Prediction

sxjbkqcpf5rm00chr6vvmmbh0w

Status

Succeeded

Source

Web

Hardware

H100

Total duration

21.1s

Created

9 months ago

Input

model: dev
prompt: data center in the style of archillect, grayscale
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

{
  "model": "dev",
  "prompt": "data center in the style of archillect, grayscale",
  "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
}

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 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
  {
    input: {
      model: "dev",
      prompt: "data center in the style of archillect, grayscale",
      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.

pip install replicate

Import the client:

import replicate

Run 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    input={
        "model": "dev",
        "prompt": "data center in the style of archillect, grayscale",
        "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 0xtuba/archillect-lora 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": "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    "input": {
      "model": "dev",
      "prompt": "data center in the style of archillect, grayscale",
      "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": "2024-09-05T10:25:41.074682Z",
  "created_at": "2024-09-05T10:25:19.993000Z",
  "data_removed": false,
  "error": null,
  "id": "sxjbkqcpf5rm00chr6vvmmbh0w",
  "input": {
    "model": "dev",
    "prompt": "data center in the style of archillect, grayscale",
    "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: 55802\nPrompt: data center in the style of archillect, grayscale\ntxt2img mode\nUsing dev model\nfree=8604409741312\nDownloading weights\n2024-09-05T10:25:20Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpuqehlle4/weights url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar\n2024-09-05T10:25:23Z | INFO  | [ Complete ] dest=/tmp/tmpuqehlle4/weights size=\"172 MB\" total_elapsed=3.299s url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar\nDownloaded weights in 3.33s\nLoaded LoRAs in 12.51s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.47it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.92it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.70it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.60it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.55it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.52it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.50it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.49it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.48it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.48it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.48it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.47it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.47it/s]\n 50%|█████     | 14/28 [00:03<00:04,  3.47it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.47it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.47it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.47it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.47it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.47it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.47it/s]\n 75%|███████▌  | 21/28 [00:06<00:02,  3.46it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.47it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.46it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.47it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.47it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.47it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.47it/s]\n100%|██████████| 28/28 [00:08<00:00,  3.47it/s]\n100%|██████████| 28/28 [00:08<00:00,  3.49it/s]",
  "metrics": {
    "predict_time": 21.071949953,
    "total_time": 21.081682
  },
  "output": [
    "https://replicate.delivery/yhqm/E7F5mn6751rGNBhRuXLgiQgaEcl03jqNhhQpVuQ5S7KJ5c2E/out-0.webp"
  ],
  "started_at": "2024-09-05T10:25:20.002732Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/sxjbkqcpf5rm00chr6vvmmbh0w",
    "cancel": "https://api.replicate.com/v1/predictions/sxjbkqcpf5rm00chr6vvmmbh0w/cancel"
  },
  "version": "599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42"
}

Generated in

21.1 seconds

0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42

Using seed: 55802
Prompt: data center in the style of archillect, grayscale
txt2img mode
Using dev model
free=8604409741312
Downloading weights
2024-09-05T10:25:20Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpuqehlle4/weights url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar
2024-09-05T10:25:23Z | INFO  | [ Complete ] dest=/tmp/tmpuqehlle4/weights size="172 MB" total_elapsed=3.299s url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar
Downloaded weights in 3.33s
Loaded LoRAs in 12.51s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:07,  3.47it/s]
  7%|▋         | 2/28 [00:00<00:06,  3.92it/s]
 11%|█         | 3/28 [00:00<00:06,  3.70it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.60it/s]
 18%|█▊        | 5/28 [00:01<00:06,  3.55it/s]
 21%|██▏       | 6/28 [00:01<00:06,  3.52it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.50it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.49it/s]
 32%|███▏      | 9/28 [00:02<00:05,  3.48it/s]
 36%|███▌      | 10/28 [00:02<00:05,  3.48it/s]
 39%|███▉      | 11/28 [00:03<00:04,  3.48it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.47it/s]
 46%|████▋     | 13/28 [00:03<00:04,  3.47it/s]
 50%|█████     | 14/28 [00:03<00:04,  3.47it/s]
 54%|█████▎    | 15/28 [00:04<00:03,  3.47it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.47it/s]
 61%|██████    | 17/28 [00:04<00:03,  3.47it/s]
 64%|██████▍   | 18/28 [00:05<00:02,  3.47it/s]
 68%|██████▊   | 19/28 [00:05<00:02,  3.47it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.47it/s]
 75%|███████▌  | 21/28 [00:06<00:02,  3.46it/s]
 79%|███████▊  | 22/28 [00:06<00:01,  3.47it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  3.46it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.47it/s]
 89%|████████▉ | 25/28 [00:07<00:00,  3.47it/s]
 93%|█████████▎| 26/28 [00:07<00:00,  3.47it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.47it/s]
100%|██████████| 28/28 [00:08<00:00,  3.47it/s]
100%|██████████| 28/28 [00:08<00:00,  3.49it/s]

Prediction

Model

p9sprtk591rm40chr70srw8fwr

Status

Succeeded

Source

Web

Hardware

H100

Total duration

17.7s

Created

9 months ago by @0xtuba

Input

model: dev
prompt: small empty room with many computer screens in the style of ARCHLLCT, grayscale
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

{
  "model": "dev",
  "prompt": "small empty room with many computer screens in the style of ARCHLLCT, grayscale",
  "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
}

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 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
  {
    input: {
      model: "dev",
      prompt: "small empty room with many computer screens in the style of ARCHLLCT, grayscale",
      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.

pip install replicate

Import the client:

import replicate

Run 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    input={
        "model": "dev",
        "prompt": "small empty room with many computer screens in the style of ARCHLLCT, grayscale",
        "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 0xtuba/archillect-lora 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": "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    "input": {
      "model": "dev",
      "prompt": "small empty room with many computer screens in the style of ARCHLLCT, grayscale",
      "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": "2024-09-05T10:36:20.467623Z",
  "created_at": "2024-09-05T10:36:02.760000Z",
  "data_removed": false,
  "error": null,
  "id": "p9sprtk591rm40chr70srw8fwr",
  "input": {
    "model": "dev",
    "prompt": "small empty room with many computer screens in the style of ARCHLLCT, grayscale",
    "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: 49085\nPrompt: small empty room with many computer screens in the style of ARCHLLCT, grayscale\ntxt2img mode\nUsing dev model\nLoaded LoRAs in 9.08s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.46it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.91it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.69it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.60it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.55it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.52it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.51it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.49it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.49it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.48it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.48it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.47it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.47it/s]\n 50%|█████     | 14/28 [00:03<00:04,  3.47it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.47it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.47it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.47it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.46it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.47it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.46it/s]\n 75%|███████▌  | 21/28 [00:06<00:02,  3.46it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.46it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.46it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.46it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.46it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.47it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.45it/s]\n100%|██████████| 28/28 [00:08<00:00,  3.46it/s]\n100%|██████████| 28/28 [00:08<00:00,  3.49it/s]",
  "metrics": {
    "predict_time": 17.69888967,
    "total_time": 17.707623
  },
  "output": [
    "https://replicate.delivery/yhqm/O0eNA4366iUPHqW5DLdnLjZdgoXwtEzZLe7huLppYafJdnzmA/out-0.webp"
  ],
  "started_at": "2024-09-05T10:36:02.768734Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/p9sprtk591rm40chr70srw8fwr",
    "cancel": "https://api.replicate.com/v1/predictions/p9sprtk591rm40chr70srw8fwr/cancel"
  },
  "version": "599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42"
}

Generated in

17.7 seconds

0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42

Prediction

Model

0wekf80stnrm60chr7196zt7q8

Status

Succeeded

Source

Web

Hardware

H100

Total duration

25.8s

Created

9 months ago

Input

model: dev
prompt: hospital ward in the style of ARCHLLCT
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

{
  "model": "dev",
  "prompt": "hospital ward in the style of ARCHLLCT",
  "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
}

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 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
  {
    input: {
      model: "dev",
      prompt: "hospital ward in the style of ARCHLLCT",
      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.

pip install replicate

Import the client:

import replicate

Run 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    input={
        "model": "dev",
        "prompt": "hospital ward in the style of ARCHLLCT",
        "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 0xtuba/archillect-lora 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": "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    "input": {
      "model": "dev",
      "prompt": "hospital ward in the style of ARCHLLCT",
      "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": "2024-09-05T10:37:14.774239Z",
  "created_at": "2024-09-05T10:36:48.981000Z",
  "data_removed": false,
  "error": null,
  "id": "0wekf80stnrm60chr7196zt7q8",
  "input": {
    "model": "dev",
    "prompt": "hospital ward in the style of ARCHLLCT",
    "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: 9290\nPrompt: hospital ward in the style of ARCHLLCT\ntxt2img mode\nUsing dev model\nfree=8317040365568\nDownloading weights\n2024-09-05T10:36:49Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpuz9b2g26/weights url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar\n2024-09-05T10:36:50Z | INFO  | [ Complete ] dest=/tmp/tmpuz9b2g26/weights size=\"172 MB\" total_elapsed=1.088s url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar\nDownloaded weights in 1.12s\nLoaded LoRAs in 17.18s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.48it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.94it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.70it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.61it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.56it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.53it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.51it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.50it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.49it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.48it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.47it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.47it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.47it/s]\n 50%|█████     | 14/28 [00:03<00:04,  3.47it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.47it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.46it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.47it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.47it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.47it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.47it/s]\n 75%|███████▌  | 21/28 [00:05<00:02,  3.47it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.47it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.47it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.47it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.47it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.47it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.47it/s]\n100%|██████████| 28/28 [00:08<00:00,  3.47it/s]\n100%|██████████| 28/28 [00:08<00:00,  3.49it/s]",
  "metrics": {
    "predict_time": 25.782560963,
    "total_time": 25.793239
  },
  "output": [
    "https://replicate.delivery/yhqm/fe8EkEMSRFrTC0fFzw1hTPHCfW5oq1wUwdHIeuFjh46T7dObC/out-0.webp"
  ],
  "started_at": "2024-09-05T10:36:48.991678Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/0wekf80stnrm60chr7196zt7q8",
    "cancel": "https://api.replicate.com/v1/predictions/0wekf80stnrm60chr7196zt7q8/cancel"
  },
  "version": "599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42"
}

Generated in

25.8 seconds

0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42

Using seed: 9290
Prompt: hospital ward in the style of ARCHLLCT
txt2img mode
Using dev model
free=8317040365568
Downloading weights
2024-09-05T10:36:49Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpuz9b2g26/weights url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar
2024-09-05T10:36:50Z | INFO  | [ Complete ] dest=/tmp/tmpuz9b2g26/weights size="172 MB" total_elapsed=1.088s url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar
Downloaded weights in 1.12s
Loaded LoRAs in 17.18s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:07,  3.48it/s]
  7%|▋         | 2/28 [00:00<00:06,  3.94it/s]
 11%|█         | 3/28 [00:00<00:06,  3.70it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.61it/s]
 18%|█▊        | 5/28 [00:01<00:06,  3.56it/s]
 21%|██▏       | 6/28 [00:01<00:06,  3.53it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.51it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.50it/s]
 32%|███▏      | 9/28 [00:02<00:05,  3.49it/s]
 36%|███▌      | 10/28 [00:02<00:05,  3.48it/s]
 39%|███▉      | 11/28 [00:03<00:04,  3.47it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.47it/s]
 46%|████▋     | 13/28 [00:03<00:04,  3.47it/s]
 50%|█████     | 14/28 [00:03<00:04,  3.47it/s]
 54%|█████▎    | 15/28 [00:04<00:03,  3.47it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.46it/s]
 61%|██████    | 17/28 [00:04<00:03,  3.47it/s]
 64%|██████▍   | 18/28 [00:05<00:02,  3.47it/s]
 68%|██████▊   | 19/28 [00:05<00:02,  3.47it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.47it/s]
 75%|███████▌  | 21/28 [00:05<00:02,  3.47it/s]
 79%|███████▊  | 22/28 [00:06<00:01,  3.47it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  3.47it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.47it/s]
 89%|████████▉ | 25/28 [00:07<00:00,  3.47it/s]
 93%|█████████▎| 26/28 [00:07<00:00,  3.47it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.47it/s]
100%|██████████| 28/28 [00:08<00:00,  3.47it/s]
100%|██████████| 28/28 [00:08<00:00,  3.49it/s]

Prediction

Model

fa48j6vnqhrm20chr71vzktv6c

Status

Succeeded

Source

Web

Hardware

H100

Total duration

17.8s

Created

9 months ago

Input

model: dev
prompt: serious looking anime female portrait with long dark hair in the style of ARCHLLCT, grayscale, manga
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

{
  "model": "dev",
  "prompt": "serious looking anime female portrait with long dark hair in the style of ARCHLLCT, grayscale, manga",
  "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
}

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 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
  {
    input: {
      model: "dev",
      prompt: "serious looking anime female portrait with long dark hair in the style of ARCHLLCT, grayscale, manga",
      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.

pip install replicate

Import the client:

import replicate

Run 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    input={
        "model": "dev",
        "prompt": "serious looking anime female portrait with long dark hair in the style of ARCHLLCT, grayscale, manga",
        "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 0xtuba/archillect-lora 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": "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    "input": {
      "model": "dev",
      "prompt": "serious looking anime female portrait with long dark hair in the style of ARCHLLCT, grayscale, manga",
      "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": "2024-09-05T10:38:35.809300Z",
  "created_at": "2024-09-05T10:38:18.044000Z",
  "data_removed": false,
  "error": null,
  "id": "fa48j6vnqhrm20chr71vzktv6c",
  "input": {
    "model": "dev",
    "prompt": "serious looking anime female portrait with long dark hair in the style of ARCHLLCT, grayscale, manga",
    "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: 25146\nPrompt: serious looking anime female portrait with long dark hair in the style of ARCHLLCT, grayscale, manga\ntxt2img mode\nUsing dev model\nLoaded LoRAs in 9.26s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.49it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.95it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.72it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.63it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.58it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.55it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.53it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.52it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.51it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.50it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.50it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.50it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.50it/s]\n 50%|█████     | 14/28 [00:03<00:04,  3.50it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.49it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.49it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.49it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.49it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.49it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.49it/s]\n 75%|███████▌  | 21/28 [00:05<00:02,  3.49it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.49it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.49it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.49it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.49it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.49it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.49it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.49it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.52it/s]",
  "metrics": {
    "predict_time": 17.755344913,
    "total_time": 17.7653
  },
  "output": [
    "https://replicate.delivery/yhqm/cvrXppDLCeQTQyNVyMA2siQRf54mutqzB9gY5vlToLwrwzZTA/out-0.webp"
  ],
  "started_at": "2024-09-05T10:38:18.053955Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/fa48j6vnqhrm20chr71vzktv6c",
    "cancel": "https://api.replicate.com/v1/predictions/fa48j6vnqhrm20chr71vzktv6c/cancel"
  },
  "version": "599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42"
}

Generated in

17.8 seconds

0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42

Prediction

Model

5r5sbxn8x5rm40chr75vagwg5r

Status

Succeeded

Source

Web

Hardware

H100

Total duration

25.9s

Created

9 months ago

Input

model: dev
prompt: robot smoking cigarette in the style of ARCHLLCT, grayscale
lora_scale: 0.78
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

{
  "model": "dev",
  "prompt": "robot smoking cigarette in the style of ARCHLLCT, grayscale",
  "lora_scale": 0.78,
  "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
}

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 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
  {
    input: {
      model: "dev",
      prompt: "robot smoking cigarette in the style of ARCHLLCT, grayscale",
      lora_scale: 0.78,
      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.

pip install replicate

Import the client:

import replicate

Run 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    input={
        "model": "dev",
        "prompt": "robot smoking cigarette in the style of ARCHLLCT, grayscale",
        "lora_scale": 0.78,
        "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 0xtuba/archillect-lora 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": "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    "input": {
      "model": "dev",
      "prompt": "robot smoking cigarette in the style of ARCHLLCT, grayscale",
      "lora_scale": 0.78,
      "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": "2024-09-05T10:47:41.303434Z",
  "created_at": "2024-09-05T10:47:15.433000Z",
  "data_removed": false,
  "error": null,
  "id": "5r5sbxn8x5rm40chr75vagwg5r",
  "input": {
    "model": "dev",
    "prompt": "robot smoking cigarette in the style of ARCHLLCT, grayscale",
    "lora_scale": 0.78,
    "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: 11090\nPrompt: robot smoking cigarette in the style of ARCHLLCT, grayscale\ntxt2img mode\nUsing dev model\nLoaded LoRAs in 8.37s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:08,  3.35it/s]\n  7%|▋         | 2/28 [00:00<00:07,  3.69it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.59it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.55it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.52it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.50it/s]\n 25%|██▌       | 7/28 [00:01<00:06,  3.48it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.48it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.47it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.47it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.46it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.47it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.47it/s]\n 50%|█████     | 14/28 [00:04<00:04,  3.47it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.46it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.47it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.47it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.47it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.46it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.46it/s]\n 75%|███████▌  | 21/28 [00:06<00:02,  3.46it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.47it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.47it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.47it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.46it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.46it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.47it/s]\n100%|██████████| 28/28 [00:08<00:00,  3.46it/s]\n100%|██████████| 28/28 [00:08<00:00,  3.48it/s]",
  "metrics": {
    "predict_time": 17.002299305,
    "total_time": 25.870434
  },
  "output": [
    "https://replicate.delivery/yhqm/P41QSqUe5OR8e0uEvAIZtveI4MpmyO8cf0c1gSJuxY40kPnNB/out-0.webp"
  ],
  "started_at": "2024-09-05T10:47:24.301135Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/5r5sbxn8x5rm40chr75vagwg5r",
    "cancel": "https://api.replicate.com/v1/predictions/5r5sbxn8x5rm40chr75vagwg5r/cancel"
  },
  "version": "599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42"
}

Generated in

17.0 seconds

0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42

Prediction

Model

c2jv46d7q5rm40chr778e650x8

Status

Succeeded

Source

Web

Hardware

H100

Total duration

17.8s

Created

9 months ago

Input

model: dev
prompt: waves crashing on a cliff in the style of ARCHLLCT, grayscale
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

{
  "model": "dev",
  "prompt": "waves crashing on a cliff in the style of ARCHLLCT, grayscale",
  "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
}

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 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
  {
    input: {
      model: "dev",
      prompt: "waves crashing on a cliff in the style of ARCHLLCT, grayscale",
      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.

pip install replicate

Import the client:

import replicate

Run 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    input={
        "model": "dev",
        "prompt": "waves crashing on a cliff in the style of ARCHLLCT, grayscale",
        "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 0xtuba/archillect-lora 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": "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    "input": {
      "model": "dev",
      "prompt": "waves crashing on a cliff in the style of ARCHLLCT, grayscale",
      "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": "2024-09-05T10:50:49.536861Z",
  "created_at": "2024-09-05T10:50:31.737000Z",
  "data_removed": false,
  "error": null,
  "id": "c2jv46d7q5rm40chr778e650x8",
  "input": {
    "model": "dev",
    "prompt": "waves crashing on a cliff in the style of ARCHLLCT, grayscale",
    "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: 11890\nPrompt: waves crashing on a cliff in the style of ARCHLLCT, grayscale\ntxt2img mode\nUsing dev model\nfree=8392381210624\nDownloading weights\n2024-09-05T10:50:31Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpfipqocpf/weights url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar\n2024-09-05T10:50:32Z | INFO  | [ Complete ] dest=/tmp/tmpfipqocpf/weights size=\"172 MB\" total_elapsed=1.065s url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar\nDownloaded weights in 1.09s\nLoaded LoRAs in 9.24s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.49it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.95it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.73it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.63it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.58it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.55it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.53it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.52it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.51it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.51it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.50it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.50it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.50it/s]\n 50%|█████     | 14/28 [00:03<00:04,  3.50it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.50it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.50it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.50it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.50it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.50it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.50it/s]\n 75%|███████▌  | 21/28 [00:05<00:02,  3.50it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.50it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.49it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.50it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.49it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.50it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.50it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.49it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.52it/s]",
  "metrics": {
    "predict_time": 17.790276337999998,
    "total_time": 17.799861
  },
  "output": [
    "https://replicate.delivery/yhqm/ofPug2uOlyzzYKDo4meEelHlXjUpiuMSXVONIJjC2sgT4nzmA/out-0.webp"
  ],
  "started_at": "2024-09-05T10:50:31.746584Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/c2jv46d7q5rm40chr778e650x8",
    "cancel": "https://api.replicate.com/v1/predictions/c2jv46d7q5rm40chr778e650x8/cancel"
  },
  "version": "599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42"
}

Generated in

17.8 seconds

0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42

Using seed: 11890
Prompt: waves crashing on a cliff in the style of ARCHLLCT, grayscale
txt2img mode
Using dev model
free=8392381210624
Downloading weights
2024-09-05T10:50:31Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpfipqocpf/weights url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar
2024-09-05T10:50:32Z | INFO  | [ Complete ] dest=/tmp/tmpfipqocpf/weights size="172 MB" total_elapsed=1.065s url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar
Downloaded weights in 1.09s
Loaded LoRAs in 9.24s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:07,  3.49it/s]
  7%|▋         | 2/28 [00:00<00:06,  3.95it/s]
 11%|█         | 3/28 [00:00<00:06,  3.73it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.63it/s]
 18%|█▊        | 5/28 [00:01<00:06,  3.58it/s]
 21%|██▏       | 6/28 [00:01<00:06,  3.55it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.53it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.52it/s]
 32%|███▏      | 9/28 [00:02<00:05,  3.51it/s]
 36%|███▌      | 10/28 [00:02<00:05,  3.51it/s]
 39%|███▉      | 11/28 [00:03<00:04,  3.50it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.50it/s]
 46%|████▋     | 13/28 [00:03<00:04,  3.50it/s]
 50%|█████     | 14/28 [00:03<00:04,  3.50it/s]
 54%|█████▎    | 15/28 [00:04<00:03,  3.50it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.50it/s]
 61%|██████    | 17/28 [00:04<00:03,  3.50it/s]
 64%|██████▍   | 18/28 [00:05<00:02,  3.50it/s]
 68%|██████▊   | 19/28 [00:05<00:02,  3.50it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.50it/s]
 75%|███████▌  | 21/28 [00:05<00:02,  3.50it/s]
 79%|███████▊  | 22/28 [00:06<00:01,  3.50it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  3.49it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.50it/s]
 89%|████████▉ | 25/28 [00:07<00:00,  3.49it/s]
 93%|█████████▎| 26/28 [00:07<00:00,  3.50it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.50it/s]
100%|██████████| 28/28 [00:07<00:00,  3.49it/s]
100%|██████████| 28/28 [00:07<00:00,  3.52it/s]

Prediction

Model

c2jv46d7q5rm40chr778e650x8

Status

Succeeded

Source

Web

Hardware

H100

Total duration

17.8s

Created

9 months ago

Input

model: dev
prompt: waves crashing on a cliff in the style of ARCHLLCT, grayscale
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

{
  "model": "dev",
  "prompt": "waves crashing on a cliff in the style of ARCHLLCT, grayscale",
  "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
}

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 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
  {
    input: {
      model: "dev",
      prompt: "waves crashing on a cliff in the style of ARCHLLCT, grayscale",
      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.

pip install replicate

Import the client:

import replicate

Run 0xtuba/archillect-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    input={
        "model": "dev",
        "prompt": "waves crashing on a cliff in the style of ARCHLLCT, grayscale",
        "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 0xtuba/archillect-lora 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": "0xtuba/archillect-lora:599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42",
    "input": {
      "model": "dev",
      "prompt": "waves crashing on a cliff in the style of ARCHLLCT, grayscale",
      "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": "2024-09-05T10:50:49.536861Z",
  "created_at": "2024-09-05T10:50:31.737000Z",
  "data_removed": false,
  "error": null,
  "id": "c2jv46d7q5rm40chr778e650x8",
  "input": {
    "model": "dev",
    "prompt": "waves crashing on a cliff in the style of ARCHLLCT, grayscale",
    "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: 11890\nPrompt: waves crashing on a cliff in the style of ARCHLLCT, grayscale\ntxt2img mode\nUsing dev model\nfree=8392381210624\nDownloading weights\n2024-09-05T10:50:31Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpfipqocpf/weights url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar\n2024-09-05T10:50:32Z | INFO  | [ Complete ] dest=/tmp/tmpfipqocpf/weights size=\"172 MB\" total_elapsed=1.065s url=https://replicate.delivery/yhqm/mj2J5t3eRv0KRKGQ4C0C6XArbfz0v6Eh9psYsecljJReebObC/trained_model.tar\nDownloaded weights in 1.09s\nLoaded LoRAs in 9.24s\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:07,  3.49it/s]\n  7%|▋         | 2/28 [00:00<00:06,  3.95it/s]\n 11%|█         | 3/28 [00:00<00:06,  3.73it/s]\n 14%|█▍        | 4/28 [00:01<00:06,  3.63it/s]\n 18%|█▊        | 5/28 [00:01<00:06,  3.58it/s]\n 21%|██▏       | 6/28 [00:01<00:06,  3.55it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  3.53it/s]\n 29%|██▊       | 8/28 [00:02<00:05,  3.52it/s]\n 32%|███▏      | 9/28 [00:02<00:05,  3.51it/s]\n 36%|███▌      | 10/28 [00:02<00:05,  3.51it/s]\n 39%|███▉      | 11/28 [00:03<00:04,  3.50it/s]\n 43%|████▎     | 12/28 [00:03<00:04,  3.50it/s]\n 46%|████▋     | 13/28 [00:03<00:04,  3.50it/s]\n 50%|█████     | 14/28 [00:03<00:04,  3.50it/s]\n 54%|█████▎    | 15/28 [00:04<00:03,  3.50it/s]\n 57%|█████▋    | 16/28 [00:04<00:03,  3.50it/s]\n 61%|██████    | 17/28 [00:04<00:03,  3.50it/s]\n 64%|██████▍   | 18/28 [00:05<00:02,  3.50it/s]\n 68%|██████▊   | 19/28 [00:05<00:02,  3.50it/s]\n 71%|███████▏  | 20/28 [00:05<00:02,  3.50it/s]\n 75%|███████▌  | 21/28 [00:05<00:02,  3.50it/s]\n 79%|███████▊  | 22/28 [00:06<00:01,  3.50it/s]\n 82%|████████▏ | 23/28 [00:06<00:01,  3.49it/s]\n 86%|████████▌ | 24/28 [00:06<00:01,  3.50it/s]\n 89%|████████▉ | 25/28 [00:07<00:00,  3.49it/s]\n 93%|█████████▎| 26/28 [00:07<00:00,  3.50it/s]\n 96%|█████████▋| 27/28 [00:07<00:00,  3.50it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.49it/s]\n100%|██████████| 28/28 [00:07<00:00,  3.52it/s]",
  "metrics": {
    "predict_time": 17.790276337999998,
    "total_time": 17.799861
  },
  "output": [
    "https://replicate.delivery/yhqm/ofPug2uOlyzzYKDo4meEelHlXjUpiuMSXVONIJjC2sgT4nzmA/out-0.webp"
  ],
  "started_at": "2024-09-05T10:50:31.746584Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/c2jv46d7q5rm40chr778e650x8",
    "cancel": "https://api.replicate.com/v1/predictions/c2jv46d7q5rm40chr778e650x8/cancel"
  },
  "version": "599ad8df6667caa3ab865345dcb0f98b673a4e4505a8ffc2eea52bd8ba152b42"
}

Generated in

17.8 seconds