Prediction

Model

dslteaching/alvin:c1fe8d43

6nx7jyzw2hrme0cm8pht5qwpbc

Status

Succeeded

Source

Web

Hardware

H100

Total duration

8.1s

Created

11 months ago

Webhook

–

Input

prompt: A cartoon illustration in the style of AAST
image: https://replicate.delivery/pbxt/MHlHZzs9tmnOIFLXP3QUY6EUzGw5t1NBkoPN9cUSkHcBaV6L/Petland_Florida_Cavalier_King_Charles_Spaniel_puppy.jpg
aspect_ratio: 1:1
prompt_strength: 0.8
model: dev
num_outputs: 1
num_inference_steps: 28
guidance_scale: 3
output_format: webp
output_quality: 80
go_fast: false
megapixels: 1
lora_scale: 1
extra_lora_scale: 1

{
  "aspect_ratio": "1:1",
  "extra_lora_scale": 1,
  "go_fast": false,
  "guidance_scale": 3,
  "image": "https://replicate.delivery/pbxt/MHlHZzs9tmnOIFLXP3QUY6EUzGw5t1NBkoPN9cUSkHcBaV6L/Petland_Florida_Cavalier_King_Charles_Spaniel_puppy.jpg",
  "lora_scale": 1,
  "megapixels": "1",
  "model": "dev",
  "num_inference_steps": 28,
  "num_outputs": 1,
  "output_format": "webp",
  "output_quality": 80,
  "prompt": "A cartoon illustration in the style of AAST",
  "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_erG**********************************

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

const output = await replicate.run(
  "dslteaching/alvin:c1fe8d431d735dd9f5272a41af66b07797e8caef07bf2c4a3bc3251c612506f0",
  {
    input: {
      aspect_ratio: "1:1",
      extra_lora_scale: 1,
      go_fast: false,
      guidance_scale: 3,
      image: "https://replicate.delivery/pbxt/MHlHZzs9tmnOIFLXP3QUY6EUzGw5t1NBkoPN9cUSkHcBaV6L/Petland_Florida_Cavalier_King_Charles_Spaniel_puppy.jpg",
      lora_scale: 1,
      megapixels: "1",
      model: "dev",
      num_inference_steps: 28,
      num_outputs: 1,
      output_format: "webp",
      output_quality: 80,
      prompt: "A cartoon illustration in the style of AAST",
      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_erG**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

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

output = replicate.run(
    "dslteaching/alvin:c1fe8d431d735dd9f5272a41af66b07797e8caef07bf2c4a3bc3251c612506f0",
    input={
        "aspect_ratio": "1:1",
        "extra_lora_scale": 1,
        "go_fast": False,
        "guidance_scale": 3,
        "image": "https://replicate.delivery/pbxt/MHlHZzs9tmnOIFLXP3QUY6EUzGw5t1NBkoPN9cUSkHcBaV6L/Petland_Florida_Cavalier_King_Charles_Spaniel_puppy.jpg",
        "lora_scale": 1,
        "megapixels": "1",
        "model": "dev",
        "num_inference_steps": 28,
        "num_outputs": 1,
        "output_format": "webp",
        "output_quality": 80,
        "prompt": "A cartoon illustration in the style of AAST",
        "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_erG**********************************

This is your API token. Keep it to yourself.

Run dslteaching/alvin 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": "dslteaching/alvin:c1fe8d431d735dd9f5272a41af66b07797e8caef07bf2c4a3bc3251c612506f0",
    "input": {
      "aspect_ratio": "1:1",
      "extra_lora_scale": 1,
      "go_fast": false,
      "guidance_scale": 3,
      "image": "https://replicate.delivery/pbxt/MHlHZzs9tmnOIFLXP3QUY6EUzGw5t1NBkoPN9cUSkHcBaV6L/Petland_Florida_Cavalier_King_Charles_Spaniel_puppy.jpg",
      "lora_scale": 1,
      "megapixels": "1",
      "model": "dev",
      "num_inference_steps": 28,
      "num_outputs": 1,
      "output_format": "webp",
      "output_quality": 80,
      "prompt": "A cartoon illustration in the style of AAST",
      "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": "6nx7jyzw2hrme0cm8pht5qwpbc",
  "model": "dslteaching/alvin",
  "version": "c1fe8d431d735dd9f5272a41af66b07797e8caef07bf2c4a3bc3251c612506f0",
  "input": {
    "aspect_ratio": "1:1",
    "extra_lora_scale": 1,
    "go_fast": false,
    "guidance_scale": 3,
    "image": "https://replicate.delivery/pbxt/MHlHZzs9tmnOIFLXP3QUY6EUzGw5t1NBkoPN9cUSkHcBaV6L/Petland_Florida_Cavalier_King_Charles_Spaniel_puppy.jpg",
    "lora_scale": 1,
    "megapixels": "1",
    "model": "dev",
    "num_inference_steps": 28,
    "num_outputs": 1,
    "output_format": "webp",
    "output_quality": 80,
    "prompt": "A cartoon illustration in the style of AAST",
    "prompt_strength": 0.8
  },
  "logs": "2025-01-08 11:19:22.518 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-08 11:19:22.518 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  95%|█████████▌| 289/304 [00:00<00:00, 2877.09it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2793.03it/s]\n2025-01-08 11:19:22.627 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.11s\nfree=28896518746112\nDownloading weights\n2025-01-08T11:19:22Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpio0ozq8h/weights url=https://replicate.delivery/xezq/zoleyQqIJrWePk6PUFYmFaz49CcIb5IyKUQ6DEd6Qes36AGoA/trained_model.tar\n2025-01-08T11:19:25Z | INFO  | [ Complete ] dest=/tmp/tmpio0ozq8h/weights size=\"644 MB\" total_elapsed=3.272s url=https://replicate.delivery/xezq/zoleyQqIJrWePk6PUFYmFaz49CcIb5IyKUQ6DEd6Qes36AGoA/trained_model.tar\nDownloaded weights in 3.32s\n2025-01-08 11:19:25.950 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/7571a90d53eee5d6\n2025-01-08 11:19:26.120 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded\n2025-01-08 11:19:26.120 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-08 11:19:26.120 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  98%|█████████▊| 298/304 [00:00<00:00, 2977.35it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2987.77it/s]\n2025-01-08 11:19:26.222 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.27s\nUsing seed: 22512\nImage detected - setting to img2img mode\nInput image size: 1000x709\nInput image size set to: 992x704\n0it [00:00, ?it/s]\n2it [00:00,  9.12it/s]\n3it [00:00,  8.23it/s]\n4it [00:00,  7.83it/s]\n5it [00:00,  7.62it/s]\n6it [00:00,  7.50it/s]\n7it [00:00,  7.41it/s]\n8it [00:01,  7.33it/s]\n9it [00:01,  7.27it/s]\n10it [00:01,  7.26it/s]\n11it [00:01,  7.25it/s]\n12it [00:01,  7.25it/s]\n13it [00:01,  7.24it/s]\n14it [00:01,  7.24it/s]\n15it [00:02,  7.23it/s]\n16it [00:02,  7.22it/s]\n17it [00:02,  7.21it/s]\n18it [00:02,  7.22it/s]\n19it [00:02,  7.22it/s]\n20it [00:02,  7.21it/s]\n21it [00:02,  7.19it/s]\n22it [00:02,  7.21it/s]\n23it [00:03,  7.20it/s]\n23it [00:03,  7.35it/s]\nTotal safe images: 1 out of 1",
  "output": [
    "https://replicate.delivery/xezq/gMfi9flb98mQhExbJiAt19N9mvahJMn3MwioYIBim0LCFBDUA/out-0.webp"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2025-01-08T11:19:22.388Z",
  "started_at": "2025-01-08T11:19:22.396051Z",
  "completed_at": "2025-01-08T11:19:30.452196Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/6nx7jyzw2hrme0cm8pht5qwpbc/cancel",
    "get": "https://api.replicate.com/v1/predictions/6nx7jyzw2hrme0cm8pht5qwpbc",
    "stream": "https://stream.replicate.com/v1/files/bcwr-o6ayhkqz5inocizgv7ewgkint34p2wu6etdbwnb5ykmgppokobbq",
    "web": "https://replicate.com/p/6nx7jyzw2hrme0cm8pht5qwpbc"
  },
  "metrics": {
    "predict_time": 8.056144528,
    "total_time": 8.064196
  }
}

Generated in

8.1 seconds

Tweak it Report

2025-01-08 11:19:22.518 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2025-01-08 11:19:22.518 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 95%|█████████▌| 289/304 [00:00<00:00, 2877.09it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2793.03it/s] 2025-01-08 11:19:22.627 | SUCCESS | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.11s free=28896518746112 Downloading weights 2025-01-08T11:19:22Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpio0ozq8h/weights url=https://replicate.delivery/xezq/zoleyQqIJrWePk6PUFYmFaz49CcIb5IyKUQ6DEd6Qes36AGoA/trained_model.tar 2025-01-08T11:19:25Z | INFO | [ Complete ] dest=/tmp/tmpio0ozq8h/weights size="644 MB" total_elapsed=3.272s url=https://replicate.delivery/xezq/zoleyQqIJrWePk6PUFYmFaz49CcIb5IyKUQ6DEd6Qes36AGoA/trained_model.tar Downloaded weights in 3.32s 2025-01-08 11:19:25.950 | INFO | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/7571a90d53eee5d6 2025-01-08 11:19:26.120 | INFO | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded 2025-01-08 11:19:26.120 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2025-01-08 11:19:26.120 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 98%|█████████▊| 298/304 [00:00<00:00, 2977.35it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2987.77it/s] 2025-01-08 11:19:26.222 | SUCCESS | fp8.lora_loading:load_lora:539 - LoRA applied in 0.27s Using seed: 22512 Image detected - setting to img2img mode Input image size: 1000x709 Input image size set to: 992x704 0it [00:00, ?it/s] 2it [00:00, 9.12it/s] 3it [00:00, 8.23it/s] 4it [00:00, 7.83it/s] 5it [00:00, 7.62it/s] 6it [00:00, 7.50it/s] 7it [00:00, 7.41it/s] 8it [00:01, 7.33it/s] 9it [00:01, 7.27it/s] 10it [00:01, 7.26it/s] 11it [00:01, 7.25it/s] 12it [00:01, 7.25it/s] 13it [00:01, 7.24it/s] 14it [00:01, 7.24it/s] 15it [00:02, 7.23it/s] 16it [00:02, 7.22it/s] 17it [00:02, 7.21it/s] 18it [00:02, 7.22it/s] 19it [00:02, 7.22it/s] 20it [00:02, 7.21it/s] 21it [00:02, 7.19it/s] 22it [00:02, 7.21it/s] 23it [00:03, 7.20it/s] 23it [00:03, 7.35it/s] Total safe images: 1 out of 1