alphayeho / train4

{
  "model": "dev",
  "prompt": "man TOK",
  "lora_scale": 1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 90,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

Run alphayeho/train4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "alphayeho/train4:a6123293588fe88d2a0ac0bd3dcc71eddd02fff90d7152841adec34ea25613c3",
  {
    input: {
      model: "dev",
      prompt: "man TOK",
      lora_scale: 1,
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 3.5,
      output_quality: 90,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// 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

Import the client:

import replicate

Run alphayeho/train4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "alphayeho/train4:a6123293588fe88d2a0ac0bd3dcc71eddd02fff90d7152841adec34ea25613c3",
    input={
        "model": "dev",
        "prompt": "man TOK",
        "lora_scale": 1,
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 3.5,
        "output_quality": 90,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

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

Run alphayeho/train4 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": "alphayeho/train4:a6123293588fe88d2a0ac0bd3dcc71eddd02fff90d7152841adec34ea25613c3",
    "input": {
      "model": "dev",
      "prompt": "man TOK",
      "lora_scale": 1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 3.5,
      "output_quality": 90,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-09-28T18:22:11.501059Z",
  "created_at": "2024-09-28T18:21:50.666000Z",
  "data_removed": false,
  "error": null,
  "id": "6nf1ezgws9rj20cj77f8xwmmwr",
  "input": {
    "model": "dev",
    "prompt": "man TOK",
    "lora_scale": 1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 3.5,
    "output_quality": 90,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Using seed: 38839\nPrompt: man TOK\n[!] txt2img mode\nUsing dev model\nfree=4488938237952\nDownloading weights\n2024-09-28T18:21:50Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpik12i749/weights url=https://replicate.delivery/yhqm/EfwT0sGyAT3UfETXdsoiGOzfnMeIfNBf2rAkYHVnf7X1eyMhTA/trained_model.tar\n2024-09-28T18:21:52Z | INFO  | [ Complete ] dest=/tmp/tmpik12i749/weights size=\"172 MB\" total_elapsed=1.290s url=https://replicate.delivery/yhqm/EfwT0sGyAT3UfETXdsoiGOzfnMeIfNBf2rAkYHVnf7X1eyMhTA/trained_model.tar\nDownloaded weights in 1.31s\nLoaded LoRAs in 2.13s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:17,  1.55it/s]\n  7%|▋         | 2/28 [00:01<00:14,  1.75it/s]\n 11%|█         | 3/28 [00:01<00:15,  1.66it/s]\n 14%|█▍        | 4/28 [00:02<00:14,  1.61it/s]\n 18%|█▊        | 5/28 [00:03<00:14,  1.59it/s]\n 21%|██▏       | 6/28 [00:03<00:13,  1.58it/s]\n 25%|██▌       | 7/28 [00:04<00:13,  1.57it/s]\n 29%|██▊       | 8/28 [00:05<00:12,  1.56it/s]\n 32%|███▏      | 9/28 [00:05<00:12,  1.56it/s]\n 36%|███▌      | 10/28 [00:06<00:11,  1.56it/s]\n 39%|███▉      | 11/28 [00:06<00:10,  1.55it/s]\n 43%|████▎     | 12/28 [00:07<00:10,  1.55it/s]\n 46%|████▋     | 13/28 [00:08<00:09,  1.55it/s]\n 50%|█████     | 14/28 [00:08<00:09,  1.55it/s]\n 54%|█████▎    | 15/28 [00:09<00:08,  1.55it/s]\n 57%|█████▋    | 16/28 [00:10<00:07,  1.55it/s]\n 61%|██████    | 17/28 [00:10<00:07,  1.55it/s]\n 64%|██████▍   | 18/28 [00:11<00:06,  1.55it/s]\n 68%|██████▊   | 19/28 [00:12<00:05,  1.55it/s]\n 71%|███████▏  | 20/28 [00:12<00:05,  1.55it/s]\n 75%|███████▌  | 21/28 [00:13<00:04,  1.55it/s]\n 79%|███████▊  | 22/28 [00:14<00:03,  1.55it/s]\n 82%|████████▏ | 23/28 [00:14<00:03,  1.55it/s]\n 86%|████████▌ | 24/28 [00:15<00:02,  1.55it/s]\n 89%|████████▉ | 25/28 [00:16<00:01,  1.55it/s]\n 93%|█████████▎| 26/28 [00:16<00:01,  1.55it/s]\n 96%|█████████▋| 27/28 [00:17<00:00,  1.55it/s]\n100%|██████████| 28/28 [00:17<00:00,  1.55it/s]\n100%|██████████| 28/28 [00:17<00:00,  1.56it/s]",
  "metrics": {
    "predict_time": 20.825837185,
    "total_time": 20.835059
  },
  "output": [
    "https://replicate.delivery/yhqm/0qPoUewvEdRfGkszrlYlIcgdIFFwJhtGLf9LSe0T5qEM1eLcC/out-0.webp"
  ],
  "started_at": "2024-09-28T18:21:50.675221Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/6nf1ezgws9rj20cj77f8xwmmwr",
    "cancel": "https://api.replicate.com/v1/predictions/6nf1ezgws9rj20cj77f8xwmmwr/cancel"
  },
  "version": "a6123293588fe88d2a0ac0bd3dcc71eddd02fff90d7152841adec34ea25613c3"
}

Generated in

20.8 seconds

Tweak it ShareReport

Using seed: 38839
Prompt: man TOK
[!] txt2img mode
Using dev model
free=4488938237952
Downloading weights
2024-09-28T18:21:50Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpik12i749/weights url=https://replicate.delivery/yhqm/EfwT0sGyAT3UfETXdsoiGOzfnMeIfNBf2rAkYHVnf7X1eyMhTA/trained_model.tar
2024-09-28T18:21:52Z | INFO  | [ Complete ] dest=/tmp/tmpik12i749/weights size="172 MB" total_elapsed=1.290s url=https://replicate.delivery/yhqm/EfwT0sGyAT3UfETXdsoiGOzfnMeIfNBf2rAkYHVnf7X1eyMhTA/trained_model.tar
Downloaded weights in 1.31s
Loaded LoRAs in 2.13s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:17,  1.55it/s]
  7%|▋         | 2/28 [00:01<00:14,  1.75it/s]
 11%|█         | 3/28 [00:01<00:15,  1.66it/s]
 14%|█▍        | 4/28 [00:02<00:14,  1.61it/s]
 18%|█▊        | 5/28 [00:03<00:14,  1.59it/s]
 21%|██▏       | 6/28 [00:03<00:13,  1.58it/s]
 25%|██▌       | 7/28 [00:04<00:13,  1.57it/s]
 29%|██▊       | 8/28 [00:05<00:12,  1.56it/s]
 32%|███▏      | 9/28 [00:05<00:12,  1.56it/s]
 36%|███▌      | 10/28 [00:06<00:11,  1.56it/s]
 39%|███▉      | 11/28 [00:06<00:10,  1.55it/s]
 43%|████▎     | 12/28 [00:07<00:10,  1.55it/s]
 46%|████▋     | 13/28 [00:08<00:09,  1.55it/s]
 50%|█████     | 14/28 [00:08<00:09,  1.55it/s]
 54%|█████▎    | 15/28 [00:09<00:08,  1.55it/s]
 57%|█████▋    | 16/28 [00:10<00:07,  1.55it/s]
 61%|██████    | 17/28 [00:10<00:07,  1.55it/s]
 64%|██████▍   | 18/28 [00:11<00:06,  1.55it/s]
 68%|██████▊   | 19/28 [00:12<00:05,  1.55it/s]
 71%|███████▏  | 20/28 [00:12<00:05,  1.55it/s]
 75%|███████▌  | 21/28 [00:13<00:04,  1.55it/s]
 79%|███████▊  | 22/28 [00:14<00:03,  1.55it/s]
 82%|████████▏ | 23/28 [00:14<00:03,  1.55it/s]
 86%|████████▌ | 24/28 [00:15<00:02,  1.55it/s]
 89%|████████▉ | 25/28 [00:16<00:01,  1.55it/s]
 93%|█████████▎| 26/28 [00:16<00:01,  1.55it/s]
 96%|█████████▋| 27/28 [00:17<00:00,  1.55it/s]
100%|██████████| 28/28 [00:17<00:00,  1.55it/s]
100%|██████████| 28/28 [00:17<00:00,  1.56it/s]

Want to make some of these yourself?

Run this model