@miike-ai's miike-ai/flux-sprites

Model

miike-ai/flux-sprites:bfbaa424

9e8wqefx0xrj00cj95bbjwvd24

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

8.5s

Created

about 1 year ago

Webhook

–

Input

prompt: A sprite sheet of SPRITES showcasing an animated Paladin character in various action poses. The SPRITES are arranged in a grid pattern equal distance between each other, with each Link having a unique poses and weapons.
aspect_ratio: 1:1
prompt_strength: 0.8
model: schnell
num_outputs: 1
num_inference_steps: 8
guidance_scale: 3.5
output_format: webp
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": "schnell",
  "num_inference_steps": 8,
  "num_outputs": 1,
  "output_format": "webp",
  "output_quality": 100,
  "prompt": "A sprite sheet of SPRITES showcasing an animated Paladin character in various action poses. The SPRITES are arranged in a grid pattern equal distance between each other, with each Link having a unique poses and weapons.",
  "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_fHv**********************************

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

const output = await replicate.run(
  "miike-ai/flux-sprites:bfbaa4240a9948bcc5483cceb9abd73db68c63018a4a7ba5b8a01616d291dcc9",
  {
    input: {
      aspect_ratio: "1:1",
      extra_lora_scale: 1,
      guidance_scale: 3.5,
      lora_scale: 1,
      model: "schnell",
      num_inference_steps: 8,
      num_outputs: 1,
      output_format: "webp",
      output_quality: 100,
      prompt: "A sprite sheet of SPRITES showcasing an animated Paladin character in various action poses. The SPRITES are arranged in a grid pattern equal distance between each other, with each Link having a unique poses and weapons.",
      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_fHv**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

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

output = replicate.run(
    "miike-ai/flux-sprites:bfbaa4240a9948bcc5483cceb9abd73db68c63018a4a7ba5b8a01616d291dcc9",
    input={
        "aspect_ratio": "1:1",
        "extra_lora_scale": 1,
        "guidance_scale": 3.5,
        "lora_scale": 1,
        "model": "schnell",
        "num_inference_steps": 8,
        "num_outputs": 1,
        "output_format": "webp",
        "output_quality": 100,
        "prompt": "A sprite sheet of SPRITES showcasing an animated Paladin character in various action poses. The SPRITES are arranged in a grid pattern equal distance between each other, with each Link having a unique poses and weapons.",
        "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_fHv**********************************

This is your API token. Keep it to yourself.

Run miike-ai/flux-sprites 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": "miike-ai/flux-sprites:bfbaa4240a9948bcc5483cceb9abd73db68c63018a4a7ba5b8a01616d291dcc9",
    "input": {
      "aspect_ratio": "1:1",
      "extra_lora_scale": 1,
      "guidance_scale": 3.5,
      "lora_scale": 1,
      "model": "schnell",
      "num_inference_steps": 8,
      "num_outputs": 1,
      "output_format": "webp",
      "output_quality": 100,
      "prompt": "A sprite sheet of SPRITES showcasing an animated Paladin character in various action poses. The SPRITES are arranged in a grid pattern equal distance between each other, with each Link having a unique poses and weapons.",
      "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": "9e8wqefx0xrj00cj95bbjwvd24",
  "model": "miike-ai/flux-sprites",
  "version": "bfbaa4240a9948bcc5483cceb9abd73db68c63018a4a7ba5b8a01616d291dcc9",
  "input": {
    "aspect_ratio": "1:1",
    "extra_lora_scale": 1,
    "guidance_scale": 3.5,
    "lora_scale": 1,
    "model": "schnell",
    "num_inference_steps": 8,
    "num_outputs": 1,
    "output_format": "webp",
    "output_quality": 100,
    "prompt": "A sprite sheet of SPRITES showcasing an animated Paladin character in various action poses. The SPRITES are arranged in a grid pattern equal distance between each other, with each Link having a unique poses and weapons.",
    "prompt_strength": 0.8
  },
  "logs": "Using seed: 56556\nPrompt: A sprite sheet of SPRITES showcasing an animated Paladin character in various action poses. The SPRITES are arranged in a grid pattern equal distance between each other, with each Link having a unique poses and weapons.\n[!] txt2img mode\nUsing schnell model\nfree=2980394508288\nDownloading weights\n2024-10-01T18:28:10Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpea5snvdf/weights url=https://replicate.delivery/yhqm/BrBhiiwPD0ZSM1m5lv38DSuTd9xXKLJQFFpUR5vM7Q0Erj4E/trained_model.tar\n2024-10-01T18:28:12Z | INFO  | [ Complete ] dest=/tmp/tmpea5snvdf/weights size=\"1.4 GB\" total_elapsed=1.744s url=https://replicate.delivery/yhqm/BrBhiiwPD0ZSM1m5lv38DSuTd9xXKLJQFFpUR5vM7Q0Erj4E/trained_model.tar\nDownloaded weights in 1.82s\nLoaded LoRAs in 2.94s\n  0%|          | 0/8 [00:00<?, ?it/s]\n 12%|█▎        | 1/8 [00:00<00:04,  1.59it/s]\n 25%|██▌       | 2/8 [00:01<00:03,  1.80it/s]\n 38%|███▊      | 3/8 [00:01<00:02,  1.70it/s]\n 50%|█████     | 4/8 [00:02<00:02,  1.65it/s]\n 62%|██████▎   | 5/8 [00:03<00:01,  1.63it/s]\n 75%|███████▌  | 6/8 [00:03<00:01,  1.62it/s]\n 88%|████████▊ | 7/8 [00:04<00:00,  1.61it/s]\n100%|██████████| 8/8 [00:04<00:00,  1.60it/s]\n100%|██████████| 8/8 [00:04<00:00,  1.63it/s]",
  "output": [
    "https://replicate.delivery/yhqm/VPaxqOrgmWLYI1rNwGo5jrA2ynFk5GWj3Jfrdq8ShvPhiPxJA/out-0.webp"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2024-10-01T18:28:10.631Z",
  "started_at": "2024-10-01T18:28:10.641195Z",
  "completed_at": "2024-10-01T18:28:19.16148Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/9e8wqefx0xrj00cj95bbjwvd24/cancel",
    "get": "https://api.replicate.com/v1/predictions/9e8wqefx0xrj00cj95bbjwvd24",
    "web": "https://replicate.com/p/9e8wqefx0xrj00cj95bbjwvd24"
  },
  "metrics": {
    "predict_time": 8.520285038,
    "total_time": 8.53048
  }
}

Generated in

8.5 seconds

Tweak it Report