | 46/100 [00:17<00:17,  3.10it/s]\n 47%|████▋     | 47/100 [00:17<00:17,  3.09it/s]\n 48%|████▊     | 48/100 [00:17<00:16,  3.08it/s]\n 49%|████▉     | 49/100 [00:18<00:16,  3.09it/s]\n 50%|█████     | 50/100 [00:18<00:16,  3.07it/s]\n 51%|█████     | 51/100 [00:18<00:15,  3.07it/s]\n 52%|█████▏    | 52/100 [00:19<00:15,  3.07it/s]\n 53%|█████▎    | 53/100 [00:19<00:15,  3.07it/s]\n 54%|█████▍    | 54/100 [00:19<00:14,  3.07it/s]\n 55%|█████▌    | 55/100 [00:20<00:14,  3.07it/s]\n 56%|█████▌    | 56/100 [00:20<00:14,  3.07it/s]\n 57%|█████▋    | 57/100 [00:20<00:14,  3.06it/s]\n 58%|█████▊    | 58/100 [00:21<00:13,  3.05it/s]\n 59%|█████▉    | 59/100 [00:21<00:13,  3.05it/s]\n 60%|██████    | 60/100 [00:21<00:13,  3.05it/s]\n 61%|██████    | 61/100 [00:22<00:12,  3.04it/s]\n 62%|██████▏   | 62/100 [00:22<00:12,  3.04it/s]\n 63%|██████▎   | 63/100 [00:22<00:12,  3.03it/s]\n 64%|██████▍   | 64/100 [00:23<00:11,  3.03it/s]\n 65%|██████▌   | 65/100 [00:23<00:11,  3.04it/s]\n 66%|██████▌   | 66/100 [00:23<00:11,  3.04it/s]\n 67%|██████▋   | 67/100 [00:24<00:10,  3.02it/s]\n 68%|██████▊   | 68/100 [00:24<00:10,  3.02it/s]\n 69%|██████▉   | 69/100 [00:24<00:10,  3.02it/s]\n 70%|███████   | 70/100 [00:25<00:09,  3.01it/s]\n 71%|███████   | 71/100 [00:25<00:09,  3.01it/s]\n 72%|███████▏  | 72/100 [00:25<00:09,  3.01it/s]\n 73%|███████▎  | 73/100 [00:26<00:09,  2.99it/s]\n 74%|███████▍  | 74/100 [00:26<00:08,  3.00it/s]\n 75%|███████▌  | 75/100 [00:26<00:08,  3.00it/s]\n 76%|███████▌  | 76/100 [00:27<00:08,  2.99it/s]\n 77%|███████▋  | 77/100 [00:27<00:07,  2.99it/s]\n 78%|███████▊  | 78/100 [00:27<00:07,  2.99it/s]\n 79%|███████▉  | 79/100 [00:28<00:07,  2.99it/s]\n 80%|████████  | 80/100 [00:28<00:06,  2.99it/s]\n 81%|████████  | 81/100 [00:28<00:06,  2.99it/s]\n 82%|████████▏ | 82/100 [00:29<00:06,  2.98it/s]\n 83%|████████▎ | 83/100 [00:29<00:05,  2.97it/s]\n 84%|████████▍ | 84/100 [00:29<00:05,  2.98it/s]\n 85%|████████▌ | 85/100 [00:30<00:05,  2.98it/s]\n 86%|████████▌ | 86/100 [00:30<00:04,  2.98it/s]\n 87%|████████▋ | 87/100 [00:30<00:04,  2.98it/s]\n 88%|████████▊ | 88/100 [00:31<00:04,  2.96it/s]\n 89%|████████▉ | 89/100 [00:31<00:03,  2.96it/s]\n 90%|█████████ | 90/100 [00:31<00:03,  2.97it/s]\n 91%|█████████ | 91/100 [00:32<00:03,  2.96it/s]\n 92%|█████████▏| 92/100 [00:32<00:02,  2.97it/s]\n 93%|█████████▎| 93/100 [00:32<00:02,  2.98it/s]\n 94%|█████████▍| 94/100 [00:33<00:02,  2.97it/s]\n 95%|█████████▌| 95/100 [00:33<00:01,  2.98it/s]\n 96%|█████████▌| 96/100 [00:33<00:01,  2.99it/s]\n 97%|█████████▋| 97/100 [00:34<00:01,  2.98it/s]\n 98%|█████████▊| 98/100 [00:34<00:00,  2.99it/s]\n 99%|█████████▉| 99/100 [00:34<00:00,  3.00it/s]\n100%|██████████| 100/100 [00:35<00:00,  3.00it/s]\n100%|██████████| 100/100 [00:35<00:00,  2.84it/s]\nSaving final sample/s",
  "metrics": {
    "predict_time": 40.089363,
    "total_time": 40.298987
  },
  "output": [
    [
      "https://replicate.delivery/mgxm/18798d43-04ea-4a39-ae1d-9e1bcee8bf89/current_0.png",
      "https://replicate.delivery/mgxm/5c6a268e-950c-4f71-acdc-07aebd5fdad5/current_1.png",
      "https://replicate.delivery/mgxm/f8154499-129a-4919-bc9c-8f65a8b32a3e/current_2.png",
      "https://replicate.delivery/mgxm/d8a9bbd1-e184-4148-9737-70dc0c2c1fd3/current_3.png",
      "https://replicate.delivery/mgxm/e10d03c1-3cd2-4f83-b644-78900be39631/current_4.png",
      "https://replicate.delivery/mgxm/e37899be-7c9e-4083-a68b-e1c92233fe0b/current_5.png"
    ]
  ],
  "started_at": "2022-07-10T10:31:27.683736Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/6ur4mbq6bvgq7ahfr6yiywsqbi",
    "cancel": "https://api.replicate.com/v1/predictions/6ur4mbq6bvgq7ahfr6yiywsqbi/cancel"
  },
  "version": "a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa"
}

Generated in

40.1 seconds

Tweak it ShareReport

Using seed 2877705998
Running simulation for stranger things
Encoding text embeddings with stranger things dimensions
Using aesthetic embedding 9 with weight 0.1
Running diffusion...

  0%|          | 0/100 [00:00<?, ?it/s]
  1%|          | 1/100 [00:01<02:03,  1.25s/it]
  2%|▏         | 2/100 [00:02<02:00,  1.23s/it]
  3%|▎         | 3/100 [00:03<01:59,  1.23s/it]
  4%|▍         | 4/100 [00:04<01:23,  1.16it/s]
  5%|▌         | 5/100 [00:04<01:03,  1.50it/s]
  6%|▌         | 6/100 [00:04<00:50,  1.84it/s]
  7%|▋         | 7/100 [00:04<00:43,  2.15it/s]
  8%|▊         | 8/100 [00:05<00:38,  2.41it/s]
  9%|▉         | 9/100 [00:05<00:34,  2.61it/s]
 10%|█         | 10/100 [00:05<00:32,  2.78it/s]
 11%|█         | 11/100 [00:06<00:30,  2.91it/s]
 12%|█▏        | 12/100 [00:06<00:29,  3.00it/s]
 13%|█▎        | 13/100 [00:06<00:28,  3.06it/s]
 14%|█▍        | 14/100 [00:07<00:27,  3.11it/s]
 15%|█▌        | 15/100 [00:07<00:27,  3.15it/s]
 16%|█▌        | 16/100 [00:07<00:26,  3.16it/s]
 17%|█▋        | 17/100 [00:08<00:26,  3.17it/s]
 18%|█▊        | 18/100 [00:08<00:25,  3.18it/s]
 19%|█▉        | 19/100 [00:08<00:25,  3.18it/s]
 20%|██        | 20/100 [00:08<00:25,  3.18it/s]
 21%|██        | 21/100 [00:09<00:24,  3.18it/s]
 22%|██▏       | 22/100 [00:09<00:24,  3.17it/s]
 23%|██▎       | 23/100 [00:09<00:24,  3.18it/s]
 24%|██▍       | 24/100 [00:10<00:23,  3.17it/s]
 25%|██▌       | 25/100 [00:10<00:23,  3.17it/s]
 26%|██▌       | 26/100 [00:10<00:23,  3.18it/s]
 27%|██▋       | 27/100 [00:11<00:23,  3.17it/s]
 28%|██▊       | 28/100 [00:11<00:22,  3.17it/s]
 29%|██▉       | 29/100 [00:11<00:22,  3.15it/s]
 30%|███       | 30/100 [00:12<00:22,  3.16it/s]
 31%|███       | 31/100 [00:12<00:21,  3.17it/s]
 32%|███▏      | 32/100 [00:12<00:21,  3.15it/s]
 33%|███▎      | 33/100 [00:13<00:21,  3.16it/s]
 34%|███▍      | 34/100 [00:13<00:20,  3.16it/s]
 35%|███▌      | 35/100 [00:13<00:20,  3.14it/s]
 36%|███▌      | 36/100 [00:14<00:20,  3.15it/s]
 37%|███▋      | 37/100 [00:14<00:20,  3.14it/s]
 38%|███▊      | 38/100 [00:14<00:19,  3.13it/s]
 39%|███▉      | 39/100 [00:14<00:19,  3.12it/s]
 40%|████      | 40/100 [00:15<00:19,  3.12it/s]
 41%|████      | 41/100 [00:15<00:18,  3.14it/s]
 42%|████▏     | 42/100 [00:15<00:18,  3.13it/s]
 43%|████▎     | 43/100 [00:16<00:18,  3.11it/s]
 44%|████▍     | 44/100 [00:16<00:17,  3.11it/s]
 45%|████▌     | 45/100 [00:16<00:17,  3.10it/s]
 46%|████▌     | 46/100 [00:17<00:17,  3.10it/s]
 47%|████▋     | 47/100 [00:17<00:17,  3.09it/s]
 48%|████▊     | 48/100 [00:17<00:16,  3.08it/s]
 49%|████▉     | 49/100 [00:18<00:16,  3.09it/s]
 50%|█████     | 50/100 [00:18<00:16,  3.07it/s]
 51%|█████     | 51/100 [00:18<00:15,  3.07it/s]
 52%|█████▏    | 52/100 [00:19<00:15,  3.07it/s]
 53%|█████▎    | 53/100 [00:19<00:15,  3.07it/s]
 54%|█████▍    | 54/100 [00:19<00:14,  3.07it/s]
 55%|█████▌    | 55/100 [00:20<00:14,  3.07it/s]
 56%|█████▌    | 56/100 [00:20<00:14,  3.07it/s]
 57%|█████▋    | 57/100 [00:20<00:14,  3.06it/s]
 58%|█████▊    | 58/100 [00:21<00:13,  3.05it/s]
 59%|█████▉    | 59/100 [00:21<00:13,  3.05it/s]
 60%|██████    | 60/100 [00:21<00:13,  3.05it/s]
 61%|██████    | 61/100 [00:22<00:12,  3.04it/s]
 62%|██████▏   | 62/100 [00:22<00:12,  3.04it/s]
 63%|██████▎   | 63/100 [00:22<00:12,  3.03it/s]
 64%|██████▍   | 64/100 [00:23<00:11,  3.03it/s]
 65%|██████▌   | 65/100 [00:23<00:11,  3.04it/s]
 66%|██████▌   | 66/100 [00:23<00:11,  3.04it/s]
 67%|██████▋   | 67/100 [00:24<00:10,  3.02it/s]
 68%|██████▊   | 68/100 [00:24<00:10,  3.02it/s]
 69%|██████▉   | 69/100 [00:24<00:10,  3.02it/s]
 70%|███████   | 70/100 [00:25<00:09,  3.01it/s]
 71%|███████   | 71/100 [00:25<00:09,  3.01it/s]
 72%|███████▏  | 72/100 [00:25<00:09,  3.01it/s]
 73%|███████▎  | 73/100 [00:26<00:09,  2.99it/s]
 74%|███████▍  | 74/100 [00:26<00:08,  3.00it/s]
 75%|███████▌  | 75/100 [00:26<00:08,  3.00it/s]
 76%|███████▌  | 76/100 [00:27<00:08,  2.99it/s]
 77%|███████▋  | 77/100 [00:27<00:07,  2.99it/s]
 78%|███████▊  | 78/100 [00:27<00:07,  2.99it/s]
 79%|███████▉  | 79/100 [00:28<00:07,  2.99it/s]
 80%|████████  | 80/100 [00:28<00:06,  2.99it/s]
 81%|████████  | 81/100 [00:28<00:06,  2.99it/s]
 82%|████████▏ | 82/100 [00:29<00:06,  2.98it/s]
 83%|████████▎ | 83/100 [00:29<00:05,  2.97it/s]
 84%|████████▍ | 84/100 [00:29<00:05,  2.98it/s]
 85%|████████▌ | 85/100 [00:30<00:05,  2.98it/s]
 86%|████████▌ | 86/100 [00:30<00:04,  2.98it/s]
 87%|████████▋ | 87/100 [00:30<00:04,  2.98it/s]
 88%|████████▊ | 88/100 [00:31<00:04,  2.96it/s]
 89%|████████▉ | 89/100 [00:31<00:03,  2.96it/s]
 90%|█████████ | 90/100 [00:31<00:03,  2.97it/s]
 91%|█████████ | 91/100 [00:32<00:03,  2.96it/s]
 92%|█████████▏| 92/100 [00:32<00:02,  2.97it/s]
 93%|█████████▎| 93/100 [00:32<00:02,  2.98it/s]
 94%|█████████▍| 94/100 [00:33<00:02,  2.97it/s]
 95%|█████████▌| 95/100 [00:33<00:01,  2.98it/s]
 96%|█████████▌| 96/100 [00:33<00:01,  2.99it/s]
 97%|█████████▋| 97/100 [00:34<00:01,  2.98it/s]
 98%|█████████▊| 98/100 [00:34<00:00,  2.99it/s]
 99%|█████████▉| 99/100 [00:34<00:00,  3.00it/s]
100%|██████████| 100/100 [00:35<00:00,  3.00it/s]
100%|██████████| 100/100 [00:35<00:00,  2.84it/s]
Saving final sample/s

Prediction

laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa

Model

laion-ai/erlich:a51ce279

ammwcg4ktzavxcxefr4mrtfxuu

Status

Succeeded

Source

Web

Hardware

–

Total duration

36.9s

Created

almost 3 years ago by @afiaka87

Input

seed: "-1"
steps: "100"
width: "256"
height: "256"
prompt: vector logo, owl with wings spread on fire, purple fire, psychedelic, symbol
batch_size: "6"
guidance_scale: "5"
aesthetic_rating: 9
aesthetic_weight: 0.1

{
  "seed": "-1",
  "steps": "100",
  "width": "256",
  "height": "256",
  "prompt": "vector logo, owl with wings spread on fire, purple fire, psychedelic, symbol",
  "batch_size": "6",
  "guidance_scale": "5",
  "aesthetic_rating": 9,
  "aesthetic_weight": 0.1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
  {
    input: {
      seed: "-1",
      steps: "100",
      width: "256",
      height: "256",
      prompt: "vector logo, owl with wings spread on fire, purple fire, psychedelic, symbol",
      batch_size: "6",
      guidance_scale: "5",
      aesthetic_rating: 9,
      aesthetic_weight: 0.1
    }
  }
);

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

Import the client:

import replicate

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
    input={
        "seed": "-1",
        "steps": "100",
        "width": "256",
        "height": "256",
        "prompt": "vector logo, owl with wings spread on fire, purple fire, psychedelic, symbol",
        "batch_size": "6",
        "guidance_scale": "5",
        "aesthetic_rating": 9,
        "aesthetic_weight": 0.1
    }
)

# The laion-ai/erlich 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/erlich/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run laion-ai/erlich 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": "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
    "input": {
      "seed": "-1",
      "steps": "100",
      "width": "256",
      "height": "256",
      "prompt": "vector logo, owl with wings spread on fire, purple fire, psychedelic, symbol",
      "batch_size": "6",
      "guidance_scale": "5",
      "aesthetic_rating": 9,
      "aesthetic_weight": 0.1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-07-21T19:32:46Z",
  "created_at": "2022-07-21T19:32:09.128980Z",
  "data_removed": false,
  "error": "",
  "id": "ammwcg4ktzavxcxefr4mrtfxuu",
  "input": {
    "seed": "-1",
    "steps": "100",
    "width": "256",
    "height": "256",
    "prompt": "vector logo, owl with wings spread on fire, purple fire, psychedelic, symbol",
    "batch_size": "6",
    "guidance_scale": "5",
    "aesthetic_rating": 9,
    "aesthetic_weight": 0.1
  },
  "logs": "Using seed 16158454\r\nRunning simulation for vector logo, owl with wings spread on fire, purple fire, psychedelic, symbol\r\nEncoding text embeddings with vector logo, owl with wings spread on fire, purple fire, psychedelic, symbol dimensions\r\nUsing aesthetic embedding 9 with weight 0.1\r\nRunning diffusion...\r\n\r\n  0%|          | 0/100 [00:00<?, ?it/s]\r\n  1%|          | 1/100 [00:01<01:58,  1.20s/it]\r\n  2%|▏         | 2/100 [00:02<01:54,  1.17s/it]\r\n  3%|▎         | 3/100 [00:03<01:52,  1.16s/it]\r\n  4%|▍         | 4/100 [00:03<01:18,  1.23it/s]\r\n  5%|▌         | 5/100 [00:04<00:59,  1.60it/s]\r\n  6%|▌         | 6/100 [00:04<00:48,  1.95it/s]\r\n  7%|▋         | 7/100 [00:04<00:40,  2.28it/s]\r\n  8%|▊         | 8/100 [00:04<00:35,  2.56it/s]\r\n  9%|▉         | 9/100 [00:05<00:32,  2.79it/s]\r\n 10%|█         | 10/100 [00:05<00:30,  2.96it/s]\r\n 11%|█         | 11/100 [00:05<00:28,  3.10it/s]\r\n 12%|█▏        | 12/100 [00:06<00:27,  3.20it/s]\r\n 13%|█▎        | 13/100 [00:06<00:26,  3.27it/s]\r\n 14%|█▍        | 14/100 [00:06<00:25,  3.33it/s]\r\n 15%|█▌        | 15/100 [00:06<00:25,  3.38it/s]\r\n 16%|█▌        | 16/100 [00:07<00:24,  3.40it/s]\r\n 17%|█▋        | 17/100 [00:07<00:24,  3.41it/s]\r\n 18%|█▊        | 18/100 [00:07<00:23,  3.43it/s]\r\n 19%|█▉        | 19/100 [00:08<00:23,  3.44it/s]\r\n 20%|██        | 20/100 [00:08<00:23,  3.44it/s]\r\n 21%|██        | 21/100 [00:08<00:23,  3.43it/s]\r\n 22%|██▏       | 22/100 [00:08<00:22,  3.45it/s]\r\n 23%|██▎       | 23/100 [00:09<00:22,  3.44it/s]\r\n 24%|██▍       | 24/100 [00:09<00:22,  3.43it/s]\r\n 25%|██▌       | 25/100 [00:09<00:21,  3.44it/s]\r\n 26%|██▌       | 26/100 [00:10<00:21,  3.44it/s]\r\n 27%|██▋       | 27/100 [00:10<00:21,  3.44it/s]\r\n 28%|██▊       | 28/100 [00:10<00:20,  3.44it/s]\r\n 29%|██▉       | 29/100 [00:11<00:20,  3.44it/s]\r\n 30%|███       | 30/100 [00:11<00:20,  3.44it/s]\r\n 31%|███       | 31/100 [00:11<00:20,  3.44it/s]\r\n 32%|███▏      | 32/100 [00:11<00:19,  3.43it/s]\r\n 33%|███▎      | 33/100 [00:12<00:19,  3.44it/s]\r\n 34%|███▍      | 34/100 [00:12<00:19,  3.44it/s]\r\n 35%|███▌      | 35/100 [00:12<00:18,  3.44it/s]\r\n 36%|███▌      | 36/100 [00:13<00:18,  3.44it/s]\r\n 37%|███▋      | 37/100 [00:13<00:18,  3.44it/s]\r\n 38%|███▊      | 38/100 [00:13<00:18,  3.43it/s]\r\n 39%|███▉      | 39/100 [00:13<00:17,  3.43it/s]\r\n 40%|████      | 40/100 [00:14<00:17,  3.43it/s]\r\n 41%|████      | 41/100 [00:14<00:17,  3.43it/s]\r\n 42%|████▏     | 42/100 [00:14<00:16,  3.43it/s]\r\n 43%|████▎     | 43/100 [00:15<00:16,  3.43it/s]\r\n 44%|████▍     | 44/100 [00:15<00:16,  3.43it/s]\r\n 45%|████▌     | 45/100 [00:15<00:16,  3.42it/s]\r\n 46%|████▌     | 46/100 [00:15<00:15,  3.42it/s]\r\n 47%|████▋     | 47/100 [00:16<00:15,  3.43it/s]\r\n 48%|████▊     | 48/100 [00:16<00:15,  3.42it/s]\r\n 49%|████▉     | 49/100 [00:16<00:14,  3.42it/s]\r\n 50%|█████     | 50/100 [00:17<00:14,  3.42it/s]\r\n 51%|█████     | 51/100 [00:17<00:14,  3.43it/s]\r\n 52%|█████▏    | 52/100 [00:17<00:14,  3.42it/s]\r\n 53%|█████▎    | 53/100 [00:18<00:13,  3.42it/s]\r\n 54%|█████▍    | 54/100 [00:18<00:13,  3.42it/s]\r\n 55%|█████▌    | 55/100 [00:18<00:13,  3.42it/s]\r\n 56%|█████▌    | 56/100 [00:18<00:12,  3.42it/s]\r\n 57%|█████▋    | 57/100 [00:19<00:12,  3.42it/s]\r\n 58%|█████▊    | 58/100 [00:19<00:12,  3.42it/s]\r\n 59%|█████▉    | 59/100 [00:19<00:12,  3.41it/s]\r\n 60%|██████    | 60/100 [00:20<00:11,  3.41it/s]\r\n 61%|██████    | 61/100 [00:20<00:11,  3.41it/s]\r\n 62%|██████▏   | 62/100 [00:20<00:11,  3.42it/s]\r\n 63%|██████▎   | 63/100 [00:20<00:10,  3.42it/s]\r\n 64%|██████▍   | 64/100 [00:21<00:10,  3.42it/s]\r\n 65%|██████▌   | 65/100 [00:21<00:10,  3.42it/s]\r\n 66%|██████▌   | 66/100 [00:21<00:09,  3.41it/s]\r\n 67%|██████▋   | 67/100 [00:22<00:09,  3.41it/s]\r\n 68%|██████▊   | 68/100 [00:22<00:09,  3.41it/s]\r\n 69%|██████▉   | 69/100 [00:22<00:09,  3.41it/s]\r\n 70%|███████   | 70/100 [00:23<00:08,  3.41it/s]\r\n 71%|███████   | 71/100 [00:23<00:08,  3.41it/s]\r\n 72%|███████▏  | 72/100 [00:23<00:08,  3.41it/s]\r\n 73%|███████▎  | 73/100 [00:23<00:07,  3.41it/s]\r\n 74%|███████▍  | 74/100 [00:24<00:07,  3.41it/s]\r\n 75%|███████▌  | 75/100 [00:24<00:07,  3.41it/s]\r\n 76%|███████▌  | 76/100 [00:24<00:07,  3.40it/s]\r\n 77%|███████▋  | 77/100 [00:25<00:06,  3.40it/s]\r\n 78%|███████▊  | 78/100 [00:25<00:06,  3.40it/s]\r\n 79%|███████▉  | 79/100 [00:25<00:06,  3.40it/s]\r\n 80%|████████  | 80/100 [00:25<00:05,  3.40it/s]\r\n 81%|████████  | 81/100 [00:26<00:05,  3.40it/s]\r\n 82%|████████▏ | 82/100 [00:26<00:05,  3.41it/s]\r\n 83%|████████▎ | 83/100 [00:26<00:04,  3.41it/s]\r\n 84%|████████▍ | 84/100 [00:27<00:04,  3.41it/s]\r\n 85%|████████▌ | 85/100 [00:27<00:04,  3.41it/s]\r\n 86%|████████▌ | 86/100 [00:27<00:04,  3.41it/s]\r\n 87%|████████▋ | 87/100 [00:27<00:03,  3.40it/s]\r\n 88%|████████▊ | 88/100 [00:28<00:03,  3.40it/s]\r\n 89%|████████▉ | 89/100 [00:28<00:03,  3.40it/s]\r\n 90%|█████████ | 90/100 [00:28<00:02,  3.40it/s]\r\n 91%|█████████ | 91/100 [00:29<00:02,  3.40it/s]\r\n 92%|█████████▏| 92/100 [00:29<00:02,  3.39it/s]\r\n 93%|█████████▎| 93/100 [00:29<00:02,  3.39it/s]\r\n 94%|█████████▍| 94/100 [00:30<00:01,  3.39it/s]\r\n 95%|█████████▌| 95/100 [00:30<00:01,  3.40it/s]\r\n 96%|█████████▌| 96/100 [00:30<00:01,  3.39it/s]\r\n 97%|█████████▋| 97/100 [00:30<00:00,  3.39it/s]\r\n 98%|█████████▊| 98/100 [00:31<00:00,  3.38it/s]\r\n 99%|█████████▉| 99/100 [00:31<00:00,  3.39it/s]\r\n100%|██████████| 100/100 [00:31<00:00,  3.39it/s]\r\n100%|██████████| 100/100 [00:31<00:00,  3.14it/s]\r\nSaving final sample/s",
  "metrics": {
    "predict_time": 37,
    "total_time": 36.87102
  },
  "output": [
    [
      "https://replicate.delivery/mgxm/0a305d40-edc8-48a3-a801-e4ed6e37d0c8/current_0.png",
      "https://replicate.delivery/mgxm/13dc984f-aadc-4af7-8071-d32e03873d47/current_1.png",
      "https://replicate.delivery/mgxm/4c4c03b9-1b4b-495f-9203-9a6a6e0da708/current_2.png",
      "https://replicate.delivery/mgxm/d1c8d266-4eb9-4096-9947-620ac22175cc/current_3.png",
      "https://replicate.delivery/mgxm/1f348c2d-c4c7-48ab-8372-3c913ecbe2b5/current_4.png",
      "https://replicate.delivery/mgxm/a56af400-8cb1-457d-8395-65d355b46e03/current_5.png"
    ]
  ],
  "started_at": "2022-07-21T19:32:09Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ammwcg4ktzavxcxefr4mrtfxuu",
    "cancel": "https://api.replicate.com/v1/predictions/ammwcg4ktzavxcxefr4mrtfxuu/cancel"
  },
  "version": "a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa"
}

Generated in

37.0 seconds

Tweak it ShareReport

Using seed 16158454
Running simulation for vector logo, owl with wings spread on fire, purple fire, psychedelic, symbol
Encoding text embeddings with vector logo, owl with wings spread on fire, purple fire, psychedelic, symbol dimensions
Using aesthetic embedding 9 with weight 0.1
Running diffusion...

  0%|          | 0/100 [00:00<?, ?it/s]
  1%|          | 1/100 [00:01<01:58,  1.20s/it]
  2%|▏         | 2/100 [00:02<01:54,  1.17s/it]
  3%|▎         | 3/100 [00:03<01:52,  1.16s/it]
  4%|▍         | 4/100 [00:03<01:18,  1.23it/s]
  5%|▌         | 5/100 [00:04<00:59,  1.60it/s]
  6%|▌         | 6/100 [00:04<00:48,  1.95it/s]
  7%|▋         | 7/100 [00:04<00:40,  2.28it/s]
  8%|▊         | 8/100 [00:04<00:35,  2.56it/s]
  9%|▉         | 9/100 [00:05<00:32,  2.79it/s]
 10%|█         | 10/100 [00:05<00:30,  2.96it/s]
 11%|█         | 11/100 [00:05<00:28,  3.10it/s]
 12%|█▏        | 12/100 [00:06<00:27,  3.20it/s]
 13%|█▎        | 13/100 [00:06<00:26,  3.27it/s]
 14%|█▍        | 14/100 [00:06<00:25,  3.33it/s]
 15%|█▌        | 15/100 [00:06<00:25,  3.38it/s]
 16%|█▌        | 16/100 [00:07<00:24,  3.40it/s]
 17%|█▋        | 17/100 [00:07<00:24,  3.41it/s]
 18%|█▊        | 18/100 [00:07<00:23,  3.43it/s]
 19%|█▉        | 19/100 [00:08<00:23,  3.44it/s]
 20%|██        | 20/100 [00:08<00:23,  3.44it/s]
 21%|██        | 21/100 [00:08<00:23,  3.43it/s]
 22%|██▏       | 22/100 [00:08<00:22,  3.45it/s]
 23%|██▎       | 23/100 [00:09<00:22,  3.44it/s]
 24%|██▍       | 24/100 [00:09<00:22,  3.43it/s]
 25%|██▌       | 25/100 [00:09<00:21,  3.44it/s]
 26%|██▌       | 26/100 [00:10<00:21,  3.44it/s]
 27%|██▋       | 27/100 [00:10<00:21,  3.44it/s]
 28%|██▊       | 28/100 [00:10<00:20,  3.44it/s]
 29%|██▉       | 29/100 [00:11<00:20,  3.44it/s]
 30%|███       | 30/100 [00:11<00:20,  3.44it/s]
 31%|███       | 31/100 [00:11<00:20,  3.44it/s]
 32%|███▏      | 32/100 [00:11<00:19,  3.43it/s]
 33%|███▎      | 33/100 [00:12<00:19,  3.44it/s]
 34%|███▍      | 34/100 [00:12<00:19,  3.44it/s]
 35%|███▌      | 35/100 [00:12<00:18,  3.44it/s]
 36%|███▌      | 36/100 [00:13<00:18,  3.44it/s]
 37%|███▋      | 37/100 [00:13<00:18,  3.44it/s]
 38%|███▊      | 38/100 [00:13<00:18,  3.43it/s]
 39%|███▉      | 39/100 [00:13<00:17,  3.43it/s]
 40%|████      | 40/100 [00:14<00:17,  3.43it/s]
 41%|████      | 41/100 [00:14<00:17,  3.43it/s]
 42%|████▏     | 42/100 [00:14<00:16,  3.43it/s]
 43%|████▎     | 43/100 [00:15<00:16,  3.43it/s]
 44%|████▍     | 44/100 [00:15<00:16,  3.43it/s]
 45%|████▌     | 45/100 [00:15<00:16,  3.42it/s]
 46%|████▌     | 46/100 [00:15<00:15,  3.42it/s]
 47%|████▋     | 47/100 [00:16<00:15,  3.43it/s]
 48%|████▊     | 48/100 [00:16<00:15,  3.42it/s]
 49%|████▉     | 49/100 [00:16<00:14,  3.42it/s]
 50%|█████     | 50/100 [00:17<00:14,  3.42it/s]
 51%|█████     | 51/100 [00:17<00:14,  3.43it/s]
 52%|█████▏    | 52/100 [00:17<00:14,  3.42it/s]
 53%|█████▎    | 53/100 [00:18<00:13,  3.42it/s]
 54%|█████▍    | 54/100 [00:18<00:13,  3.42it/s]
 55%|█████▌    | 55/100 [00:18<00:13,  3.42it/s]
 56%|█████▌    | 56/100 [00:18<00:12,  3.42it/s]
 57%|█████▋    | 57/100 [00:19<00:12,  3.42it/s]
 58%|█████▊    | 58/100 [00:19<00:12,  3.42it/s]
 59%|█████▉    | 59/100 [00:19<00:12,  3.41it/s]
 60%|██████    | 60/100 [00:20<00:11,  3.41it/s]
 61%|██████    | 61/100 [00:20<00:11,  3.41it/s]
 62%|██████▏   | 62/100 [00:20<00:11,  3.42it/s]
 63%|██████▎   | 63/100 [00:20<00:10,  3.42it/s]
 64%|██████▍   | 64/100 [00:21<00:10,  3.42it/s]
 65%|██████▌   | 65/100 [00:21<00:10,  3.42it/s]
 66%|██████▌   | 66/100 [00:21<00:09,  3.41it/s]
 67%|██████▋   | 67/100 [00:22<00:09,  3.41it/s]
 68%|██████▊   | 68/100 [00:22<00:09,  3.41it/s]
 69%|██████▉   | 69/100 [00:22<00:09,  3.41it/s]
 70%|███████   | 70/100 [00:23<00:08,  3.41it/s]
 71%|███████   | 71/100 [00:23<00:08,  3.41it/s]
 72%|███████▏  | 72/100 [00:23<00:08,  3.41it/s]
 73%|███████▎  | 73/100 [00:23<00:07,  3.41it/s]
 74%|███████▍  | 74/100 [00:24<00:07,  3.41it/s]
 75%|███████▌  | 75/100 [00:24<00:07,  3.41it/s]
 76%|███████▌  | 76/100 [00:24<00:07,  3.40it/s]
 77%|███████▋  | 77/100 [00:25<00:06,  3.40it/s]
 78%|███████▊  | 78/100 [00:25<00:06,  3.40it/s]
 79%|███████▉  | 79/100 [00:25<00:06,  3.40it/s]
 80%|████████  | 80/100 [00:25<00:05,  3.40it/s]
 81%|████████  | 81/100 [00:26<00:05,  3.40it/s]
 82%|████████▏ | 82/100 [00:26<00:05,  3.41it/s]
 83%|████████▎ | 83/100 [00:26<00:04,  3.41it/s]
 84%|████████▍ | 84/100 [00:27<00:04,  3.41it/s]
 85%|████████▌ | 85/100 [00:27<00:04,  3.41it/s]
 86%|████████▌ | 86/100 [00:27<00:04,  3.41it/s]
 87%|████████▋ | 87/100 [00:27<00:03,  3.40it/s]
 88%|████████▊ | 88/100 [00:28<00:03,  3.40it/s]
 89%|████████▉ | 89/100 [00:28<00:03,  3.40it/s]
 90%|█████████ | 90/100 [00:28<00:02,  3.40it/s]
 91%|█████████ | 91/100 [00:29<00:02,  3.40it/s]
 92%|█████████▏| 92/100 [00:29<00:02,  3.39it/s]
 93%|█████████▎| 93/100 [00:29<00:02,  3.39it/s]
 94%|█████████▍| 94/100 [00:30<00:01,  3.39it/s]
 95%|█████████▌| 95/100 [00:30<00:01,  3.40it/s]
 96%|█████████▌| 96/100 [00:30<00:01,  3.39it/s]
 97%|█████████▋| 97/100 [00:30<00:00,  3.39it/s]
 98%|█████████▊| 98/100 [00:31<00:00,  3.38it/s]
 99%|█████████▉| 99/100 [00:31<00:00,  3.39it/s]
100%|██████████| 100/100 [00:31<00:00,  3.39it/s]
100%|██████████| 100/100 [00:31<00:00,  3.14it/s]
Saving final sample/s

Prediction

laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa

Model

laion-ai/erlich:a51ce279

5mychegnafh73mrc2zmbdvxfqi

Status

Succeeded

Source

Web

Hardware

–

Total duration

38.5s

Created

almost 3 years ago

Input

seed: "-1"
steps: "100"
width: "256"
height: "256"
prompt: paper plane logo with shadow of plane flying around the world, logo, vector
batch_size: "6"
guidance_scale: "5"
aesthetic_rating: 9
aesthetic_weight: 0.1

{
  "seed": "-1",
  "steps": "100",
  "width": "256",
  "height": "256",
  "prompt": "paper plane logo with shadow of plane flying around the world, logo, vector",
  "batch_size": "6",
  "guidance_scale": "5",
  "aesthetic_rating": 9,
  "aesthetic_weight": 0.1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
  {
    input: {
      seed: "-1",
      steps: "100",
      width: "256",
      height: "256",
      prompt: "paper plane logo with shadow of plane flying around the world, logo, vector",
      batch_size: "6",
      guidance_scale: "5",
      aesthetic_rating: 9,
      aesthetic_weight: 0.1
    }
  }
);

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

Import the client:

import replicate

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
    input={
        "seed": "-1",
        "steps": "100",
        "width": "256",
        "height": "256",
        "prompt": "paper plane logo with shadow of plane flying around the world, logo, vector",
        "batch_size": "6",
        "guidance_scale": "5",
        "aesthetic_rating": 9,
        "aesthetic_weight": 0.1
    }
)

# The laion-ai/erlich 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/erlich/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run laion-ai/erlich 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": "laion-ai/erlich:a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa",
    "input": {
      "seed": "-1",
      "steps": "100",
      "width": "256",
      "height": "256",
      "prompt": "paper plane logo with shadow of plane flying around the world, logo, vector",
      "batch_size": "6",
      "guidance_scale": "5",
      "aesthetic_rating": 9,
      "aesthetic_weight": 0.1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-07-21T19:34:51.200560Z",
  "created_at": "2022-07-21T19:34:12.690573Z",
  "data_removed": false,
  "error": null,
  "id": "5mychegnafh73mrc2zmbdvxfqi",
  "input": {
    "seed": "-1",
    "steps": "100",
    "width": "256",
    "height": "256",
    "prompt": "paper plane logo with shadow of plane flying around the world, logo, vector",
    "batch_size": "6",
    "guidance_scale": "5",
    "aesthetic_rating": 9,
    "aesthetic_weight": 0.1
  },
  "logs": "Using seed 2312414383\nRunning simulation for paper plane logo with shadow of plane flying around the world, logo, vector\nEncoding text embeddings with paper plane logo with shadow of plane flying around the world, logo, vector dimensions\nUsing aesthetic embedding 9 with weight 0.1\nRunning diffusion...\n\n  0%|          | 0/100 [00:00<?, ?it/s]\n  1%|          | 1/100 [00:01<02:01,  1.23s/it]\n  2%|▏         | 2/100 [00:02<01:53,  1.16s/it]\n  3%|▎         | 3/100 [00:03<01:50,  1.14s/it]\n  4%|▍         | 4/100 [00:03<01:16,  1.25it/s]\n  5%|▌         | 5/100 [00:04<00:58,  1.63it/s]\n  6%|▌         | 6/100 [00:04<00:46,  2.01it/s]\n  7%|▋         | 7/100 [00:04<00:39,  2.34it/s]\n  8%|▊         | 8/100 [00:04<00:34,  2.63it/s]\n  9%|▉         | 9/100 [00:05<00:31,  2.87it/s]\n 10%|█         | 10/100 [00:05<00:29,  3.06it/s]\n 11%|█         | 11/100 [00:05<00:27,  3.21it/s]\n 12%|█▏        | 12/100 [00:05<00:26,  3.31it/s]\n 13%|█▎        | 13/100 [00:06<00:25,  3.39it/s]\n 14%|█▍        | 14/100 [00:06<00:25,  3.44it/s]\n 15%|█▌        | 15/100 [00:06<00:24,  3.48it/s]\n 16%|█▌        | 16/100 [00:07<00:23,  3.52it/s]\n 17%|█▋        | 17/100 [00:07<00:23,  3.53it/s]\n 18%|█▊        | 18/100 [00:07<00:23,  3.54it/s]\n 19%|█▉        | 19/100 [00:07<00:22,  3.55it/s]\n 20%|██        | 20/100 [00:08<00:22,  3.57it/s]\n 21%|██        | 21/100 [00:08<00:22,  3.57it/s]\n 22%|██▏       | 22/100 [00:08<00:21,  3.57it/s]\n 23%|██▎       | 23/100 [00:09<00:21,  3.57it/s]\n 24%|██▍       | 24/100 [00:09<00:21,  3.57it/s]\n 25%|██▌       | 25/100 [00:09<00:21,  3.57it/s]\n 26%|██▌       | 26/100 [00:09<00:20,  3.56it/s]\n 27%|██▋       | 27/100 [00:10<00:20,  3.57it/s]\n 28%|██▊       | 28/100 [00:10<00:20,  3.57it/s]\n 29%|██▉       | 29/100 [00:10<00:19,  3.56it/s]\n 30%|███       | 30/100 [00:11<00:19,  3.57it/s]\n 31%|███       | 31/100 [00:11<00:19,  3.56it/s]\n 32%|███▏      | 32/100 [00:11<00:19,  3.57it/s]\n 33%|███▎      | 33/100 [00:11<00:18,  3.56it/s]\n 34%|███▍      | 34/100 [00:12<00:18,  3.56it/s]\n 35%|███▌      | 35/100 [00:12<00:18,  3.56it/s]\n 36%|███▌      | 36/100 [00:12<00:18,  3.55it/s]\n 37%|███▋      | 37/100 [00:12<00:17,  3.55it/s]\n 38%|███▊      | 38/100 [00:13<00:17,  3.55it/s]\n 39%|███▉      | 39/100 [00:13<00:17,  3.56it/s]\n 40%|████      | 40/100 [00:13<00:16,  3.55it/s]\n 41%|████      | 41/100 [00:14<00:16,  3.55it/s]\n 42%|████▏     | 42/100 [00:14<00:16,  3.56it/s]\n 43%|████▎     | 43/100 [00:14<00:15,  3.57it/s]\n 44%|████▍     | 44/100 [00:14<00:15,  3.56it/s]\n 45%|████▌     | 45/100 [00:15<00:15,  3.56it/s]\n 46%|████▌     | 46/100 [00:15<00:15,  3.55it/s]\n 47%|████▋     | 47/100 [00:15<00:14,  3.56it/s]\n 48%|████▊     | 48/100 [00:16<00:14,  3.55it/s]\n 49%|████▉     | 49/100 [00:16<00:14,  3.54it/s]\n 50%|█████     | 50/100 [00:16<00:14,  3.55it/s]\n 51%|█████     | 51/100 [00:16<00:13,  3.56it/s]\n 52%|█████▏    | 52/100 [00:17<00:13,  3.56it/s]\n 53%|█████▎    | 53/100 [00:17<00:13,  3.56it/s]\n 54%|█████▍    | 54/100 [00:17<00:12,  3.55it/s]\n 55%|█████▌    | 55/100 [00:18<00:12,  3.55it/s]\n 56%|█████▌    | 56/100 [00:18<00:12,  3.54it/s]\n 57%|█████▋    | 57/100 [00:18<00:12,  3.54it/s]\n 58%|█████▊    | 58/100 [00:18<00:11,  3.55it/s]\n 59%|█████▉    | 59/100 [00:19<00:11,  3.54it/s]\n 60%|██████    | 60/100 [00:19<00:11,  3.52it/s]\n 61%|██████    | 61/100 [00:19<00:11,  3.53it/s]\n 62%|██████▏   | 62/100 [00:20<00:10,  3.53it/s]\n 63%|██████▎   | 63/100 [00:20<00:10,  3.53it/s]\n 64%|██████▍   | 64/100 [00:20<00:10,  3.53it/s]\n 65%|██████▌   | 65/100 [00:20<00:09,  3.53it/s]\n 66%|██████▌   | 66/100 [00:21<00:09,  3.53it/s]\n 67%|██████▋   | 67/100 [00:21<00:09,  3.52it/s]\n 68%|██████▊   | 68/100 [00:21<00:09,  3.52it/s]\n 69%|██████▉   | 69/100 [00:22<00:08,  3.53it/s]\n 70%|███████   | 70/100 [00:22<00:08,  3.53it/s]\n 71%|███████   | 71/100 [00:22<00:08,  3.53it/s]\n 72%|███████▏  | 72/100 [00:22<00:07,  3.53it/s]\n 73%|███████▎  | 73/100 [00:23<00:07,  3.53it/s]\n 74%|███████▍  | 74/100 [00:23<00:07,  3.53it/s]\n 75%|███████▌  | 75/100 [00:23<00:07,  3.53it/s]\n 76%|███████▌  | 76/100 [00:23<00:06,  3.52it/s]\n 77%|███████▋  | 77/100 [00:24<00:06,  3.52it/s]\n 78%|███████▊  | 78/100 [00:24<00:06,  3.52it/s]\n 79%|███████▉  | 79/100 [00:24<00:05,  3.53it/s]\n 80%|████████  | 80/100 [00:25<00:05,  3.52it/s]\n 81%|████████  | 81/100 [00:25<00:05,  3.52it/s]\n 82%|████████▏ | 82/100 [00:25<00:05,  3.53it/s]\n 83%|████████▎ | 83/100 [00:25<00:04,  3.52it/s]\n 84%|████████▍ | 84/100 [00:26<00:04,  3.52it/s]\n 85%|████████▌ | 85/100 [00:26<00:04,  3.52it/s]\n 86%|████████▌ | 86/100 [00:26<00:03,  3.53it/s]\n 87%|████████▋ | 87/100 [00:27<00:03,  3.52it/s]\n 88%|████████▊ | 88/100 [00:27<00:03,  3.52it/s]\n 89%|████████▉ | 89/100 [00:27<00:03,  3.52it/s]\n 90%|█████████ | 90/100 [00:27<00:02,  3.52it/s]\n 91%|█████████ | 91/100 [00:28<00:02,  3.53it/s]\n 92%|█████████▏| 92/100 [00:28<00:02,  3.52it/s]\n 93%|█████████▎| 93/100 [00:28<00:01,  3.53it/s]\n 94%|█████████▍| 94/100 [00:29<00:01,  3.52it/s]\n 95%|█████████▌| 95/100 [00:29<00:01,  3.52it/s]\n 96%|█████████▌| 96/100 [00:29<00:01,  3.52it/s]\n 97%|█████████▋| 97/100 [00:29<00:00,  3.52it/s]\n 98%|█████████▊| 98/100 [00:30<00:00,  3.52it/s]\n 99%|█████████▉| 99/100 [00:30<00:00,  3.52it/s]\n100%|██████████| 100/100 [00:30<00:00,  3.52it/s]\n100%|██████████| 100/100 [00:30<00:00,  3.25it/s]\nSaving final sample/s",
  "metrics": {
    "predict_time": 38.342397,
    "total_time": 38.509987
  },
  "output": [
    [
      "https://replicate.delivery/mgxm/271db70b-9e90-4825-9596-b759af8e6d28/current_0.png",
      "https://replicate.delivery/mgxm/27c035e6-9ad6-43b5-8b83-b87a9e132c08/current_1.png",
      "https://replicate.delivery/mgxm/976054e7-e18d-41f6-a73a-16a7ef356e10/current_2.png",
      "https://replicate.delivery/mgxm/7a1f4d4f-8fc9-4624-baeb-f4ddcf644958/current_3.png",
      "https://replicate.delivery/mgxm/153f966e-43dc-4bf6-b8fc-69b3cc27bf33/current_4.png",
      "https://replicate.delivery/mgxm/ec51a2db-283b-4668-9010-b3ea5a2a34d2/current_5.png"
    ]
  ],
  "started_at": "2022-07-21T19:34:12.858163Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/5mychegnafh73mrc2zmbdvxfqi",
    "cancel": "https://api.replicate.com/v1/predictions/5mychegnafh73mrc2zmbdvxfqi/cancel"
  },
  "version": "a51ce279c0131991c5a143a9c6a3ec6de146e765d9311cff7435b1db1190faaa"
}

Generated in

38.4 seconds

Tweak it ShareReport

Using seed 2312414383
Running simulation for paper plane logo with shadow of plane flying around the world, logo, vector
Encoding text embeddings with paper plane logo with shadow of plane flying around the world, logo, vector dimensions
Using aesthetic embedding 9 with weight 0.1
Running diffusion...

  0%|          | 0/100 [00:00<?, ?it/s]
  1%|          | 1/100 [00:01<02:01,  1.23s/it]
  2%|▏         | 2/100 [00:02<01:53,  1.16s/it]
  3%|▎         | 3/100 [00:03<01:50,  1.14s/it]
  4%|▍         | 4/100 [00:03<01:16,  1.25it/s]
  5%|▌         | 5/100 [00:04<00:58,  1.63it/s]
  6%|▌         | 6/100 [00:04<00:46,  2.01it/s]
  7%|▋         | 7/100 [00:04<00:39,  2.34it/s]
  8%|▊         | 8/100 [00:04<00:34,  2.63it/s]
  9%|▉         | 9/100 [00:05<00:31,  2.87it/s]
 10%|█         | 10/100 [00:05<00:29,  3.06it/s]
 11%|█         | 11/100 [00:05<00:27,  3.21it/s]
 12%|█▏        | 12/100 [00:05<00:26,  3.31it/s]
 13%|█▎        | 13/100 [00:06<00:25,  3.39it/s]
 14%|█▍        | 14/100 [00:06<00:25,  3.44it/s]
 15%|█▌        | 15/100 [00:06<00:24,  3.48it/s]
 16%|█▌        | 16/100 [00:07<00:23,  3.52it/s]
 17%|█▋        | 17/100 [00:07<00:23,  3.53it/s]
 18%|█▊        | 18/100 [00:07<00:23,  3.54it/s]
 19%|█▉        | 19/100 [00:07<00:22,  3.55it/s]
 20%|██        | 20/100 [00:08<00:22,  3.57it/s]
 21%|██        | 21/100 [00:08<00:22,  3.57it/s]
 22%|██▏       | 22/100 [00:08<00:21,  3.57it/s]
 23%|██▎       | 23/100 [00:09<00:21,  3.57it/s]
 24%|██▍       | 24/100 [00:09<00:21,  3.57it/s]
 25%|██▌       | 25/100 [00:09<00:21,  3.57it/s]
 26%|██▌       | 26/100 [00:09<00:20,  3.56it/s]
 27%|██▋       | 27/100 [00:10<00:20,  3.57it/s]
 28%|██▊       | 28/100 [00:10<00:20,  3.57it/s]
 29%|██▉       | 29/100 [00:10<00:19,  3.56it/s]
 30%|███       | 30/100 [00:11<00:19,  3.57it/s]
 31%|███       | 31/100 [00:11<00:19,  3.56it/s]
 32%|███▏      | 32/100 [00:11<00:19,  3.57it/s]
 33%|███▎      | 33/100 [00:11<00:18,  3.56it/s]
 34%|███▍      | 34/100 [00:12<00:18,  3.56it/s]
 35%|███▌      | 35/100 [00:12<00:18,  3.56it/s]
 36%|███▌      | 36/100 [00:12<00:18,  3.55it/s]
 37%|███▋      | 37/100 [00:12<00:17,  3.55it/s]
 38%|███▊      | 38/100 [00:13<00:17,  3.55it/s]
 39%|███▉      | 39/100 [00:13<00:17,  3.56it/s]
 40%|████      | 40/100 [00:13<00:16,  3.55it/s]
 41%|████      | 41/100 [00:14<00:16,  3.55it/s]
 42%|████▏     | 42/100 [00:14<00:16,  3.56it/s]
 43%|████▎     | 43/100 [00:14<00:15,  3.57it/s]
 44%|████▍     | 44/100 [00:14<00:15,  3.56it/s]
 45%|████▌     | 45/100 [00:15<00:15,  3.56it/s]
 46%|████▌     | 46/100 [00:15<00:15,  3.55it/s]
 47%|████▋     | 47/100 [00:15<00:14,  3.56it/s]
 48%|████▊     | 48/100 [00:16<00:14,  3.55it/s]
 49%|████▉     | 49/100 [00:16<00:14,  3.54it/s]
 50%|█████     | 50/100 [00:16<00:14,  3.55it/s]
 51%|█████     | 51/100 [00:16<00:13,  3.56it/s]
 52%|█████▏    | 52/100 [00:17<00:13,  3.56it/s]
 53%|█████▎    | 53/100 [00:17<00:13,  3.56it/s]
 54%|█████▍    | 54/100 [00:17<00:12,  3.55it/s]
 55%|█████▌    | 55/100 [00:18<00:12,  3.55it/s]
 56%|█████▌    | 56/100 [00:18<00:12,  3.54it/s]
 57%|█████▋    | 57/100 [00:18<00:12,  3.54it/s]
 58%|█████▊    | 58/100 [00:18<00:11,  3.55it/s]
 59%|█████▉    | 59/100 [00:19<00:11,  3.54it/s]
 60%|██████    | 60/100 [00:19<00:11,  3.52it/s]
 61%|██████    | 61/100 [00:19<00:11,  3.53it/s]
 62%|██████▏   | 62/100 [00:20<00:10,  3.53it/s]
 63%|██████▎   | 63/100 [00:20<00:10,  3.53it/s]
 64%|██████▍   | 64/100 [00:20<00:10,  3.53it/s]
 65%|██████▌   | 65/100 [00:20<00:09,  3.53it/s]
 66%|██████▌   | 66/100 [00:21<00:09,  3.53it/s]
 67%|██████▋   | 67/100 [00:21<00:09,  3.52it/s]
 68%|██████▊   | 68/100 [00:21<00:09,  3.52it/s]
 69%|██████▉   | 69/100 [00:22<00:08,  3.53it/s]
 70%|███████   | 70/100 [00:22<00:08,  3.53it/s]
 71%|███████   | 71/100 [00:22<00:08,  3.53it/s]
 72%|███████▏  | 72/100 [00:22<00:07,  3.53it/s]
 73%|███████▎  | 73/100 [00:23<00:07,  3.53it/s]
 74%|███████▍  | 74/100 [00:23<00:07,  3.53it/s]
 75%|███████▌  | 75/100 [00:23<00:07,  3.53it/s]
 76%|███████▌  | 76/100 [00:23<00:06,  3.52it/s]
 77%|███████▋  | 77/100 [00:24<00:06,  3.52it/s]
 78%|███████▊  | 78/100 [00:24<00:06,  3.52it/s]
 79%|███████▉  | 79/100 [00:24<00:05,  3.53it/s]
 80%|████████  | 80/100 [00:25<00:05,  3.52it/s]
 81%|████████  | 81/100 [00:25<00:05,  3.52it/s]
 82%|████████▏ | 82/100 [00:25<00:05,  3.53it/s]
 83%|████████▎ | 83/100 [00:25<00:04,  3.52it/s]
 84%|████████▍ | 84/100 [00:26<00:04,  3.52it/s]
 85%|████████▌ | 85/100 [00:26<00:04,  3.52it/s]
 86%|████████▌ | 86/100 [00:26<00:03,  3.53it/s]
 87%|████████▋ | 87/100 [00:27<00:03,  3.52it/s]
 88%|████████▊ | 88/100 [00:27<00:03,  3.52it/s]
 89%|████████▉ | 89/100 [00:27<00:03,  3.52it/s]
 90%|█████████ | 90/100 [00:27<00:02,  3.52it/s]
 91%|█████████ | 91/100 [00:28<00:02,  3.53it/s]
 92%|█████████▏| 92/100 [00:28<00:02,  3.52it/s]
 93%|█████████▎| 93/100 [00:28<00:01,  3.53it/s]
 94%|█████████▍| 94/100 [00:29<00:01,  3.52it/s]
 95%|█████████▌| 95/100 [00:29<00:01,  3.52it/s]
 96%|█████████▌| 96/100 [00:29<00:01,  3.52it/s]
 97%|█████████▋| 97/100 [00:29<00:00,  3.52it/s]
 98%|█████████▊| 98/100 [00:30<00:00,  3.52it/s]
 99%|█████████▉| 99/100 [00:30<00:00,  3.52it/s]
100%|██████████| 100/100 [00:30<00:00,  3.52it/s]
100%|██████████| 100/100 [00:30<00:00,  3.25it/s]
Saving final sample/s

Prediction

laion-ai/erlich:92fa143ccefeed01534d5d6648bd47796ef06847a6bc55c0e5c5b6975f2dcdfb

Model

laion-ai/erlich:92fa143c

kjo2hwofv5ak3ffw2673cdnlny

Status

Succeeded

Source

Web

Hardware

–

Total duration

6m 23s

Created

almost 3 years ago

Input

seed: "-1"
steps: "100"
width: "256"
height: "256"
prompt: paper plane logo with shadow of plane flying around the world, logo, digital art
batch_size: "6"
guidance_scale: "5"
aesthetic_rating: 9
aesthetic_weight: 0.1

{
  "seed": "-1",
  "steps": "100",
  "width": "256",
  "height": "256",
  "prompt": "paper plane logo with shadow of plane flying around the world, logo, digital art",
  "batch_size": "6",
  "guidance_scale": "5",
  "aesthetic_rating": 9,
  "aesthetic_weight": 0.1
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "laion-ai/erlich:92fa143ccefeed01534d5d6648bd47796ef06847a6bc55c0e5c5b6975f2dcdfb",
  {
    input: {
      seed: "-1",
      steps: "100",
      width: "256",
      height: "256",
      prompt: "paper plane logo with shadow of plane flying around the world, logo, digital art",
      batch_size: "6",
      guidance_scale: "5",
      aesthetic_rating: 9,
      aesthetic_weight: 0.1
    }
  }
);

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

Import the client:

import replicate

Run laion-ai/erlich using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "laion-ai/erlich:92fa143ccefeed01534d5d6648bd47796ef06847a6bc55c0e5c5b6975f2dcdfb",
    input={
        "seed": "-1",
        "steps": "100",
        "width": "256",
        "height": "256",
        "prompt": "paper plane logo with shadow of plane flying around the world, logo, digital art",
        "batch_size": "6",
        "guidance_scale": "5",
        "aesthetic_rating": 9,
        "aesthetic_weight": 0.1
    }
)

# The laion-ai/erlich 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/erlich/api#output-schema
    print(item)

To learn more, take a look at the guide on getting started with Python.

Run laion-ai/erlich 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": "laion-ai/erlich:92fa143ccefeed01534d5d6648bd47796ef06847a6bc55c0e5c5b6975f2dcdfb",
    "input": {
      "seed": "-1",
      "steps": "100",
      "width": "256",
      "height": "256",
      "prompt": "paper plane logo with shadow of plane flying around the world, logo, digital art",
      "batch_size": "6",
      "guidance_scale": "5",
      "aesthetic_rating": 9,
      "aesthetic_weight": 0.1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-08-05T14:40:21.390360Z",
  "created_at": "2022-08-05T14:33:58.632235Z",
  "data_removed": false,
  "error": null,
  "id": "kjo2hwofv5ak3ffw2673cdnlny",
  "input": {
    "seed": "-1",
    "steps": "100",
    "width": "256",
    "height": "256",
    "prompt": "paper plane logo with shadow of plane flying around the world, logo, digital art",
    "batch_size": "6",
    "guidance_scale": "5",
    "aesthetic_rating": 9,
    "aesthetic_weight": 0.1
  },
  "logs": "Using seed 4158679567\nUsing preloaded models\nEncoding text embeddings with paper plane logo with shadow of plane flying around the world, logo, digital art dimensions\nUsing aesthetic embedding 9 with weight 0.1\nRunning diffusion...\n\n  0%|          | 0/100 [00:00<?, ?it/s]\n  1%|          | 1/100 [00:01<02:28,  1.50s/it]\n  2%|▏         | 2/100 [00:02<02:08,  1.31s/it]\n  3%|▎         | 3/100 [00:03<02:01,  1.25s/it]\n  4%|▍         | 4/100 [00:04<01:23,  1.14it/s]\n  5%|▌         | 5/100 [00:04<01:03,  1.50it/s]\n  6%|▌         | 6/100 [00:04<00:50,  1.86it/s]\n  7%|▋         | 7/100 [00:05<00:42,  2.18it/s]\n  8%|▊         | 8/100 [00:05<00:37,  2.46it/s]\n  9%|▉         | 9/100 [00:05<00:33,  2.69it/s]\n 10%|█         | 10/100 [00:05<00:31,  2.87it/s]\n 11%|█         | 11/100 [00:06<00:29,  3.01it/s]\n 12%|█▏        | 12/100 [00:06<00:28,  3.11it/s]\n 13%|█▎        | 13/100 [00:06<00:27,  3.19it/s]\n 14%|█▍        | 14/100 [00:07<00:26,  3.24it/s]\n 15%|█▌        | 15/100 [00:07<00:25,  3.28it/s]\n 16%|█▌        | 16/100 [00:07<00:25,  3.31it/s]\n 17%|█▋        | 17/100 [00:08<00:24,  3.32it/s]\n 18%|█▊        | 18/100 [00:08<00:24,  3.34it/s]\n 19%|█▉        | 19/100 [00:08<00:24,  3.35it/s]\n 20%|██        | 20/100 [00:08<00:23,  3.35it/s]\n 21%|██        | 21/100 [00:09<00:23,  3.36it/s]\n 22%|██▏       | 22/100 [00:09<00:23,  3.37it/s]\n 23%|██▎       | 23/100 [00:09<00:22,  3.39it/s]\n 24%|██▍       | 24/100 [00:10<00:22,  3.38it/s]\n 25%|██▌       | 25/100 [00:10<00:22,  3.38it/s]\n 26%|██▌       | 26/100 [00:10<00:21,  3.37it/s]\n 27%|██▋       | 27/100 [00:10<00:21,  3.36it/s]\n 28%|██▊       | 28/100 [00:11<00:21,  3.36it/s]\n 29%|██▉       | 29/100 [00:11<00:21,  3.36it/s]\n 30%|███       | 30/100 [00:11<00:20,  3.37it/s]\n 31%|███       | 31/100 [00:12<00:20,  3.37it/s]\n 32%|███▏      | 32/100 [00:12<00:20,  3.37it/s]\n 33%|███▎      | 33/100 [00:12<00:19,  3.38it/s]\n 34%|███▍      | 34/100 [00:13<00:19,  3.37it/s]\n 35%|███▌      | 35/100 [00:13<00:19,  3.38it/s]\n 36%|███▌      | 36/100 [00:13<00:18,  3.38it/s]\n 37%|███▋      | 37/100 [00:13<00:18,  3.37it/s]\n 38%|███▊      | 38/100 [00:14<00:18,  3.37it/s]\n 39%|███▉      | 39/100 [00:14<00:18,  3.37it/s]\n 40%|████      | 40/100 [00:14<00:17,  3.37it/s]\n 41%|████      | 41/100 [00:15<00:17,  3.37it/s]\n 42%|████▏     | 42/100 [00:15<00:17,  3.37it/s]\n 43%|████▎     | 43/100 [00:15<00:16,  3.36it/s]\n 44%|████▍     | 44/100 [00:16<00:16,  3.36it/s]\n 45%|████▌     | 45/100 [00:16<00:16,  3.36it/s]\n 46%|████▌     | 46/100 [00:16<00:16,  3.36it/s]\n 47%|████▋     | 47/100 [00:16<00:15,  3.36it/s]\n 48%|████▊     | 48/100 [00:17<00:15,  3.35it/s]\n 49%|████▉     | 49/100 [00:17<00:15,  3.36it/s]\n 50%|█████     | 50/100 [00:17<00:14,  3.35it/s]\n 51%|█████     | 51/100 [00:18<00:14,  3.35it/s]\n 52%|█████▏    | 52/100 [00:18<00:14,  3.34it/s]\n 53%|█████▎    | 53/100 [00:18<00:14,  3.35it/s]\n 54%|█████▍    | 54/100 [00:18<00:13,  3.35it/s]\n 55%|█████▌    | 55/100 [00:19<00:13,  3.34it/s]\n 56%|█████▌    | 56/100 [00:19<00:13,  3.35it/s]\n 57%|█████▋    | 57/100 [00:19<00:12,  3.35it/s]\n 58%|█████▊    | 58/100 [00:20<00:12,  3.35it/s]\n 59%|█████▉    | 59/100 [00:20<00:12,  3.35it/s]\n 60%|██████    | 60/100 [00:20<00:11,  3.34it/s]\n 61%|██████    | 61/100 [00:21<00:11,  3.34it/s]\n 62%|██████▏   | 62/100 [00:21<00:11,  3.34it/s]\n 63%|██████▎   | 63/100 [00:21<00:11,  3.33it/s]\n 64%|██████▍   | 64/100 [00:21<00:10,  3.34it/s]\n 65%|██████▌   | 65/100 [00:22<00:10,  3.33it/s]\n 66%|██████▌   | 66/100 [00:22<00:10,  3.33it/s]\n 67%|██████▋   | 67/100 [00:22<00:09,  3.34it/s]\n 68%|██████▊   | 68/100 [00:23<00:09,  3.34it/s]\n 69%|██████▉   | 69/100 [00:23<00:09,  3.34it/s]\n 70%|███████   | 70/100 [00:23<00:09,  3.33it/s]\n 71%|███████   | 71/100 [00:24<00:08,  3.32it/s]\n 72%|███████▏  | 72/100 [00:24<00:08,  3.32it/s]\n 73%|███████▎  | 73/100 [00:24<00:08,  3.32it/s]\n 74%|███████▍  | 74/100 [00:24<00:07,  3.32it/s]\n 75%|███████▌  | 75/100 [00:25<00:07,  3.33it/s]\n 76%|███████▌  | 76/100 [00:25<00:07,  3.33it/s]\n 77%|███████▋  | 77/100 [00:25<00:06,  3.34it/s]\n 78%|███████▊  | 78/100 [00:26<00:06,  3.33it/s]\n 79%|███████▉  | 79/100 [00:26<00:06,  3.34it/s]\n 80%|████████  | 80/100 [00:26<00:05,  3.33it/s]\n 81%|████████  | 81/100 [00:27<00:05,  3.33it/s]\n 82%|████████▏ | 82/100 [00:27<00:05,  3.33it/s]\n 83%|████████▎ | 83/100 [00:27<00:05,  3.33it/s]\n 84%|████████▍ | 84/100 [00:27<00:04,  3.33it/s]\n 85%|████████▌ | 85/100 [00:28<00:04,  3.33it/s]\n 86%|████████▌ | 86/100 [00:28<00:04,  3.32it/s]\n 87%|████████▋ | 87/100 [00:28<00:03,  3.32it/s]\n 88%|████████▊ | 88/100 [00:29<00:03,  3.32it/s]\n 89%|████████▉ | 89/100 [00:29<00:03,  3.32it/s]\n 90%|█████████ | 90/100 [00:29<00:03,  3.32it/s]\n 91%|█████████ | 91/100 [00:30<00:02,  3.32it/s]\n 92%|█████████▏| 92/100 [00:30<00:02,  3.32it/s]\n 93%|█████████▎| 93/100 [00:30<00:02,  3.32it/s]\n 94%|█████████▍| 94/100 [00:31<00:01,  3.32it/s]\n 95%|█████████▌| 95/100 [00:31<00:01,  3.32it/s]\n 96%|█████████▌| 96/100 [00:31<00:01,  3.33it/s]\n 97%|█████████▋| 97/100 [00:31<00:00,  3.32it/s]\n 98%|█████████▊| 98/100 [00:32<00:00,  3.33it/s]\n 99%|█████████▉| 99/100 [00:32<00:00,  3.32it/s]\n100%|██████████| 100/100 [00:32<00:00,  3.32it/s]\n100%|██████████| 100/100 [00:32<00:00,  3.05it/s]\nSaving final sample/s",
  "metrics": {
    "predict_time": 37.033327,
    "total_time": 382.758125
  },
  "output": [
    [
      "https://replicate.delivery/mgxm/f71aaee1-8937-403c-b497-9d05921cba95/ts_99-batch_0.png",
      "https://replicate.delivery/mgxm/0dae8f90-d30f-4bc6-a21d-98d2e6918ba5/ts_99-batch_1.png",
      "https://replicate.delivery/mgxm/3d7569c9-e1d1-400e-a7ad-1ab97c98c97c/ts_99-batch_2.png",
      "https://replicate.delivery/mgxm/264565dc-6828-4fa1-8521-614ff5c236fa/ts_99-batch_3.png",
      "https://replicate.delivery/mgxm/8022084b-a249-4979-ab0f-c774f687cf77/ts_99-batch_4.png",
      "https://replicate.delivery/mgxm/bcfb9294-1da5-4762-b761-dd14ad601f03/ts_99-batch_5.png"
    ]
  ],
  "started_at": "2022-08-05T14:39:44.357033Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/kjo2hwofv5ak3ffw2673cdnlny",
    "cancel": "https://api.replicate.com/v1/predictions/kjo2hwofv5ak3ffw2673cdnlny/cancel"
  },
  "version": "92fa143ccefeed01534d5d6648bd47796ef06847a6bc55c0e5c5b6975f2dcdfb"
}

Generated in

37.0 seconds

Tweak it ShareReport

Using seed 4158679567
Using preloaded models
Encoding text embeddings with paper plane logo with shadow of plane flying around the world, logo, digital art dimensions
Using aesthetic embedding 9 with weight 0.1
Running diffusion...

  0%|          | 0/100 [00:00<?, ?it/s]
  1%|          | 1/100 [00:01<02:28,  1.50s/it]
  2%|▏         | 2/100 [00:02<02:08,  1.31s/it]
  3%|▎         | 3/100 [00:03<02:01,  1.25s/it]
  4%|▍         | 4/100 [00:04<01:23,  1.14it/s]
  5%|▌         | 5/100 [00:04<01:03,  1.50it/s]
  6%|▌         | 6/100 [00:04<00:50,  1.86it/s]
  7%|▋         | 7/100 [00:05<00:42,  2.18it/s]
  8%|▊         | 8/100 [00:05<00:37,  2.46it/s]
  9%|▉         | 9/100 [00:05<00:33,  2.69it/s]
 10%|█         | 10/100 [00:05<00:31,  2.87it/s]
 11%|█         | 11/100 [00:06<00:29,  3.01it/s]
 12%|█▏        | 12/100 [00:06<00:28,  3.11it/s]
 13%|█▎        | 13/100 [00:06<00:27,  3.19it/s]
 14%|█▍        | 14/100 [00:07<00:26,  3.24it/s]
 15%|█▌        | 15/100 [00:07<00:25,  3.28it/s]
 16%|█▌        | 16/100 [00:07<00:25,  3.31it/s]
 17%|█▋        | 17/100 [00:08<00:24,  3.32it/s]
 18%|█▊        | 18/100 [00:08<00:24,  3.34it/s]
 19%|█▉        | 19/100 [00:08<00:24,  3.35it/s]
 20%|██        | 20/100 [00:08<00:23,  3.35it/s]
 21%|██        | 21/100 [00:09<00:23,  3.36it/s]
 22%|██▏       | 22/100 [00:09<00:23,  3.37it/s]
 23%|██▎       | 23/100 [00:09<00:22,  3.39it/s]
 24%|██▍       | 24/100 [00:10<00:22,  3.38it/s]
 25%|██▌       | 25/100 [00:10<00:22,  3.38it/s]
 26%|██▌       | 26/100 [00:10<00:21,  3.37it/s]
 27%|██▋       | 27/100 [00:10<00:21,  3.36it/s]
 28%|██▊       | 28/100 [00:11<00:21,  3.36it/s]
 29%|██▉       | 29/100 [00:11<00:21,  3.36it/s]
 30%|███       | 30/100 [00:11<00:20,  3.37it/s]
 31%|███       | 31/100 [00:12<00:20,  3.37it/s]
 32%|███▏      | 32/100 [00:12<00:20,  3.37it/s]
 33%|███▎      | 33/100 [00:12<00:19,  3.38it/s]
 34%|███▍      | 34/100 [00:13<00:19,  3.37it/s]
 35%|███▌      | 35/100 [00:13<00:19,  3.38it/s]
 36%|███▌      | 36/100 [00:13<00:18,  3.38it/s]
 37%|███▋      | 37/100 [00:13<00:18,  3.37it/s]
 38%|███▊      | 38/100 [00:14<00:18,  3.37it/s]
 39%|███▉      | 39/100 [00:14<00:18,  3.37it/s]
 40%|████      | 40/100 [00:14<00:17,  3.37it/s]
 41%|████      | 41/100 [00:15<00:17,  3.37it/s]
 42%|████▏     | 42/100 [00:15<00:17,  3.37it/s]
 43%|████▎     | 43/100 [00:15<00:16,  3.36it/s]
 44%|████▍     | 44/100 [00:16<00:16,  3.36it/s]
 45%|████▌     | 45/100 [00:16<00:16,  3.36it/s]
 46%|████▌     | 46/100 [00:16<00:16,  3.36it/s]
 47%|████▋     | 47/100 [00:16<00:15,  3.36it/s]
 48%|████▊     | 48/100 [00:17<00:15,  3.35it/s]
 49%|████▉     | 49/100 [00:17<00:15,  3.36it/s]
 50%|█████     | 50/100 [00:17<00:14,  3.35it/s]
 51%|█████     | 51/100 [00:18<00:14,  3.35it/s]
 52%|█████▏    | 52/100 [00:18<00:14,  3.34it/s]
 53%|█████▎    | 53/100 [00:18<00:14,  3.35it/s]
 54%|█████▍    | 54/100 [00:18<00:13,  3.35it/s]
 55%|█████▌    | 55/100 [00:19<00:13,  3.34it/s]
 56%|█████▌    | 56/100 [00:19<00:13,  3.35it/s]
 57%|█████▋    | 57/100 [00:19<00:12,  3.35it/s]
 58%|█████▊    | 58/100 [00:20<00:12,  3.35it/s]
 59%|█████▉    | 59/100 [00:20<00:12,  3.35it/s]
 60%|██████    | 60/100 [00:20<00:11,  3.34it/s]
 61%|██████    | 61/100 [00:21<00:11,  3.34it/s]
 62%|██████▏   | 62/100 [00:21<00:11,  3.34it/s]
 63%|██████▎   | 63/100 [00:21<00:11,  3.33it/s]
 64%|██████▍   | 64/100 [00:21<00:10,  3.34it/s]
 65%|██████▌   | 65/100 [00:22<00:10,  3.33it/s]
 66%|██████▌   | 66/100 [00:22<00:10,  3.33it/s]
 67%|██████▋   | 67/100 [00:22<00:09,  3.34it/s]
 68%|██████▊   | 68/100 [00:23<00:09,  3.34it/s]
 69%|██████▉   | 69/100 [00:23<00:09,  3.34it/s]
 70%|███████   | 70/100 [00:23<00:09,  3.33it/s]
 71%|███████   | 71/100 [00:24<00:08,  3.32it/s]
 72%|███████▏  | 72/100 [00:24<00:08,  3.32it/s]
 73%|███████▎  | 73/100 [00:24<00:08,  3.32it/s]
 74%|███████▍  | 74/100 [00:24<00:07,  3.32it/s]
 75%|███████▌  | 75/100 [00:25<00:07,  3.33it/s]
 76%|███████▌  | 76/100 [00:25<00:07,  3.33it/s]
 77%|███████▋  | 77/100 [00:25<00:06,  3.34it/s]
 78%|███████▊  | 78/100 [00:26<00:06,  3.33it/s]
 79%|███████▉  | 79/100 [00:26<00:06,  3.34it/s]
 80%|████████  | 80/100 [00:26<00:05,  3.33it/s]
 81%|████████  | 81/100 [00:27<00:05,  3.33it/s]
 82%|████████▏ | 82/100 [00:27<00:05,  3.33it/s]
 83%|████████▎ | 83/100 [00:27<00:05,  3.33it/s]
 84%|████████▍ | 84/100 [00:27<00:04,  3.33it/s]
 85%|████████▌ | 85/100 [00:28<00:04,  3.33it/s]
 86%|████████▌ | 86/100 [00:28<00:04,  3.32it/s]
 87%|████████▋ | 87/100 [00:28<00:03,  3.32it/s]
 88%|████████▊ | 88/100 [00:29<00:03,  3.32it/s]
 89%|████████▉ | 89/100 [00:29<00:03,  3.32it/s]
 90%|█████████ | 90/100 [00:29<00:03,  3.32it/s]
 91%|█████████ | 91/100 [00:30<00:02,  3.32it/s]
 92%|█████████▏| 92/100 [00:30<00:02,  3.32it/s]
 93%|█████████▎| 93/100 [00:30<00:02,  3.32it/s]
 94%|█████████▍| 94/100 [00:31<00:01,  3.32it/s]
 95%|█████████▌| 95/100 [00:31<00:01,  3.32it/s]
 96%|█████████▌| 96/100 [00:31<00:01,  3.33it/s]
 97%|█████████▋| 97/100 [00:31<00:00,  3.32it/s]
 98%|█████████▊| 98/100 [00:32<00:00,  3.33it/s]
 99%|█████████▉| 99/100 [00:32<00:00,  3.32it/s]
100%|██████████| 100/100 [00:32<00:00,  3.32it/s]
100%|██████████| 100/100 [00:32<00:00,  3.05it/s]
Saving final sample/s

Want to make some of these yourself?

Run this model