Prediction

Model

justmalhar/flux-excalidraw:f854fe3a

nkjksndwc9rj60cj6z5v5q901r

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

77.1s

Created

about 1 year ago

Webhook

–

Input

prompt: A handrawn sketch in the style of EXCALIDRAW shows a computer operating system with title text “LLM OS” . The sketch is divided into sections, each with a different function of the operating system. The sections include keyboard shortcuts, game controller, and a summary of the operating system. The drawing is done in a cartoon style, making it visually appealing and easy to understand.
aspect_ratio: 1:1
prompt_strength: 0.8
model: dev
num_outputs: 4
num_inference_steps: 28
guidance_scale: 3.5
output_format: jpg
output_quality: 100
lora_scale: 1
extra_lora_scale: 1

{
  "aspect_ratio": "1:1",
  "extra_lora_scale": 1,
  "guidance_scale": 3.5,
  "lora_scale": 1,
  "model": "dev",
  "num_inference_steps": 28,
  "num_outputs": 4,
  "output_format": "jpg",
  "output_quality": 100,
  "prompt": "A handrawn sketch in the style of EXCALIDRAW shows a computer operating system with title text “LLM OS” . The sketch is divided into sections, each with a different function of the operating system. The sections include keyboard shortcuts, game controller, and a summary of the operating system. The drawing is done in a cartoon style, making it visually appealing and easy to understand.",
  "prompt_strength": 0.8
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_1cB**********************************

This is your API token. Keep it to yourself.

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 justmalhar/flux-excalidraw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "justmalhar/flux-excalidraw:f854fe3a91032428d4a0d3717cba6314887a6f248cbd1568e58eb424d69bf994",
  {
    input: {
      aspect_ratio: "1:1",
      extra_lora_scale: 1,
      guidance_scale: 3.5,
      lora_scale: 1,
      model: "dev",
      num_inference_steps: 28,
      num_outputs: 4,
      output_format: "jpg",
      output_quality: 100,
      prompt: "A handrawn sketch in the style of EXCALIDRAW shows a computer operating system with title text “LLM OS” . The sketch is divided into sections, each with a different function of the operating system. The sections include keyboard shortcuts, game controller, and a summary of the operating system. The drawing is done in a cartoon style, making it visually appealing and easy to understand.",
      prompt_strength: 0.8
    }
  }
);

// 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=r8_1cB**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run justmalhar/flux-excalidraw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "justmalhar/flux-excalidraw:f854fe3a91032428d4a0d3717cba6314887a6f248cbd1568e58eb424d69bf994",
    input={
        "aspect_ratio": "1:1",
        "extra_lora_scale": 1,
        "guidance_scale": 3.5,
        "lora_scale": 1,
        "model": "dev",
        "num_inference_steps": 28,
        "num_outputs": 4,
        "output_format": "jpg",
        "output_quality": 100,
        "prompt": "A handrawn sketch in the style of EXCALIDRAW shows a computer operating system with title text “LLM OS” . The sketch is divided into sections, each with a different function of the operating system. The sections include keyboard shortcuts, game controller, and a summary of the operating system. The drawing is done in a cartoon style, making it visually appealing and easy to understand.",
        "prompt_strength": 0.8
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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=r8_1cB**********************************

This is your API token. Keep it to yourself.

Run justmalhar/flux-excalidraw 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": "justmalhar/flux-excalidraw:f854fe3a91032428d4a0d3717cba6314887a6f248cbd1568e58eb424d69bf994",
    "input": {
      "aspect_ratio": "1:1",
      "extra_lora_scale": 1,
      "guidance_scale": 3.5,
      "lora_scale": 1,
      "model": "dev",
      "num_inference_steps": 28,
      "num_outputs": 4,
      "output_format": "jpg",
      "output_quality": 100,
      "prompt": "A handrawn sketch in the style of EXCALIDRAW shows a computer operating system with title text “LLM OS” . The sketch is divided into sections, each with a different function of the operating system. The sections include keyboard shortcuts, game controller, and a summary of the operating system. The drawing is done in a cartoon style, making it visually appealing and easy to understand.",
      "prompt_strength": 0.8
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "nkjksndwc9rj60cj6z5v5q901r",
  "model": "justmalhar/flux-excalidraw",
  "version": "f854fe3a91032428d4a0d3717cba6314887a6f248cbd1568e58eb424d69bf994",
  "input": {
    "aspect_ratio": "1:1",
    "extra_lora_scale": 1,
    "guidance_scale": 3.5,
    "lora_scale": 1,
    "model": "dev",
    "num_inference_steps": 28,
    "num_outputs": 4,
    "output_format": "jpg",
    "output_quality": 100,
    "prompt": "A handrawn sketch in the style of EXCALIDRAW shows a computer operating system with title text “LLM OS” . The sketch is divided into sections, each with a different function of the operating system. The sections include keyboard shortcuts, game controller, and a summary of the operating system. The drawing is done in a cartoon style, making it visually appealing and easy to understand.",
    "prompt_strength": 0.8
  },
  "logs": "Using seed: 1485\nPrompt: A handrawn sketch in the style of EXCALIDRAW shows a computer operating system with title text “LLM OS” . The sketch is divided into sections, each with a different function of the operating system. The sections include keyboard shortcuts, game controller, and a summary of the operating system. The drawing is done in a cartoon style, making it visually appealing and easy to understand.\n[!] txt2img mode\nUsing dev model\nfree=4626895077376\nDownloading weights\n2024-09-28T08:42:33Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp7x32phfa/weights url=https://replicate.delivery/yhqm/0D8yaMZoPV5bGd9qo3djWuYFP5UUX4HK97sbnb538hZDyV4E/trained_model.tar\n2024-09-28T08:42:36Z | INFO  | [ Complete ] dest=/tmp/tmp7x32phfa/weights size=\"430 MB\" total_elapsed=2.934s url=https://replicate.delivery/yhqm/0D8yaMZoPV5bGd9qo3djWuYFP5UUX4HK97sbnb538hZDyV4E/trained_model.tar\nDownloaded weights in 2.97s\nLoaded LoRAs in 3.84s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:02<01:07,  2.48s/it]\n  7%|▋         | 2/28 [00:04<00:57,  2.20s/it]\n 11%|█         | 3/28 [00:06<00:58,  2.33s/it]\n 14%|█▍        | 4/28 [00:09<00:57,  2.39s/it]\n 18%|█▊        | 5/28 [00:11<00:55,  2.43s/it]\n 21%|██▏       | 6/28 [00:14<00:53,  2.45s/it]\n 25%|██▌       | 7/28 [00:16<00:51,  2.46s/it]\n 29%|██▊       | 8/28 [00:19<00:49,  2.47s/it]\n 32%|███▏      | 9/28 [00:21<00:47,  2.48s/it]\n 36%|███▌      | 10/28 [00:24<00:44,  2.48s/it]\n 39%|███▉      | 11/28 [00:26<00:42,  2.48s/it]\n 43%|████▎     | 12/28 [00:29<00:39,  2.49s/it]\n 46%|████▋     | 13/28 [00:31<00:37,  2.49s/it]\n 50%|█████     | 14/28 [00:34<00:34,  2.49s/it]\n 54%|█████▎    | 15/28 [00:36<00:32,  2.49s/it]\n 57%|█████▋    | 16/28 [00:39<00:29,  2.49s/it]\n 61%|██████    | 17/28 [00:41<00:27,  2.49s/it]\n 64%|██████▍   | 18/28 [00:44<00:24,  2.49s/it]\n 68%|██████▊   | 19/28 [00:46<00:22,  2.49s/it]\n 71%|███████▏  | 20/28 [00:49<00:19,  2.49s/it]\n 75%|███████▌  | 21/28 [00:51<00:17,  2.49s/it]\n 79%|███████▊  | 22/28 [00:54<00:14,  2.50s/it]\n 82%|████████▏ | 23/28 [00:56<00:12,  2.50s/it]\n 86%|████████▌ | 24/28 [00:59<00:09,  2.50s/it]\n 89%|████████▉ | 25/28 [01:01<00:07,  2.50s/it]\n 93%|█████████▎| 26/28 [01:04<00:04,  2.50s/it]\n 96%|█████████▋| 27/28 [01:06<00:02,  2.50s/it]\n100%|██████████| 28/28 [01:09<00:00,  2.50s/it]\n100%|██████████| 28/28 [01:09<00:00,  2.47s/it]",
  "output": [
    "https://replicate.delivery/yhqm/Wguk1h2oDMLBDFjxTR2GMi1ZxHKuFVSJckcALR375qCxzV4E/out-0.jpg",
    "https://replicate.delivery/yhqm/KeOEflX6y7oFmEXzhe3E4jwH21GHkeayIXOtTHQNgMRR8cFOB/out-1.jpg",
    "https://replicate.delivery/yhqm/wf3uhhI14lXfP0eCl6701RNUqgyEZTiEVvA1sOEg39eT8cFOB/out-2.jpg",
    "https://replicate.delivery/yhqm/fA5nMwo7D8UvT6DKuolJHbCf7mT8BAbR01B76vjAhRgEPXhTA/out-3.jpg"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2024-09-28T08:42:31.906Z",
  "started_at": "2024-09-28T08:42:33.600752Z",
  "completed_at": "2024-09-28T08:43:49.001092Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/nkjksndwc9rj60cj6z5v5q901r/cancel",
    "get": "https://api.replicate.com/v1/predictions/nkjksndwc9rj60cj6z5v5q901r",
    "web": "https://replicate.com/p/nkjksndwc9rj60cj6z5v5q901r"
  },
  "metrics": {
    "predict_time": 75.400339734,
    "total_time": 77.095092
  }
}

Generated in

75.4 seconds

Tweak it Report

Using seed: 1485 Prompt: A handrawn sketch in the style of EXCALIDRAW shows a computer operating system with title text “LLM OS” . The sketch is divided into sections, each with a different function of the operating system. The sections include keyboard shortcuts, game controller, and a summary of the operating system. The drawing is done in a cartoon style, making it visually appealing and easy to understand. [!] txt2img mode Using dev model free=4626895077376 Downloading weights 2024-09-28T08:42:33Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp7x32phfa/weights url=https://replicate.delivery/yhqm/0D8yaMZoPV5bGd9qo3djWuYFP5UUX4HK97sbnb538hZDyV4E/trained_model.tar 2024-09-28T08:42:36Z | INFO | [ Complete ] dest=/tmp/tmp7x32phfa/weights size="430 MB" total_elapsed=2.934s url=https://replicate.delivery/yhqm/0D8yaMZoPV5bGd9qo3djWuYFP5UUX4HK97sbnb538hZDyV4E/trained_model.tar Downloaded weights in 2.97s Loaded LoRAs in 3.84s 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:02<01:07, 2.48s/it] 7%|▋ | 2/28 [00:04<00:57, 2.20s/it] 11%|█ | 3/28 [00:06<00:58, 2.33s/it] 14%|█▍ | 4/28 [00:09<00:57, 2.39s/it] 18%|█▊ | 5/28 [00:11<00:55, 2.43s/it] 21%|██▏ | 6/28 [00:14<00:53, 2.45s/it] 25%|██▌ | 7/28 [00:16<00:51, 2.46s/it] 29%|██▊ | 8/28 [00:19<00:49, 2.47s/it] 32%|███▏ | 9/28 [00:21<00:47, 2.48s/it] 36%|███▌ | 10/28 [00:24<00:44, 2.48s/it] 39%|███▉ | 11/28 [00:26<00:42, 2.48s/it] 43%|████▎ | 12/28 [00:29<00:39, 2.49s/it] 46%|████▋ | 13/28 [00:31<00:37, 2.49s/it] 50%|█████ | 14/28 [00:34<00:34, 2.49s/it] 54%|█████▎ | 15/28 [00:36<00:32, 2.49s/it] 57%|█████▋ | 16/28 [00:39<00:29, 2.49s/it] 61%|██████ | 17/28 [00:41<00:27, 2.49s/it] 64%|██████▍ | 18/28 [00:44<00:24, 2.49s/it] 68%|██████▊ | 19/28 [00:46<00:22, 2.49s/it] 71%|███████▏ | 20/28 [00:49<00:19, 2.49s/it] 75%|███████▌ | 21/28 [00:51<00:17, 2.49s/it] 79%|███████▊ | 22/28 [00:54<00:14, 2.50s/it] 82%|████████▏ | 23/28 [00:56<00:12, 2.50s/it] 86%|████████▌ | 24/28 [00:59<00:09, 2.50s/it] 89%|████████▉ | 25/28 [01:01<00:07, 2.50s/it] 93%|█████████▎| 26/28 [01:04<00:04, 2.50s/it] 96%|█████████▋| 27/28 [01:06<00:02, 2.50s/it] 100%|██████████| 28/28 [01:09<00:00, 2.50s/it] 100%|██████████| 28/28 [01:09<00:00, 2.47s/it]