jyoung105/meissonic – Run with an API on Replicate

jyoung105 / meissonic

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Cold

Public
23 runs
L40S
GitHub
Weights
Paper
License

Run with an API

Playground API Examples README Versions

Input

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

npx create-replicate --model=jyoung105/meissonic

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 jyoung105/meissonic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jyoung105/meissonic:1eadf8a06fe10e2ceb8927d5fb5ec0aa4a1e73bc083fa88be80550e0c514200d",
  {
    input: {
      steps: 64,
      width: 1024,
      height: 1024,
      prompt: "A man with hoodie on, illustration",
      num_images: 1,
      guidance_scale: 9
    }
  }
);

// 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 jyoung105/meissonic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jyoung105/meissonic:1eadf8a06fe10e2ceb8927d5fb5ec0aa4a1e73bc083fa88be80550e0c514200d",
    input={
        "steps": 64,
        "width": 1024,
        "height": 1024,
        "prompt": "A man with hoodie on, illustration",
        "num_images": 1,
        "guidance_scale": 9
    }
)
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 jyoung105/meissonic 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": "jyoung105/meissonic:1eadf8a06fe10e2ceb8927d5fb5ec0aa4a1e73bc083fa88be80550e0c514200d",
    "input": {
      "steps": 64,
      "width": 1024,
      "height": 1024,
      "prompt": "A man with hoodie on, illustration",
      "num_images": 1,
      "guidance_scale": 9
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-11-04T13:22:01.323066Z",
  "created_at": "2024-11-04T13:21:54.977000Z",
  "data_removed": false,
  "error": null,
  "id": "wfcw8vyh45rgp0cjyxbbrrbbe4",
  "input": {
    "steps": 64,
    "width": 1024,
    "height": 1024,
    "prompt": "A man with hoodie on, illustration",
    "num_images": 1,
    "guidance_scale": 9
  },
  "logs": "DEVICE: cuda\nDTYPE: torch.bfloat16\nUsing seed: 24544\nFinish setup in 0.000164031982421875 secs.\n[Debug] Prompt: A man with hoodie on, illustration, best quality, high detail, sharp focus\n  0%|          | 0/64 [00:00<?, ?it/s]\n  3%|▎         | 2/64 [00:00<00:05, 11.65it/s]\n  6%|▋         | 4/64 [00:00<00:05, 11.86it/s]\n  9%|▉         | 6/64 [00:00<00:04, 11.94it/s]\n 12%|█▎        | 8/64 [00:00<00:04, 11.95it/s]\n 16%|█▌        | 10/64 [00:00<00:04, 11.98it/s]\n 19%|█▉        | 12/64 [00:01<00:04, 12.00it/s]\n 22%|██▏       | 14/64 [00:01<00:04, 12.00it/s]\n 25%|██▌       | 16/64 [00:01<00:03, 12.00it/s]\n 28%|██▊       | 18/64 [00:01<00:03, 11.70it/s]\n 31%|███▏      | 20/64 [00:01<00:03, 11.81it/s]\n 34%|███▍      | 22/64 [00:01<00:03, 11.87it/s]\n 38%|███▊      | 24/64 [00:02<00:03, 11.92it/s]\n 41%|████      | 26/64 [00:02<00:03, 11.68it/s]\n 44%|████▍     | 28/64 [00:02<00:03, 11.79it/s]\n 47%|████▋     | 30/64 [00:02<00:02, 11.86it/s]\n 50%|█████     | 32/64 [00:02<00:02, 11.89it/s]\n 53%|█████▎    | 34/64 [00:02<00:02, 11.94it/s]\n 56%|█████▋    | 36/64 [00:03<00:02, 11.97it/s]\n 59%|█████▉    | 38/64 [00:03<00:02, 11.96it/s]\n 62%|██████▎   | 40/64 [00:03<00:02, 11.98it/s]\n 66%|██████▌   | 42/64 [00:03<00:01, 11.99it/s]\n 69%|██████▉   | 44/64 [00:03<00:01, 12.00it/s]\n 72%|███████▏  | 46/64 [00:03<00:01, 12.01it/s]\n 75%|███████▌  | 48/64 [00:04<00:01, 12.01it/s]\n 78%|███████▊  | 50/64 [00:04<00:01, 11.74it/s]\n 81%|████████▏ | 52/64 [00:04<00:01, 11.82it/s]\n 84%|████████▍ | 54/64 [00:04<00:00, 11.88it/s]\n 88%|████████▊ | 56/64 [00:04<00:00, 11.91it/s]\n 91%|█████████ | 58/64 [00:04<00:00, 11.94it/s]\n 94%|█████████▍| 60/64 [00:05<00:00, 11.97it/s]\n 97%|█████████▋| 62/64 [00:05<00:00, 11.67it/s]\n100%|██████████| 64/64 [00:05<00:00, 11.79it/s]\n100%|██████████| 64/64 [00:05<00:00, 11.88it/s]\nFinish generation in 5.742046117782593 secs.",
  "metrics": {
    "predict_time": 6.337907732,
    "total_time": 6.346066
  },
  "output": [
    "https://replicate.delivery/pbxt/sHNBM02Dwt6CIV8JH4rIBx70fCLubMog70W8eaBUK0g4xntTA/out_0.png"
  ],
  "started_at": "2024-11-04T13:21:54.985158Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/wfcw8vyh45rgp0cjyxbbrrbbe4",
    "cancel": "https://api.replicate.com/v1/predictions/wfcw8vyh45rgp0cjyxbbrrbbe4/cancel"
  },
  "version": "1eadf8a06fe10e2ceb8927d5fb5ec0aa4a1e73bc083fa88be80550e0c514200d"
}

Generated in

6.3 seconds

Tweak it ShareReport

DEVICE: cuda
DTYPE: torch.bfloat16
Using seed: 24544
Finish setup in 0.000164031982421875 secs.
[Debug] Prompt: A man with hoodie on, illustration, best quality, high detail, sharp focus
  0%|          | 0/64 [00:00<?, ?it/s]
  3%|▎         | 2/64 [00:00<00:05, 11.65it/s]
  6%|▋         | 4/64 [00:00<00:05, 11.86it/s]
  9%|▉         | 6/64 [00:00<00:04, 11.94it/s]
 12%|█▎        | 8/64 [00:00<00:04, 11.95it/s]
 16%|█▌        | 10/64 [00:00<00:04, 11.98it/s]
 19%|█▉        | 12/64 [00:01<00:04, 12.00it/s]
 22%|██▏       | 14/64 [00:01<00:04, 12.00it/s]
 25%|██▌       | 16/64 [00:01<00:03, 12.00it/s]
 28%|██▊       | 18/64 [00:01<00:03, 11.70it/s]
 31%|███▏      | 20/64 [00:01<00:03, 11.81it/s]
 34%|███▍      | 22/64 [00:01<00:03, 11.87it/s]
 38%|███▊      | 24/64 [00:02<00:03, 11.92it/s]
 41%|████      | 26/64 [00:02<00:03, 11.68it/s]
 44%|████▍     | 28/64 [00:02<00:03, 11.79it/s]
 47%|████▋     | 30/64 [00:02<00:02, 11.86it/s]
 50%|█████     | 32/64 [00:02<00:02, 11.89it/s]
 53%|█████▎    | 34/64 [00:02<00:02, 11.94it/s]
 56%|█████▋    | 36/64 [00:03<00:02, 11.97it/s]
 59%|█████▉    | 38/64 [00:03<00:02, 11.96it/s]
 62%|██████▎   | 40/64 [00:03<00:02, 11.98it/s]
 66%|██████▌   | 42/64 [00:03<00:01, 11.99it/s]
 69%|██████▉   | 44/64 [00:03<00:01, 12.00it/s]
 72%|███████▏  | 46/64 [00:03<00:01, 12.01it/s]
 75%|███████▌  | 48/64 [00:04<00:01, 12.01it/s]
 78%|███████▊  | 50/64 [00:04<00:01, 11.74it/s]
 81%|████████▏ | 52/64 [00:04<00:01, 11.82it/s]
 84%|████████▍ | 54/64 [00:04<00:00, 11.88it/s]
 88%|████████▊ | 56/64 [00:04<00:00, 11.91it/s]
 91%|█████████ | 58/64 [00:04<00:00, 11.94it/s]
 94%|█████████▍| 60/64 [00:05<00:00, 11.97it/s]
 97%|█████████▋| 62/64 [00:05<00:00, 11.67it/s]
100%|██████████| 64/64 [00:05<00:00, 11.79it/s]
100%|██████████| 64/64 [00:05<00:00, 11.88it/s]
Finish generation in 5.742046117782593 secs.

Examples

View more examples

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.