meghabyte/arrival-logograms – Run with an API on Replicate

meghabyte / arrival-logograms

Generates logograms in the style of the alien language from the 2016 sci-fi film "Arrival".

Warm

Public
1.4K runs
L40S
SDXL fine-tune

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Input prompt

Default: "An astronaut riding a rainbow unicorn"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

seed

integer

Random seed. Leave blank to randomize the seed

Including negative_prompt and 14 more...

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

npx create-replicate --model=meghabyte/arrival-logograms

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

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

Run meghabyte/arrival-logograms using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "meghabyte/arrival-logograms:3d58fdf66cb45c08fa5c66f7d59bf103b6e318a4f8220dd55221844885b1d580",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "A logogram of creativity",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run meghabyte/arrival-logograms using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "meghabyte/arrival-logograms:3d58fdf66cb45c08fa5c66f7d59bf103b6e318a4f8220dd55221844885b1d580",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "A logogram of creativity",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)
print(output)

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run meghabyte/arrival-logograms 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": "3d58fdf66cb45c08fa5c66f7d59bf103b6e318a4f8220dd55221844885b1d580",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "A logogram of creativity",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-08-24T08:38:29.199386Z",
  "created_at": "2024-08-24T08:38:06.934000Z",
  "data_removed": false,
  "error": null,
  "id": "dp734s8xasrgp0chge4smb2mkm",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "A logogram of creativity",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 1452\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A <s0><s1> of creativity\ntxt2img mode\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:11,  4.26it/s]\n  4%|▍         | 2/50 [00:00<00:11,  4.25it/s]\n  6%|▌         | 3/50 [00:00<00:11,  4.24it/s]\n  8%|▊         | 4/50 [00:00<00:10,  4.24it/s]\n 10%|█         | 5/50 [00:01<00:10,  4.24it/s]\n 12%|█▏        | 6/50 [00:01<00:10,  4.24it/s]\n 14%|█▍        | 7/50 [00:01<00:10,  4.25it/s]\n 16%|█▌        | 8/50 [00:01<00:09,  4.25it/s]\n 18%|█▊        | 9/50 [00:02<00:09,  4.25it/s]\n 20%|██        | 10/50 [00:02<00:09,  4.26it/s]\n 22%|██▏       | 11/50 [00:02<00:09,  4.26it/s]\n 24%|██▍       | 12/50 [00:02<00:08,  4.26it/s]\n 26%|██▌       | 13/50 [00:03<00:08,  4.26it/s]\n 28%|██▊       | 14/50 [00:03<00:08,  4.26it/s]\n 30%|███       | 15/50 [00:03<00:08,  4.26it/s]\n 32%|███▏      | 16/50 [00:03<00:07,  4.26it/s]\n 34%|███▍      | 17/50 [00:03<00:07,  4.26it/s]\n 36%|███▌      | 18/50 [00:04<00:07,  4.25it/s]\n 38%|███▊      | 19/50 [00:04<00:07,  4.25it/s]\n 40%|████      | 20/50 [00:04<00:07,  4.26it/s]\n 42%|████▏     | 21/50 [00:04<00:06,  4.26it/s]\n 44%|████▍     | 22/50 [00:05<00:06,  4.25it/s]\n 46%|████▌     | 23/50 [00:05<00:06,  4.25it/s]\n 48%|████▊     | 24/50 [00:05<00:06,  4.26it/s]\n 50%|█████     | 25/50 [00:05<00:05,  4.26it/s]\n 52%|█████▏    | 26/50 [00:06<00:05,  4.25it/s]\n 54%|█████▍    | 27/50 [00:06<00:05,  4.25it/s]\n 56%|█████▌    | 28/50 [00:06<00:05,  4.25it/s]\n 58%|█████▊    | 29/50 [00:06<00:04,  4.25it/s]\n 60%|██████    | 30/50 [00:07<00:04,  4.25it/s]\n 62%|██████▏   | 31/50 [00:07<00:04,  4.25it/s]\n 64%|██████▍   | 32/50 [00:07<00:04,  4.25it/s]\n 66%|██████▌   | 33/50 [00:07<00:03,  4.25it/s]\n 68%|██████▊   | 34/50 [00:07<00:03,  4.25it/s]\n 70%|███████   | 35/50 [00:08<00:03,  4.25it/s]\n 72%|███████▏  | 36/50 [00:08<00:03,  4.25it/s]\n 74%|███████▍  | 37/50 [00:08<00:03,  4.25it/s]\n 76%|███████▌  | 38/50 [00:08<00:02,  4.25it/s]\n 78%|███████▊  | 39/50 [00:09<00:02,  4.25it/s]\n 80%|████████  | 40/50 [00:09<00:02,  4.25it/s]\n 82%|████████▏ | 41/50 [00:09<00:02,  4.25it/s]\n 84%|████████▍ | 42/50 [00:09<00:01,  4.25it/s]\n 86%|████████▌ | 43/50 [00:10<00:01,  4.25it/s]\n 88%|████████▊ | 44/50 [00:10<00:01,  4.25it/s]\n 90%|█████████ | 45/50 [00:10<00:01,  4.25it/s]\n 92%|█████████▏| 46/50 [00:10<00:00,  4.25it/s]\n 94%|█████████▍| 47/50 [00:11<00:00,  4.25it/s]\n 96%|█████████▌| 48/50 [00:11<00:00,  4.25it/s]\n 98%|█████████▊| 49/50 [00:11<00:00,  4.24it/s]\n100%|██████████| 50/50 [00:11<00:00,  4.24it/s]\n100%|██████████| 50/50 [00:11<00:00,  4.25it/s]",
  "metrics": {
    "predict_time": 16.003729808,
    "total_time": 22.265386
  },
  "output": [
    "https://replicate.delivery/pbxt/JXpYiWG1kyo8PJfQ427rLkh8dwLkrAl4aDFwqnJ6j14Bc6qJA/out-0.png"
  ],
  "started_at": "2024-08-24T08:38:13.195656Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/dp734s8xasrgp0chge4smb2mkm",
    "cancel": "https://api.replicate.com/v1/predictions/dp734s8xasrgp0chge4smb2mkm/cancel"
  },
  "version": "3d58fdf66cb45c08fa5c66f7d59bf103b6e318a4f8220dd55221844885b1d580"
}

Generated in

16.0 seconds

Tweak it ShareReport

Using seed: 1452
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: A <s0><s1> of creativity
txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:11,  4.26it/s]
  4%|▍         | 2/50 [00:00<00:11,  4.25it/s]
  6%|▌         | 3/50 [00:00<00:11,  4.24it/s]
  8%|▊         | 4/50 [00:00<00:10,  4.24it/s]
 10%|█         | 5/50 [00:01<00:10,  4.24it/s]
 12%|█▏        | 6/50 [00:01<00:10,  4.24it/s]
 14%|█▍        | 7/50 [00:01<00:10,  4.25it/s]
 16%|█▌        | 8/50 [00:01<00:09,  4.25it/s]
 18%|█▊        | 9/50 [00:02<00:09,  4.25it/s]
 20%|██        | 10/50 [00:02<00:09,  4.26it/s]
 22%|██▏       | 11/50 [00:02<00:09,  4.26it/s]
 24%|██▍       | 12/50 [00:02<00:08,  4.26it/s]
 26%|██▌       | 13/50 [00:03<00:08,  4.26it/s]
 28%|██▊       | 14/50 [00:03<00:08,  4.26it/s]
 30%|███       | 15/50 [00:03<00:08,  4.26it/s]
 32%|███▏      | 16/50 [00:03<00:07,  4.26it/s]
 34%|███▍      | 17/50 [00:03<00:07,  4.26it/s]
 36%|███▌      | 18/50 [00:04<00:07,  4.25it/s]
 38%|███▊      | 19/50 [00:04<00:07,  4.25it/s]
 40%|████      | 20/50 [00:04<00:07,  4.26it/s]
 42%|████▏     | 21/50 [00:04<00:06,  4.26it/s]
 44%|████▍     | 22/50 [00:05<00:06,  4.25it/s]
 46%|████▌     | 23/50 [00:05<00:06,  4.25it/s]
 48%|████▊     | 24/50 [00:05<00:06,  4.26it/s]
 50%|█████     | 25/50 [00:05<00:05,  4.26it/s]
 52%|█████▏    | 26/50 [00:06<00:05,  4.25it/s]
 54%|█████▍    | 27/50 [00:06<00:05,  4.25it/s]
 56%|█████▌    | 28/50 [00:06<00:05,  4.25it/s]
 58%|█████▊    | 29/50 [00:06<00:04,  4.25it/s]
 60%|██████    | 30/50 [00:07<00:04,  4.25it/s]
 62%|██████▏   | 31/50 [00:07<00:04,  4.25it/s]
 64%|██████▍   | 32/50 [00:07<00:04,  4.25it/s]
 66%|██████▌   | 33/50 [00:07<00:03,  4.25it/s]
 68%|██████▊   | 34/50 [00:07<00:03,  4.25it/s]
 70%|███████   | 35/50 [00:08<00:03,  4.25it/s]
 72%|███████▏  | 36/50 [00:08<00:03,  4.25it/s]
 74%|███████▍  | 37/50 [00:08<00:03,  4.25it/s]
 76%|███████▌  | 38/50 [00:08<00:02,  4.25it/s]
 78%|███████▊  | 39/50 [00:09<00:02,  4.25it/s]
 80%|████████  | 40/50 [00:09<00:02,  4.25it/s]
 82%|████████▏ | 41/50 [00:09<00:02,  4.25it/s]
 84%|████████▍ | 42/50 [00:09<00:01,  4.25it/s]
 86%|████████▌ | 43/50 [00:10<00:01,  4.25it/s]
 88%|████████▊ | 44/50 [00:10<00:01,  4.25it/s]
 90%|█████████ | 45/50 [00:10<00:01,  4.25it/s]
 92%|█████████▏| 46/50 [00:10<00:00,  4.25it/s]
 94%|█████████▍| 47/50 [00:11<00:00,  4.25it/s]
 96%|█████████▌| 48/50 [00:11<00:00,  4.25it/s]
 98%|█████████▊| 49/50 [00:11<00:00,  4.24it/s]
100%|██████████| 50/50 [00:11<00:00,  4.24it/s]
100%|██████████| 50/50 [00:11<00:00,  4.25it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.0065 to run on Replicate, or 153 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 7 seconds.

Readme

This model generated logograms for the Alien language used in the 2016 sci-fi film “Arrival”, directed by Denis Villeneuve and based on Ted Chiang’s short story “Story of Your Life”. The model is trained on a small dataset of logograms from the movie. This model is not based on any “real” language created for the movie, and is mostly just for fun :)