width: 1024
height: 1024
prompt: In the style of TOK, a photo of a modern kitchen, white marble, large island
refine: no_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, large island",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "sidhq/vzug:49e0e9370b5361ffd56e753209b065f8d0d55f754cd404784c1b136595f90911",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "In the style of TOK, a photo of a modern kitchen, white marble, large island",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "sidhq/vzug:49e0e9370b5361ffd56e753209b065f8d0d55f754cd404784c1b136595f90911",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, large island",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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.

Run sidhq/vzug 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": "sidhq/vzug:49e0e9370b5361ffd56e753209b065f8d0d55f754cd404784c1b136595f90911",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, large island",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

16.4 seconds

Tweak it Iterate in playground Share Report

Prediction

sidhq/vzug:49e0e9370b5361ffd56e753209b065f8d0d55f754cd404784c1b136595f90911

Model

sidhq/vzug:49e0e937

byq5mf3bswmjliievykj3ee5ea

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

12.3s

Created

almost 2 years ago

Input

width: 1024
height: 1024
prompt: In the style of TOK, a photo of a kitchen, modern, gray, stone, zebra pattern rug
refine: expert_ensemble_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, a photo of a kitchen, modern, gray, stone, zebra pattern rug",
  "refine": "expert_ensemble_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "sidhq/vzug:49e0e9370b5361ffd56e753209b065f8d0d55f754cd404784c1b136595f90911",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "In the style of TOK, a photo of a kitchen, modern, gray, stone, zebra pattern rug",
      refine: "expert_ensemble_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "sidhq/vzug:49e0e9370b5361ffd56e753209b065f8d0d55f754cd404784c1b136595f90911",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "In the style of TOK, a photo of a kitchen, modern, gray, stone, zebra pattern rug",
        "refine": "expert_ensemble_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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.

Run sidhq/vzug 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": "sidhq/vzug:49e0e9370b5361ffd56e753209b065f8d0d55f754cd404784c1b136595f90911",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "In the style of TOK, a photo of a kitchen, modern, gray, stone, zebra pattern rug",
      "refine": "expert_ensemble_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

12.3 seconds

Tweak it Iterate in playground Share Report

Prediction

sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e

Model

sidhq/vzug:418eb37d

d4w5ep3b3xeqlgdvaviwf4q2eu

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

20.8s

Created

almost 2 years ago

Input

width: 1024
height: 1024
prompt: In the style of TOK, a photo of a modern kitchen, zebra carpet, wood floors, front view
refine: no_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, a photo of a modern kitchen, zebra carpet, wood floors, front view",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "In the style of TOK, a photo of a modern kitchen, zebra carpet, wood floors, front view",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "In the style of TOK, a photo of a modern kitchen, zebra carpet, wood floors, front view",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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.

Run sidhq/vzug 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": "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "In the style of TOK, a photo of a modern kitchen, zebra carpet, wood floors, front view",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-12T10:17:10.832329Z",
  "created_at": "2023-11-12T10:16:50.006732Z",
  "data_removed": false,
  "error": null,
  "id": "d4w5ep3b3xeqlgdvaviwf4q2eu",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "In the style of TOK, a photo of a modern kitchen, zebra carpet, wood floors, front view",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 19920\nEnsuring enough disk space...\nFree disk space: 1419574206464\nDownloading weights: https://replicate.delivery/pbxt/JnKBppcawgaKCtkS6JrbIekKWYrfrNHvvQbSLSlqGTfi3KvjA/trained_model.tar\nb'Downloaded 186 MB bytes in 0.315s (591 MB/s)\\nExtracted 186 MB in 0.051s (3.6 GB/s)\\n'\nDownloaded weights in 0.4972960948944092 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: In the style of <s0><s1>, a photo of a modern kitchen, zebra carpet, wood floors, front view\ntxt2img mode\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:13,  3.64it/s]\n  4%|▍         | 2/50 [00:00<00:13,  3.64it/s]\n  6%|▌         | 3/50 [00:00<00:12,  3.65it/s]\n  8%|▊         | 4/50 [00:01<00:12,  3.64it/s]\n 10%|█         | 5/50 [00:01<00:12,  3.64it/s]\n 12%|█▏        | 6/50 [00:01<00:12,  3.64it/s]\n 14%|█▍        | 7/50 [00:01<00:11,  3.64it/s]\n 16%|█▌        | 8/50 [00:02<00:11,  3.64it/s]\n 18%|█▊        | 9/50 [00:02<00:11,  3.64it/s]\n 20%|██        | 10/50 [00:02<00:10,  3.64it/s]\n 22%|██▏       | 11/50 [00:03<00:10,  3.64it/s]\n 24%|██▍       | 12/50 [00:03<00:10,  3.64it/s]\n 26%|██▌       | 13/50 [00:03<00:10,  3.63it/s]\n 28%|██▊       | 14/50 [00:03<00:09,  3.63it/s]\n 30%|███       | 15/50 [00:04<00:09,  3.63it/s]\n 32%|███▏      | 16/50 [00:04<00:09,  3.63it/s]\n 34%|███▍      | 17/50 [00:04<00:09,  3.63it/s]\n 36%|███▌      | 18/50 [00:04<00:08,  3.62it/s]\n 38%|███▊      | 19/50 [00:05<00:08,  3.62it/s]\n 40%|████      | 20/50 [00:05<00:08,  3.62it/s]\n 42%|████▏     | 21/50 [00:05<00:08,  3.62it/s]\n 44%|████▍     | 22/50 [00:06<00:07,  3.62it/s]\n 46%|████▌     | 23/50 [00:06<00:07,  3.62it/s]\n 48%|████▊     | 24/50 [00:06<00:07,  3.62it/s]\n 50%|█████     | 25/50 [00:06<00:06,  3.62it/s]\n 52%|█████▏    | 26/50 [00:07<00:06,  3.62it/s]\n 54%|█████▍    | 27/50 [00:07<00:06,  3.62it/s]\n 56%|█████▌    | 28/50 [00:07<00:06,  3.62it/s]\n 58%|█████▊    | 29/50 [00:07<00:05,  3.62it/s]\n 60%|██████    | 30/50 [00:08<00:05,  3.62it/s]\n 62%|██████▏   | 31/50 [00:08<00:05,  3.62it/s]\n 64%|██████▍   | 32/50 [00:08<00:04,  3.62it/s]\n 66%|██████▌   | 33/50 [00:09<00:04,  3.62it/s]\n 68%|██████▊   | 34/50 [00:09<00:04,  3.62it/s]\n 70%|███████   | 35/50 [00:09<00:04,  3.62it/s]\n 72%|███████▏  | 36/50 [00:09<00:03,  3.62it/s]\n 74%|███████▍  | 37/50 [00:10<00:03,  3.62it/s]\n 76%|███████▌  | 38/50 [00:10<00:03,  3.62it/s]\n 78%|███████▊  | 39/50 [00:10<00:03,  3.62it/s]\n 80%|████████  | 40/50 [00:11<00:02,  3.62it/s]\n 82%|████████▏ | 41/50 [00:11<00:02,  3.62it/s]\n 84%|████████▍ | 42/50 [00:11<00:02,  3.62it/s]\n 86%|████████▌ | 43/50 [00:11<00:01,  3.62it/s]\n 88%|████████▊ | 44/50 [00:12<00:01,  3.62it/s]\n 90%|█████████ | 45/50 [00:12<00:01,  3.62it/s]\n 92%|█████████▏| 46/50 [00:12<00:01,  3.61it/s]\n 94%|█████████▍| 47/50 [00:12<00:00,  3.61it/s]\n 96%|█████████▌| 48/50 [00:13<00:00,  3.62it/s]\n 98%|█████████▊| 49/50 [00:13<00:00,  3.62it/s]\n100%|██████████| 50/50 [00:13<00:00,  3.62it/s]\n100%|██████████| 50/50 [00:13<00:00,  3.62it/s]",
  "metrics": {
    "predict_time": 16.966231,
    "total_time": 20.825597
  },
  "output": [
    "https://replicate.delivery/pbxt/4b2DZgk3ci6EK92efkAzrhuaQAenlzk6wL2n9rA9OfvWCWeOC/out-0.png"
  ],
  "started_at": "2023-11-12T10:16:53.866098Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/d4w5ep3b3xeqlgdvaviwf4q2eu",
    "cancel": "https://api.replicate.com/v1/predictions/d4w5ep3b3xeqlgdvaviwf4q2eu/cancel"
  },
  "version": "418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e"
}

Generated in

17.0 seconds

Tweak it Iterate in playground Share Report

Using seed: 19920
Ensuring enough disk space...
Free disk space: 1419574206464
Downloading weights: https://replicate.delivery/pbxt/JnKBppcawgaKCtkS6JrbIekKWYrfrNHvvQbSLSlqGTfi3KvjA/trained_model.tar
b'Downloaded 186 MB bytes in 0.315s (591 MB/s)\nExtracted 186 MB in 0.051s (3.6 GB/s)\n'
Downloaded weights in 0.4972960948944092 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: In the style of <s0><s1>, a photo of a modern kitchen, zebra carpet, wood floors, front view
txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:13,  3.64it/s]
  4%|▍         | 2/50 [00:00<00:13,  3.64it/s]
  6%|▌         | 3/50 [00:00<00:12,  3.65it/s]
  8%|▊         | 4/50 [00:01<00:12,  3.64it/s]
 10%|█         | 5/50 [00:01<00:12,  3.64it/s]
 12%|█▏        | 6/50 [00:01<00:12,  3.64it/s]
 14%|█▍        | 7/50 [00:01<00:11,  3.64it/s]
 16%|█▌        | 8/50 [00:02<00:11,  3.64it/s]
 18%|█▊        | 9/50 [00:02<00:11,  3.64it/s]
 20%|██        | 10/50 [00:02<00:10,  3.64it/s]
 22%|██▏       | 11/50 [00:03<00:10,  3.64it/s]
 24%|██▍       | 12/50 [00:03<00:10,  3.64it/s]
 26%|██▌       | 13/50 [00:03<00:10,  3.63it/s]
 28%|██▊       | 14/50 [00:03<00:09,  3.63it/s]
 30%|███       | 15/50 [00:04<00:09,  3.63it/s]
 32%|███▏      | 16/50 [00:04<00:09,  3.63it/s]
 34%|███▍      | 17/50 [00:04<00:09,  3.63it/s]
 36%|███▌      | 18/50 [00:04<00:08,  3.62it/s]
 38%|███▊      | 19/50 [00:05<00:08,  3.62it/s]
 40%|████      | 20/50 [00:05<00:08,  3.62it/s]
 42%|████▏     | 21/50 [00:05<00:08,  3.62it/s]
 44%|████▍     | 22/50 [00:06<00:07,  3.62it/s]
 46%|████▌     | 23/50 [00:06<00:07,  3.62it/s]
 48%|████▊     | 24/50 [00:06<00:07,  3.62it/s]
 50%|█████     | 25/50 [00:06<00:06,  3.62it/s]
 52%|█████▏    | 26/50 [00:07<00:06,  3.62it/s]
 54%|█████▍    | 27/50 [00:07<00:06,  3.62it/s]
 56%|█████▌    | 28/50 [00:07<00:06,  3.62it/s]
 58%|█████▊    | 29/50 [00:07<00:05,  3.62it/s]
 60%|██████    | 30/50 [00:08<00:05,  3.62it/s]
 62%|██████▏   | 31/50 [00:08<00:05,  3.62it/s]
 64%|██████▍   | 32/50 [00:08<00:04,  3.62it/s]
 66%|██████▌   | 33/50 [00:09<00:04,  3.62it/s]
 68%|██████▊   | 34/50 [00:09<00:04,  3.62it/s]
 70%|███████   | 35/50 [00:09<00:04,  3.62it/s]
 72%|███████▏  | 36/50 [00:09<00:03,  3.62it/s]
 74%|███████▍  | 37/50 [00:10<00:03,  3.62it/s]
 76%|███████▌  | 38/50 [00:10<00:03,  3.62it/s]
 78%|███████▊  | 39/50 [00:10<00:03,  3.62it/s]
 80%|████████  | 40/50 [00:11<00:02,  3.62it/s]
 82%|████████▏ | 41/50 [00:11<00:02,  3.62it/s]
 84%|████████▍ | 42/50 [00:11<00:02,  3.62it/s]
 86%|████████▌ | 43/50 [00:11<00:01,  3.62it/s]
 88%|████████▊ | 44/50 [00:12<00:01,  3.62it/s]
 90%|█████████ | 45/50 [00:12<00:01,  3.62it/s]
 92%|█████████▏| 46/50 [00:12<00:01,  3.61it/s]
 94%|█████████▍| 47/50 [00:12<00:00,  3.61it/s]
 96%|█████████▌| 48/50 [00:13<00:00,  3.62it/s]
 98%|█████████▊| 49/50 [00:13<00:00,  3.62it/s]
100%|██████████| 50/50 [00:13<00:00,  3.62it/s]
100%|██████████| 50/50 [00:13<00:00,  3.62it/s]

Prediction

sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e

Model

sidhq/vzug:418eb37d

pxtfmnlbbuavg5d7uhkdoxzaza

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

29.0s

Created

almost 2 years ago

Input

image
width: 1024
height: 1024
prompt: In the style of TOK, a photo of modern kitchen, oven, white marble
refine: no_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 50

{
  "image": "https://replicate.delivery/pbxt/JrcvLghAOC7fOcuI0E3O45oFepbaQ1e3ssiQRwDKdpIJR9mZ/kitchen_before.jpeg",
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, a photo of modern kitchen, oven, white marble",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JrcvLghAOC7fOcuI0E3O45oFepbaQ1e3ssiQRwDKdpIJR9mZ/kitchen_before.jpeg",
      width: 1024,
      height: 1024,
      prompt: "In the style of TOK, a photo of modern kitchen, oven, white marble",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    input={
        "image": "https://replicate.delivery/pbxt/JrcvLghAOC7fOcuI0E3O45oFepbaQ1e3ssiQRwDKdpIJR9mZ/kitchen_before.jpeg",
        "width": 1024,
        "height": 1024,
        "prompt": "In the style of TOK, a photo of modern kitchen, oven, white marble",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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.

Run sidhq/vzug 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": "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    "input": {
      "image": "https://replicate.delivery/pbxt/JrcvLghAOC7fOcuI0E3O45oFepbaQ1e3ssiQRwDKdpIJR9mZ/kitchen_before.jpeg",
      "width": 1024,
      "height": 1024,
      "prompt": "In the style of TOK, a photo of modern kitchen, oven, white marble",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-12T12:07:22.719665Z",
  "created_at": "2023-11-12T12:06:53.730319Z",
  "data_removed": false,
  "error": null,
  "id": "pxtfmnlbbuavg5d7uhkdoxzaza",
  "input": {
    "image": "https://replicate.delivery/pbxt/JrcvLghAOC7fOcuI0E3O45oFepbaQ1e3ssiQRwDKdpIJR9mZ/kitchen_before.jpeg",
    "width": 1024,
    "height": 1024,
    "prompt": "In the style of TOK, a photo of modern kitchen, oven, white marble",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 50420\nEnsuring enough disk space...\nFree disk space: 1752990011392\nDownloading weights: https://replicate.delivery/pbxt/JnKBppcawgaKCtkS6JrbIekKWYrfrNHvvQbSLSlqGTfi3KvjA/trained_model.tar\nb'Downloaded 186 MB bytes in 0.227s (818 MB/s)\\nExtracted 186 MB in 0.059s (3.2 GB/s)\\n'\nDownloaded weights in 0.3952369689941406 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: In the style of <s0><s1>, a photo of modern kitchen, oven, white marble\nimg2img mode\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:18,  2.12it/s]\n  5%|▌         | 2/40 [00:00<00:17,  2.14it/s]\n  8%|▊         | 3/40 [00:01<00:17,  2.15it/s]\n 10%|█         | 4/40 [00:01<00:16,  2.15it/s]\n 12%|█▎        | 5/40 [00:02<00:16,  2.15it/s]\n 15%|█▌        | 6/40 [00:02<00:15,  2.15it/s]\n 18%|█▊        | 7/40 [00:03<00:15,  2.16it/s]\n 20%|██        | 8/40 [00:03<00:14,  2.16it/s]\n 22%|██▎       | 9/40 [00:04<00:14,  2.16it/s]\n 25%|██▌       | 10/40 [00:04<00:13,  2.16it/s]\n 28%|██▊       | 11/40 [00:05<00:13,  2.16it/s]\n 30%|███       | 12/40 [00:05<00:12,  2.16it/s]\n 32%|███▎      | 13/40 [00:06<00:12,  2.16it/s]\n 35%|███▌      | 14/40 [00:06<00:12,  2.16it/s]\n 38%|███▊      | 15/40 [00:06<00:11,  2.15it/s]\n 40%|████      | 16/40 [00:07<00:11,  2.16it/s]\n 42%|████▎     | 17/40 [00:07<00:10,  2.15it/s]\n 45%|████▌     | 18/40 [00:08<00:10,  2.15it/s]\n 48%|████▊     | 19/40 [00:08<00:09,  2.15it/s]\n 50%|█████     | 20/40 [00:09<00:09,  2.15it/s]\n 52%|█████▎    | 21/40 [00:09<00:08,  2.15it/s]\n 55%|█████▌    | 22/40 [00:10<00:08,  2.15it/s]\n 57%|█████▊    | 23/40 [00:10<00:07,  2.15it/s]\n 60%|██████    | 24/40 [00:11<00:07,  2.15it/s]\n 62%|██████▎   | 25/40 [00:11<00:06,  2.15it/s]\n 65%|██████▌   | 26/40 [00:12<00:06,  2.15it/s]\n 68%|██████▊   | 27/40 [00:12<00:06,  2.15it/s]\n 70%|███████   | 28/40 [00:13<00:05,  2.15it/s]\n 72%|███████▎  | 29/40 [00:13<00:05,  2.15it/s]\n 75%|███████▌  | 30/40 [00:13<00:04,  2.15it/s]\n 78%|███████▊  | 31/40 [00:14<00:04,  2.15it/s]\n 80%|████████  | 32/40 [00:14<00:03,  2.15it/s]\n 82%|████████▎ | 33/40 [00:15<00:03,  2.15it/s]\n 85%|████████▌ | 34/40 [00:15<00:02,  2.15it/s]\n 88%|████████▊ | 35/40 [00:16<00:02,  2.15it/s]\n 90%|█████████ | 36/40 [00:16<00:01,  2.15it/s]\n 92%|█████████▎| 37/40 [00:17<00:01,  2.15it/s]\n 95%|█████████▌| 38/40 [00:17<00:00,  2.15it/s]\n 98%|█████████▊| 39/40 [00:18<00:00,  2.15it/s]\n100%|██████████| 40/40 [00:18<00:00,  2.15it/s]\n100%|██████████| 40/40 [00:18<00:00,  2.15it/s]",
  "metrics": {
    "predict_time": 23.353435,
    "total_time": 28.989346
  },
  "output": [
    "https://replicate.delivery/pbxt/5yrt90zvS3KpNNozylrMPRpKUCFfwjH1zIK76AxqU698jz7IA/out-0.png"
  ],
  "started_at": "2023-11-12T12:06:59.366230Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/pxtfmnlbbuavg5d7uhkdoxzaza",
    "cancel": "https://api.replicate.com/v1/predictions/pxtfmnlbbuavg5d7uhkdoxzaza/cancel"
  },
  "version": "418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e"
}

Generated in

23.4 seconds

Tweak it Iterate in playground Share Report

Using seed: 50420
Ensuring enough disk space...
Free disk space: 1752990011392
Downloading weights: https://replicate.delivery/pbxt/JnKBppcawgaKCtkS6JrbIekKWYrfrNHvvQbSLSlqGTfi3KvjA/trained_model.tar
b'Downloaded 186 MB bytes in 0.227s (818 MB/s)\nExtracted 186 MB in 0.059s (3.2 GB/s)\n'
Downloaded weights in 0.3952369689941406 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: In the style of <s0><s1>, a photo of modern kitchen, oven, white marble
img2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:18,  2.12it/s]
  5%|▌         | 2/40 [00:00<00:17,  2.14it/s]
  8%|▊         | 3/40 [00:01<00:17,  2.15it/s]
 10%|█         | 4/40 [00:01<00:16,  2.15it/s]
 12%|█▎        | 5/40 [00:02<00:16,  2.15it/s]
 15%|█▌        | 6/40 [00:02<00:15,  2.15it/s]
 18%|█▊        | 7/40 [00:03<00:15,  2.16it/s]
 20%|██        | 8/40 [00:03<00:14,  2.16it/s]
 22%|██▎       | 9/40 [00:04<00:14,  2.16it/s]
 25%|██▌       | 10/40 [00:04<00:13,  2.16it/s]
 28%|██▊       | 11/40 [00:05<00:13,  2.16it/s]
 30%|███       | 12/40 [00:05<00:12,  2.16it/s]
 32%|███▎      | 13/40 [00:06<00:12,  2.16it/s]
 35%|███▌      | 14/40 [00:06<00:12,  2.16it/s]
 38%|███▊      | 15/40 [00:06<00:11,  2.15it/s]
 40%|████      | 16/40 [00:07<00:11,  2.16it/s]
 42%|████▎     | 17/40 [00:07<00:10,  2.15it/s]
 45%|████▌     | 18/40 [00:08<00:10,  2.15it/s]
 48%|████▊     | 19/40 [00:08<00:09,  2.15it/s]
 50%|█████     | 20/40 [00:09<00:09,  2.15it/s]
 52%|█████▎    | 21/40 [00:09<00:08,  2.15it/s]
 55%|█████▌    | 22/40 [00:10<00:08,  2.15it/s]
 57%|█████▊    | 23/40 [00:10<00:07,  2.15it/s]
 60%|██████    | 24/40 [00:11<00:07,  2.15it/s]
 62%|██████▎   | 25/40 [00:11<00:06,  2.15it/s]
 65%|██████▌   | 26/40 [00:12<00:06,  2.15it/s]
 68%|██████▊   | 27/40 [00:12<00:06,  2.15it/s]
 70%|███████   | 28/40 [00:13<00:05,  2.15it/s]
 72%|███████▎  | 29/40 [00:13<00:05,  2.15it/s]
 75%|███████▌  | 30/40 [00:13<00:04,  2.15it/s]
 78%|███████▊  | 31/40 [00:14<00:04,  2.15it/s]
 80%|████████  | 32/40 [00:14<00:03,  2.15it/s]
 82%|████████▎ | 33/40 [00:15<00:03,  2.15it/s]
 85%|████████▌ | 34/40 [00:15<00:02,  2.15it/s]
 88%|████████▊ | 35/40 [00:16<00:02,  2.15it/s]
 90%|█████████ | 36/40 [00:16<00:01,  2.15it/s]
 92%|█████████▎| 37/40 [00:17<00:01,  2.15it/s]
 95%|█████████▌| 38/40 [00:17<00:00,  2.15it/s]
 98%|█████████▊| 39/40 [00:18<00:00,  2.15it/s]
100%|██████████| 40/40 [00:18<00:00,  2.15it/s]
100%|██████████| 40/40 [00:18<00:00,  2.15it/s]

Prediction

sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e

Model

sidhq/vzug:418eb37d

idpmasdbjnsjvaep3atzl6fo3e

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

30.1s

Created

almost 2 years ago

Input

width: 1024
height: 1024
prompt: In the style of TOK, painting of a modern kitchen, oven, vincent van gogh, museum, vase of sunflowers
refine: no_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, painting of a modern kitchen, oven, vincent van gogh, museum, vase of sunflowers",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "In the style of TOK, painting of a modern kitchen, oven, vincent van gogh, museum, vase of sunflowers",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "In the style of TOK, painting of a modern kitchen, oven, vincent van gogh, museum, vase of sunflowers",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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.

Run sidhq/vzug 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": "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "In the style of TOK, painting of a modern kitchen, oven, vincent van gogh, museum, vase of sunflowers",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-12T12:18:14.454180Z",
  "created_at": "2023-11-12T12:17:44.326870Z",
  "data_removed": false,
  "error": null,
  "id": "idpmasdbjnsjvaep3atzl6fo3e",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "In the style of TOK, painting of a modern kitchen, oven, vincent van gogh, museum, vase of sunflowers",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 7894\nskipping loading .. weights already loaded\nPrompt: In the style of <s0><s1>, painting of a modern kitchen, oven, vincent van gogh, museum, vase of sunflowers\ntxt2img mode\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:13,  3.67it/s]\n  4%|▍         | 2/50 [00:00<00:13,  3.67it/s]\n  6%|▌         | 3/50 [00:00<00:12,  3.66it/s]\n  8%|▊         | 4/50 [00:01<00:12,  3.65it/s]\n 10%|█         | 5/50 [00:01<00:12,  3.65it/s]\n 12%|█▏        | 6/50 [00:01<00:12,  3.65it/s]\n 14%|█▍        | 7/50 [00:01<00:11,  3.65it/s]\n 16%|█▌        | 8/50 [00:02<00:11,  3.65it/s]\n 18%|█▊        | 9/50 [00:02<00:11,  3.65it/s]\n 20%|██        | 10/50 [00:02<00:10,  3.65it/s]\n 22%|██▏       | 11/50 [00:03<00:10,  3.65it/s]\n 24%|██▍       | 12/50 [00:03<00:10,  3.65it/s]\n 26%|██▌       | 13/50 [00:03<00:10,  3.65it/s]\n 28%|██▊       | 14/50 [00:03<00:09,  3.65it/s]\n 30%|███       | 15/50 [00:04<00:09,  3.65it/s]\n 32%|███▏      | 16/50 [00:04<00:09,  3.65it/s]\n 34%|███▍      | 17/50 [00:04<00:09,  3.64it/s]\n 36%|███▌      | 18/50 [00:04<00:08,  3.64it/s]\n 38%|███▊      | 19/50 [00:05<00:08,  3.64it/s]\n 40%|████      | 20/50 [00:05<00:08,  3.64it/s]\n 42%|████▏     | 21/50 [00:05<00:07,  3.64it/s]\n 44%|████▍     | 22/50 [00:06<00:07,  3.64it/s]\n 46%|████▌     | 23/50 [00:06<00:07,  3.64it/s]\n 48%|████▊     | 24/50 [00:06<00:07,  3.64it/s]\n 50%|█████     | 25/50 [00:06<00:06,  3.64it/s]\n 52%|█████▏    | 26/50 [00:07<00:06,  3.64it/s]\n 54%|█████▍    | 27/50 [00:07<00:06,  3.64it/s]\n 56%|█████▌    | 28/50 [00:07<00:06,  3.64it/s]\n 58%|█████▊    | 29/50 [00:07<00:05,  3.64it/s]\n 60%|██████    | 30/50 [00:08<00:05,  3.64it/s]\n 62%|██████▏   | 31/50 [00:08<00:05,  3.64it/s]\n 64%|██████▍   | 32/50 [00:08<00:04,  3.64it/s]\n 66%|██████▌   | 33/50 [00:09<00:04,  3.64it/s]\n 68%|██████▊   | 34/50 [00:09<00:04,  3.63it/s]\n 70%|███████   | 35/50 [00:09<00:04,  3.63it/s]\n 72%|███████▏  | 36/50 [00:09<00:03,  3.63it/s]\n 74%|███████▍  | 37/50 [00:10<00:03,  3.63it/s]\n 76%|███████▌  | 38/50 [00:10<00:03,  3.63it/s]\n 78%|███████▊  | 39/50 [00:10<00:03,  3.63it/s]\n 80%|████████  | 40/50 [00:10<00:02,  3.63it/s]\n 82%|████████▏ | 41/50 [00:11<00:02,  3.63it/s]\n 84%|████████▍ | 42/50 [00:11<00:02,  3.64it/s]\n 86%|████████▌ | 43/50 [00:11<00:01,  3.63it/s]\n 88%|████████▊ | 44/50 [00:12<00:01,  3.64it/s]\n 90%|█████████ | 45/50 [00:12<00:01,  3.64it/s]\n 92%|█████████▏| 46/50 [00:12<00:01,  3.64it/s]\n 94%|█████████▍| 47/50 [00:12<00:00,  3.64it/s]\n 96%|█████████▌| 48/50 [00:13<00:00,  3.64it/s]\n 98%|█████████▊| 49/50 [00:13<00:00,  3.64it/s]\n100%|██████████| 50/50 [00:13<00:00,  3.64it/s]\n100%|██████████| 50/50 [00:13<00:00,  3.64it/s]",
  "metrics": {
    "predict_time": 15.907794,
    "total_time": 30.12731
  },
  "output": [
    "https://replicate.delivery/pbxt/Yy2NwuwXq943LJ6EFegbwOx1DzpZEZg6fprsPXJ8mSMFSn3RA/out-0.png"
  ],
  "started_at": "2023-11-12T12:17:58.546386Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/idpmasdbjnsjvaep3atzl6fo3e",
    "cancel": "https://api.replicate.com/v1/predictions/idpmasdbjnsjvaep3atzl6fo3e/cancel"
  },
  "version": "418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e"
}

Generated in

15.9 seconds

Tweak it Iterate in playground Share Report

Using seed: 7894
skipping loading .. weights already loaded
Prompt: In the style of <s0><s1>, painting of a modern kitchen, oven, vincent van gogh, museum, vase of sunflowers
txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:13,  3.67it/s]
  4%|▍         | 2/50 [00:00<00:13,  3.67it/s]
  6%|▌         | 3/50 [00:00<00:12,  3.66it/s]
  8%|▊         | 4/50 [00:01<00:12,  3.65it/s]
 10%|█         | 5/50 [00:01<00:12,  3.65it/s]
 12%|█▏        | 6/50 [00:01<00:12,  3.65it/s]
 14%|█▍        | 7/50 [00:01<00:11,  3.65it/s]
 16%|█▌        | 8/50 [00:02<00:11,  3.65it/s]
 18%|█▊        | 9/50 [00:02<00:11,  3.65it/s]
 20%|██        | 10/50 [00:02<00:10,  3.65it/s]
 22%|██▏       | 11/50 [00:03<00:10,  3.65it/s]
 24%|██▍       | 12/50 [00:03<00:10,  3.65it/s]
 26%|██▌       | 13/50 [00:03<00:10,  3.65it/s]
 28%|██▊       | 14/50 [00:03<00:09,  3.65it/s]
 30%|███       | 15/50 [00:04<00:09,  3.65it/s]
 32%|███▏      | 16/50 [00:04<00:09,  3.65it/s]
 34%|███▍      | 17/50 [00:04<00:09,  3.64it/s]
 36%|███▌      | 18/50 [00:04<00:08,  3.64it/s]
 38%|███▊      | 19/50 [00:05<00:08,  3.64it/s]
 40%|████      | 20/50 [00:05<00:08,  3.64it/s]
 42%|████▏     | 21/50 [00:05<00:07,  3.64it/s]
 44%|████▍     | 22/50 [00:06<00:07,  3.64it/s]
 46%|████▌     | 23/50 [00:06<00:07,  3.64it/s]
 48%|████▊     | 24/50 [00:06<00:07,  3.64it/s]
 50%|█████     | 25/50 [00:06<00:06,  3.64it/s]
 52%|█████▏    | 26/50 [00:07<00:06,  3.64it/s]
 54%|█████▍    | 27/50 [00:07<00:06,  3.64it/s]
 56%|█████▌    | 28/50 [00:07<00:06,  3.64it/s]
 58%|█████▊    | 29/50 [00:07<00:05,  3.64it/s]
 60%|██████    | 30/50 [00:08<00:05,  3.64it/s]
 62%|██████▏   | 31/50 [00:08<00:05,  3.64it/s]
 64%|██████▍   | 32/50 [00:08<00:04,  3.64it/s]
 66%|██████▌   | 33/50 [00:09<00:04,  3.64it/s]
 68%|██████▊   | 34/50 [00:09<00:04,  3.63it/s]
 70%|███████   | 35/50 [00:09<00:04,  3.63it/s]
 72%|███████▏  | 36/50 [00:09<00:03,  3.63it/s]
 74%|███████▍  | 37/50 [00:10<00:03,  3.63it/s]
 76%|███████▌  | 38/50 [00:10<00:03,  3.63it/s]
 78%|███████▊  | 39/50 [00:10<00:03,  3.63it/s]
 80%|████████  | 40/50 [00:10<00:02,  3.63it/s]
 82%|████████▏ | 41/50 [00:11<00:02,  3.63it/s]
 84%|████████▍ | 42/50 [00:11<00:02,  3.64it/s]
 86%|████████▌ | 43/50 [00:11<00:01,  3.63it/s]
 88%|████████▊ | 44/50 [00:12<00:01,  3.64it/s]
 90%|█████████ | 45/50 [00:12<00:01,  3.64it/s]
 92%|█████████▏| 46/50 [00:12<00:01,  3.64it/s]
 94%|█████████▍| 47/50 [00:12<00:00,  3.64it/s]
 96%|█████████▌| 48/50 [00:13<00:00,  3.64it/s]
 98%|█████████▊| 49/50 [00:13<00:00,  3.64it/s]
100%|██████████| 50/50 [00:13<00:00,  3.64it/s]
100%|██████████| 50/50 [00:13<00:00,  3.64it/s]

Prediction

sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e

Model

sidhq/vzug:418eb37d

7wkj2qdbmlnm6mdbnmlhl2mesq

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

10.9s

Created

almost 2 years ago

Input

image
width: 1024
height: 1024
prompt: In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits
refine: no_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 50

{
  "image": "https://replicate.delivery/pbxt/JrdUSkBBfvbSKlUwOcRc07pvch9pBA4upsHu9x6W5NxiS7FF/97568a.jpg",
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JrdUSkBBfvbSKlUwOcRc07pvch9pBA4upsHu9x6W5NxiS7FF/97568a.jpg",
      width: 1024,
      height: 1024,
      prompt: "In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    input={
        "image": "https://replicate.delivery/pbxt/JrdUSkBBfvbSKlUwOcRc07pvch9pBA4upsHu9x6W5NxiS7FF/97568a.jpg",
        "width": 1024,
        "height": 1024,
        "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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.

Run sidhq/vzug 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": "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    "input": {
      "image": "https://replicate.delivery/pbxt/JrdUSkBBfvbSKlUwOcRc07pvch9pBA4upsHu9x6W5NxiS7FF/97568a.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-12T12:44:07.453935Z",
  "created_at": "2023-11-12T12:43:56.527986Z",
  "data_removed": false,
  "error": null,
  "id": "7wkj2qdbmlnm6mdbnmlhl2mesq",
  "input": {
    "image": "https://replicate.delivery/pbxt/JrdUSkBBfvbSKlUwOcRc07pvch9pBA4upsHu9x6W5NxiS7FF/97568a.jpg",
    "width": 1024,
    "height": 1024,
    "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 12398\nEnsuring enough disk space...\nFree disk space: 1710430314496\nDownloading weights: https://replicate.delivery/pbxt/JnKBppcawgaKCtkS6JrbIekKWYrfrNHvvQbSLSlqGTfi3KvjA/trained_model.tar\nb'Downloaded 186 MB bytes in 0.230s (809 MB/s)\\nExtracted 186 MB in 0.064s (2.9 GB/s)\\n'\nDownloaded weights in 0.3894639015197754 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: In the style of <s0><s1>, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits\nimg2img mode\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:08,  4.76it/s]\n  5%|▌         | 2/40 [00:00<00:07,  4.97it/s]\n  8%|▊         | 3/40 [00:00<00:07,  5.05it/s]\n 10%|█         | 4/40 [00:00<00:07,  5.10it/s]\n 12%|█▎        | 5/40 [00:00<00:06,  5.12it/s]\n 15%|█▌        | 6/40 [00:01<00:06,  5.14it/s]\n 18%|█▊        | 7/40 [00:01<00:06,  5.14it/s]\n 20%|██        | 8/40 [00:01<00:06,  5.15it/s]\n 22%|██▎       | 9/40 [00:01<00:06,  5.15it/s]\n 25%|██▌       | 10/40 [00:01<00:05,  5.16it/s]\n 28%|██▊       | 11/40 [00:02<00:05,  5.16it/s]\n 30%|███       | 12/40 [00:02<00:05,  5.16it/s]\n 32%|███▎      | 13/40 [00:02<00:05,  5.16it/s]\n 35%|███▌      | 14/40 [00:02<00:05,  5.15it/s]\n 38%|███▊      | 15/40 [00:02<00:04,  5.15it/s]\n 40%|████      | 16/40 [00:03<00:04,  5.16it/s]\n 42%|████▎     | 17/40 [00:03<00:04,  5.16it/s]\n 45%|████▌     | 18/40 [00:03<00:04,  5.16it/s]\n 48%|████▊     | 19/40 [00:03<00:04,  5.16it/s]\n 50%|█████     | 20/40 [00:03<00:03,  5.16it/s]\n 52%|█████▎    | 21/40 [00:04<00:03,  5.15it/s]\n 55%|█████▌    | 22/40 [00:04<00:03,  5.15it/s]\n 57%|█████▊    | 23/40 [00:04<00:03,  5.15it/s]\n 60%|██████    | 24/40 [00:04<00:03,  5.15it/s]\n 62%|██████▎   | 25/40 [00:04<00:02,  5.15it/s]\n 65%|██████▌   | 26/40 [00:05<00:02,  5.14it/s]\n 68%|██████▊   | 27/40 [00:05<00:02,  5.14it/s]\n 70%|███████   | 28/40 [00:05<00:02,  5.14it/s]\n 72%|███████▎  | 29/40 [00:05<00:02,  5.14it/s]\n 75%|███████▌  | 30/40 [00:05<00:01,  5.14it/s]\n 78%|███████▊  | 31/40 [00:06<00:01,  5.14it/s]\n 80%|████████  | 32/40 [00:06<00:01,  5.13it/s]\n 82%|████████▎ | 33/40 [00:06<00:01,  5.14it/s]\n 85%|████████▌ | 34/40 [00:06<00:01,  5.13it/s]\n 88%|████████▊ | 35/40 [00:06<00:00,  5.13it/s]\n 90%|█████████ | 36/40 [00:07<00:00,  5.13it/s]\n 92%|█████████▎| 37/40 [00:07<00:00,  5.13it/s]\n 95%|█████████▌| 38/40 [00:07<00:00,  5.13it/s]\n 98%|█████████▊| 39/40 [00:07<00:00,  5.12it/s]\n100%|██████████| 40/40 [00:07<00:00,  5.12it/s]\n100%|██████████| 40/40 [00:07<00:00,  5.14it/s]",
  "metrics": {
    "predict_time": 10.99569,
    "total_time": 10.925949
  },
  "output": [
    "https://replicate.delivery/pbxt/le5BVOMAd13NQiYSujhPzWq4PJfrjJWBxp5ZVfYUEx5tUPvjA/out-0.png"
  ],
  "started_at": "2023-11-12T12:43:56.458245Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/7wkj2qdbmlnm6mdbnmlhl2mesq",
    "cancel": "https://api.replicate.com/v1/predictions/7wkj2qdbmlnm6mdbnmlhl2mesq/cancel"
  },
  "version": "418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e"
}

Generated in

11.0 seconds

Tweak it Iterate in playground Share Report

Using seed: 12398
Ensuring enough disk space...
Free disk space: 1710430314496
Downloading weights: https://replicate.delivery/pbxt/JnKBppcawgaKCtkS6JrbIekKWYrfrNHvvQbSLSlqGTfi3KvjA/trained_model.tar
b'Downloaded 186 MB bytes in 0.230s (809 MB/s)\nExtracted 186 MB in 0.064s (2.9 GB/s)\n'
Downloaded weights in 0.3894639015197754 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: In the style of <s0><s1>, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits
img2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:08,  4.76it/s]
  5%|▌         | 2/40 [00:00<00:07,  4.97it/s]
  8%|▊         | 3/40 [00:00<00:07,  5.05it/s]
 10%|█         | 4/40 [00:00<00:07,  5.10it/s]
 12%|█▎        | 5/40 [00:00<00:06,  5.12it/s]
 15%|█▌        | 6/40 [00:01<00:06,  5.14it/s]
 18%|█▊        | 7/40 [00:01<00:06,  5.14it/s]
 20%|██        | 8/40 [00:01<00:06,  5.15it/s]
 22%|██▎       | 9/40 [00:01<00:06,  5.15it/s]
 25%|██▌       | 10/40 [00:01<00:05,  5.16it/s]
 28%|██▊       | 11/40 [00:02<00:05,  5.16it/s]
 30%|███       | 12/40 [00:02<00:05,  5.16it/s]
 32%|███▎      | 13/40 [00:02<00:05,  5.16it/s]
 35%|███▌      | 14/40 [00:02<00:05,  5.15it/s]
 38%|███▊      | 15/40 [00:02<00:04,  5.15it/s]
 40%|████      | 16/40 [00:03<00:04,  5.16it/s]
 42%|████▎     | 17/40 [00:03<00:04,  5.16it/s]
 45%|████▌     | 18/40 [00:03<00:04,  5.16it/s]
 48%|████▊     | 19/40 [00:03<00:04,  5.16it/s]
 50%|█████     | 20/40 [00:03<00:03,  5.16it/s]
 52%|█████▎    | 21/40 [00:04<00:03,  5.15it/s]
 55%|█████▌    | 22/40 [00:04<00:03,  5.15it/s]
 57%|█████▊    | 23/40 [00:04<00:03,  5.15it/s]
 60%|██████    | 24/40 [00:04<00:03,  5.15it/s]
 62%|██████▎   | 25/40 [00:04<00:02,  5.15it/s]
 65%|██████▌   | 26/40 [00:05<00:02,  5.14it/s]
 68%|██████▊   | 27/40 [00:05<00:02,  5.14it/s]
 70%|███████   | 28/40 [00:05<00:02,  5.14it/s]
 72%|███████▎  | 29/40 [00:05<00:02,  5.14it/s]
 75%|███████▌  | 30/40 [00:05<00:01,  5.14it/s]
 78%|███████▊  | 31/40 [00:06<00:01,  5.14it/s]
 80%|████████  | 32/40 [00:06<00:01,  5.13it/s]
 82%|████████▎ | 33/40 [00:06<00:01,  5.14it/s]
 85%|████████▌ | 34/40 [00:06<00:01,  5.13it/s]
 88%|████████▊ | 35/40 [00:06<00:00,  5.13it/s]
 90%|█████████ | 36/40 [00:07<00:00,  5.13it/s]
 92%|█████████▎| 37/40 [00:07<00:00,  5.13it/s]
 95%|█████████▌| 38/40 [00:07<00:00,  5.13it/s]
 98%|█████████▊| 39/40 [00:07<00:00,  5.12it/s]
100%|██████████| 40/40 [00:07<00:00,  5.12it/s]
100%|██████████| 40/40 [00:07<00:00,  5.14it/s]

Prediction

sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e

Model

sidhq/vzug:418eb37d

3yzbuc3bdgzqsdo4udeog43i3q

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

28.4s

Created

almost 2 years ago

Input

image
width: 1024
height: 1024
prompt: In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits
refine: no_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 50

{
  "image": "https://replicate.delivery/pbxt/JrdV2yR7IoOv54mhmis6W7i0YPZ9cWqBk6Es3zjMMy6k6wc1/97568a.jpg",
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JrdV2yR7IoOv54mhmis6W7i0YPZ9cWqBk6Es3zjMMy6k6wc1/97568a.jpg",
      width: 1024,
      height: 1024,
      prompt: "In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    input={
        "image": "https://replicate.delivery/pbxt/JrdV2yR7IoOv54mhmis6W7i0YPZ9cWqBk6Es3zjMMy6k6wc1/97568a.jpg",
        "width": 1024,
        "height": 1024,
        "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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.

Run sidhq/vzug 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": "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    "input": {
      "image": "https://replicate.delivery/pbxt/JrdV2yR7IoOv54mhmis6W7i0YPZ9cWqBk6Es3zjMMy6k6wc1/97568a.jpg",
      "width": 1024,
      "height": 1024,
      "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-12T12:45:01.586645Z",
  "created_at": "2023-11-12T12:44:33.174417Z",
  "data_removed": false,
  "error": null,
  "id": "3yzbuc3bdgzqsdo4udeog43i3q",
  "input": {
    "image": "https://replicate.delivery/pbxt/JrdV2yR7IoOv54mhmis6W7i0YPZ9cWqBk6Es3zjMMy6k6wc1/97568a.jpg",
    "width": 1024,
    "height": 1024,
    "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 7412\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: In the style of <s0><s1>, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits\nimg2img mode\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:08,  4.78it/s]\n  5%|▌         | 2/40 [00:00<00:07,  5.00it/s]\n  8%|▊         | 3/40 [00:00<00:07,  5.07it/s]\n 10%|█         | 4/40 [00:00<00:07,  5.11it/s]\n 12%|█▎        | 5/40 [00:00<00:06,  5.13it/s]\n 15%|█▌        | 6/40 [00:01<00:06,  5.14it/s]\n 18%|█▊        | 7/40 [00:01<00:06,  5.15it/s]\n 20%|██        | 8/40 [00:01<00:06,  5.16it/s]\n 22%|██▎       | 9/40 [00:01<00:06,  5.16it/s]\n 25%|██▌       | 10/40 [00:01<00:05,  5.16it/s]\n 28%|██▊       | 11/40 [00:02<00:05,  5.16it/s]\n 30%|███       | 12/40 [00:02<00:05,  5.16it/s]\n 32%|███▎      | 13/40 [00:02<00:05,  5.17it/s]\n 35%|███▌      | 14/40 [00:02<00:05,  5.17it/s]\n 38%|███▊      | 15/40 [00:02<00:04,  5.17it/s]\n 40%|████      | 16/40 [00:03<00:04,  5.17it/s]\n 42%|████▎     | 17/40 [00:03<00:04,  5.17it/s]\n 45%|████▌     | 18/40 [00:03<00:04,  5.17it/s]\n 48%|████▊     | 19/40 [00:03<00:04,  5.17it/s]\n 50%|█████     | 20/40 [00:03<00:03,  5.17it/s]\n 52%|█████▎    | 21/40 [00:04<00:03,  5.17it/s]\n 55%|█████▌    | 22/40 [00:04<00:03,  5.17it/s]\n 57%|█████▊    | 23/40 [00:04<00:03,  5.17it/s]\n 60%|██████    | 24/40 [00:04<00:03,  5.17it/s]\n 62%|██████▎   | 25/40 [00:04<00:02,  5.17it/s]\n 65%|██████▌   | 26/40 [00:05<00:02,  5.17it/s]\n 68%|██████▊   | 27/40 [00:05<00:02,  5.17it/s]\n 70%|███████   | 28/40 [00:05<00:02,  5.17it/s]\n 72%|███████▎  | 29/40 [00:05<00:02,  5.17it/s]\n 75%|███████▌  | 30/40 [00:05<00:01,  5.17it/s]\n 78%|███████▊  | 31/40 [00:06<00:01,  5.17it/s]\n 80%|████████  | 32/40 [00:06<00:01,  5.16it/s]\n 82%|████████▎ | 33/40 [00:06<00:01,  5.16it/s]\n 85%|████████▌ | 34/40 [00:06<00:01,  5.16it/s]\n 88%|████████▊ | 35/40 [00:06<00:00,  5.15it/s]\n 90%|█████████ | 36/40 [00:06<00:00,  5.15it/s]\n 92%|█████████▎| 37/40 [00:07<00:00,  5.15it/s]\n 95%|█████████▌| 38/40 [00:07<00:00,  5.14it/s]\n 98%|█████████▊| 39/40 [00:07<00:00,  5.14it/s]\n100%|██████████| 40/40 [00:07<00:00,  5.14it/s]\n100%|██████████| 40/40 [00:07<00:00,  5.15it/s]",
  "metrics": {
    "predict_time": 10.623606,
    "total_time": 28.412228
  },
  "output": [
    "https://replicate.delivery/pbxt/mH59DiejElzOQKqtY79Rb1bfb5vOfzXfRUXXtAf0GpUgZ98OC/out-0.png"
  ],
  "started_at": "2023-11-12T12:44:50.963039Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/3yzbuc3bdgzqsdo4udeog43i3q",
    "cancel": "https://api.replicate.com/v1/predictions/3yzbuc3bdgzqsdo4udeog43i3q/cancel"
  },
  "version": "418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e"
}

Generated in

10.6 seconds

Tweak it Iterate in playground Share Report

Using seed: 7412
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: In the style of <s0><s1>, a photo of a modern kitchen, white marble, large island, wooden floors, oven, bowl of fruits
img2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:08,  4.78it/s]
  5%|▌         | 2/40 [00:00<00:07,  5.00it/s]
  8%|▊         | 3/40 [00:00<00:07,  5.07it/s]
 10%|█         | 4/40 [00:00<00:07,  5.11it/s]
 12%|█▎        | 5/40 [00:00<00:06,  5.13it/s]
 15%|█▌        | 6/40 [00:01<00:06,  5.14it/s]
 18%|█▊        | 7/40 [00:01<00:06,  5.15it/s]
 20%|██        | 8/40 [00:01<00:06,  5.16it/s]
 22%|██▎       | 9/40 [00:01<00:06,  5.16it/s]
 25%|██▌       | 10/40 [00:01<00:05,  5.16it/s]
 28%|██▊       | 11/40 [00:02<00:05,  5.16it/s]
 30%|███       | 12/40 [00:02<00:05,  5.16it/s]
 32%|███▎      | 13/40 [00:02<00:05,  5.17it/s]
 35%|███▌      | 14/40 [00:02<00:05,  5.17it/s]
 38%|███▊      | 15/40 [00:02<00:04,  5.17it/s]
 40%|████      | 16/40 [00:03<00:04,  5.17it/s]
 42%|████▎     | 17/40 [00:03<00:04,  5.17it/s]
 45%|████▌     | 18/40 [00:03<00:04,  5.17it/s]
 48%|████▊     | 19/40 [00:03<00:04,  5.17it/s]
 50%|█████     | 20/40 [00:03<00:03,  5.17it/s]
 52%|█████▎    | 21/40 [00:04<00:03,  5.17it/s]
 55%|█████▌    | 22/40 [00:04<00:03,  5.17it/s]
 57%|█████▊    | 23/40 [00:04<00:03,  5.17it/s]
 60%|██████    | 24/40 [00:04<00:03,  5.17it/s]
 62%|██████▎   | 25/40 [00:04<00:02,  5.17it/s]
 65%|██████▌   | 26/40 [00:05<00:02,  5.17it/s]
 68%|██████▊   | 27/40 [00:05<00:02,  5.17it/s]
 70%|███████   | 28/40 [00:05<00:02,  5.17it/s]
 72%|███████▎  | 29/40 [00:05<00:02,  5.17it/s]
 75%|███████▌  | 30/40 [00:05<00:01,  5.17it/s]
 78%|███████▊  | 31/40 [00:06<00:01,  5.17it/s]
 80%|████████  | 32/40 [00:06<00:01,  5.16it/s]
 82%|████████▎ | 33/40 [00:06<00:01,  5.16it/s]
 85%|████████▌ | 34/40 [00:06<00:01,  5.16it/s]
 88%|████████▊ | 35/40 [00:06<00:00,  5.15it/s]
 90%|█████████ | 36/40 [00:06<00:00,  5.15it/s]
 92%|█████████▎| 37/40 [00:07<00:00,  5.15it/s]
 95%|█████████▌| 38/40 [00:07<00:00,  5.14it/s]
 98%|█████████▊| 39/40 [00:07<00:00,  5.14it/s]
100%|██████████| 40/40 [00:07<00:00,  5.14it/s]
100%|██████████| 40/40 [00:07<00:00,  5.15it/s]

Prediction

sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e

Model

sidhq/vzug:418eb37d

nu66kn3bxpezq7igfs7gc64uqi

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

32.0s

Created

almost 2 years ago

Input

image
width: 1024
height: 1024
prompt: In the style of TOK, a photo of a modern kitchen, white marble, wooden floors, oven, bowl of fruits
refine: no_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 50

{
  "image": "https://replicate.delivery/pbxt/JrdXFc1cNVidA2a2iNHo5irzz8NrkMc2avXRAiHLQpAol2Zm/Screenshot%202023-11-12%20at%2013.46.28.png",
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wooden floors, oven, bowl of fruits",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JrdXFc1cNVidA2a2iNHo5irzz8NrkMc2avXRAiHLQpAol2Zm/Screenshot%202023-11-12%20at%2013.46.28.png",
      width: 1024,
      height: 1024,
      prompt: "In the style of TOK, a photo of a modern kitchen, white marble, wooden floors, oven, bowl of fruits",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    input={
        "image": "https://replicate.delivery/pbxt/JrdXFc1cNVidA2a2iNHo5irzz8NrkMc2avXRAiHLQpAol2Zm/Screenshot%202023-11-12%20at%2013.46.28.png",
        "width": 1024,
        "height": 1024,
        "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wooden floors, oven, bowl of fruits",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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.

Run sidhq/vzug 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": "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    "input": {
      "image": "https://replicate.delivery/pbxt/JrdXFc1cNVidA2a2iNHo5irzz8NrkMc2avXRAiHLQpAol2Zm/Screenshot%202023-11-12%20at%2013.46.28.png",
      "width": 1024,
      "height": 1024,
      "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wooden floors, oven, bowl of fruits",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-12T12:47:32.928234Z",
  "created_at": "2023-11-12T12:47:00.878538Z",
  "data_removed": false,
  "error": null,
  "id": "nu66kn3bxpezq7igfs7gc64uqi",
  "input": {
    "image": "https://replicate.delivery/pbxt/JrdXFc1cNVidA2a2iNHo5irzz8NrkMc2avXRAiHLQpAol2Zm/Screenshot%202023-11-12%20at%2013.46.28.png",
    "width": 1024,
    "height": 1024,
    "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wooden floors, oven, bowl of fruits",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 20161\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: In the style of <s0><s1>, a photo of a modern kitchen, white marble, wooden floors, oven, bowl of fruits\nimg2img mode\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:17,  2.21it/s]\n  5%|▌         | 2/40 [00:00<00:17,  2.23it/s]\n  8%|▊         | 3/40 [00:01<00:16,  2.23it/s]\n 10%|█         | 4/40 [00:01<00:16,  2.23it/s]\n 12%|█▎        | 5/40 [00:02<00:15,  2.23it/s]\n 15%|█▌        | 6/40 [00:02<00:15,  2.24it/s]\n 18%|█▊        | 7/40 [00:03<00:14,  2.23it/s]\n 20%|██        | 8/40 [00:03<00:14,  2.23it/s]\n 22%|██▎       | 9/40 [00:04<00:13,  2.23it/s]\n 25%|██▌       | 10/40 [00:04<00:13,  2.23it/s]\n 28%|██▊       | 11/40 [00:04<00:12,  2.23it/s]\n 30%|███       | 12/40 [00:05<00:12,  2.23it/s]\n 32%|███▎      | 13/40 [00:05<00:12,  2.23it/s]\n 35%|███▌      | 14/40 [00:06<00:11,  2.23it/s]\n 38%|███▊      | 15/40 [00:06<00:11,  2.23it/s]\n 40%|████      | 16/40 [00:07<00:10,  2.23it/s]\n 42%|████▎     | 17/40 [00:07<00:10,  2.23it/s]\n 45%|████▌     | 18/40 [00:08<00:09,  2.23it/s]\n 48%|████▊     | 19/40 [00:08<00:09,  2.23it/s]\n 50%|█████     | 20/40 [00:08<00:08,  2.23it/s]\n 52%|█████▎    | 21/40 [00:09<00:08,  2.22it/s]\n 55%|█████▌    | 22/40 [00:09<00:08,  2.22it/s]\n 57%|█████▊    | 23/40 [00:10<00:07,  2.22it/s]\n 60%|██████    | 24/40 [00:10<00:07,  2.22it/s]\n 62%|██████▎   | 25/40 [00:11<00:06,  2.22it/s]\n 65%|██████▌   | 26/40 [00:11<00:06,  2.22it/s]\n 68%|██████▊   | 27/40 [00:12<00:05,  2.22it/s]\n 70%|███████   | 28/40 [00:12<00:05,  2.22it/s]\n 72%|███████▎  | 29/40 [00:13<00:04,  2.22it/s]\n 75%|███████▌  | 30/40 [00:13<00:04,  2.22it/s]\n 78%|███████▊  | 31/40 [00:13<00:04,  2.22it/s]\n 80%|████████  | 32/40 [00:14<00:03,  2.20it/s]\n 82%|████████▎ | 33/40 [00:14<00:03,  2.20it/s]\n 85%|████████▌ | 34/40 [00:15<00:02,  2.21it/s]\n 88%|████████▊ | 35/40 [00:15<00:02,  2.21it/s]\n 90%|█████████ | 36/40 [00:16<00:01,  2.21it/s]\n 92%|█████████▎| 37/40 [00:16<00:01,  2.21it/s]\n 95%|█████████▌| 38/40 [00:17<00:00,  2.21it/s]\n 98%|█████████▊| 39/40 [00:17<00:00,  2.21it/s]\n100%|██████████| 40/40 [00:17<00:00,  2.21it/s]\n100%|██████████| 40/40 [00:18<00:00,  2.22it/s]",
  "metrics": {
    "predict_time": 22.395197,
    "total_time": 32.049696
  },
  "output": [
    "https://replicate.delivery/pbxt/0O08YIbdd6qfHiDf9hifIKvlE7dfqUhpTkjI2f3UYx9ks98OC/out-0.png"
  ],
  "started_at": "2023-11-12T12:47:10.533037Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nu66kn3bxpezq7igfs7gc64uqi",
    "cancel": "https://api.replicate.com/v1/predictions/nu66kn3bxpezq7igfs7gc64uqi/cancel"
  },
  "version": "418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e"
}

Generated in

22.4 seconds

Tweak it Iterate in playground Share Report

Using seed: 20161
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: In the style of <s0><s1>, a photo of a modern kitchen, white marble, wooden floors, oven, bowl of fruits
img2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:17,  2.21it/s]
  5%|▌         | 2/40 [00:00<00:17,  2.23it/s]
  8%|▊         | 3/40 [00:01<00:16,  2.23it/s]
 10%|█         | 4/40 [00:01<00:16,  2.23it/s]
 12%|█▎        | 5/40 [00:02<00:15,  2.23it/s]
 15%|█▌        | 6/40 [00:02<00:15,  2.24it/s]
 18%|█▊        | 7/40 [00:03<00:14,  2.23it/s]
 20%|██        | 8/40 [00:03<00:14,  2.23it/s]
 22%|██▎       | 9/40 [00:04<00:13,  2.23it/s]
 25%|██▌       | 10/40 [00:04<00:13,  2.23it/s]
 28%|██▊       | 11/40 [00:04<00:12,  2.23it/s]
 30%|███       | 12/40 [00:05<00:12,  2.23it/s]
 32%|███▎      | 13/40 [00:05<00:12,  2.23it/s]
 35%|███▌      | 14/40 [00:06<00:11,  2.23it/s]
 38%|███▊      | 15/40 [00:06<00:11,  2.23it/s]
 40%|████      | 16/40 [00:07<00:10,  2.23it/s]
 42%|████▎     | 17/40 [00:07<00:10,  2.23it/s]
 45%|████▌     | 18/40 [00:08<00:09,  2.23it/s]
 48%|████▊     | 19/40 [00:08<00:09,  2.23it/s]
 50%|█████     | 20/40 [00:08<00:08,  2.23it/s]
 52%|█████▎    | 21/40 [00:09<00:08,  2.22it/s]
 55%|█████▌    | 22/40 [00:09<00:08,  2.22it/s]
 57%|█████▊    | 23/40 [00:10<00:07,  2.22it/s]
 60%|██████    | 24/40 [00:10<00:07,  2.22it/s]
 62%|██████▎   | 25/40 [00:11<00:06,  2.22it/s]
 65%|██████▌   | 26/40 [00:11<00:06,  2.22it/s]
 68%|██████▊   | 27/40 [00:12<00:05,  2.22it/s]
 70%|███████   | 28/40 [00:12<00:05,  2.22it/s]
 72%|███████▎  | 29/40 [00:13<00:04,  2.22it/s]
 75%|███████▌  | 30/40 [00:13<00:04,  2.22it/s]
 78%|███████▊  | 31/40 [00:13<00:04,  2.22it/s]
 80%|████████  | 32/40 [00:14<00:03,  2.20it/s]
 82%|████████▎ | 33/40 [00:14<00:03,  2.20it/s]
 85%|████████▌ | 34/40 [00:15<00:02,  2.21it/s]
 88%|████████▊ | 35/40 [00:15<00:02,  2.21it/s]
 90%|█████████ | 36/40 [00:16<00:01,  2.21it/s]
 92%|█████████▎| 37/40 [00:16<00:01,  2.21it/s]
 95%|█████████▌| 38/40 [00:17<00:00,  2.21it/s]
 98%|█████████▊| 39/40 [00:17<00:00,  2.21it/s]
100%|██████████| 40/40 [00:17<00:00,  2.21it/s]
100%|██████████| 40/40 [00:18<00:00,  2.22it/s]

Prediction

sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e

Model

sidhq/vzug:418eb37d

ibdjfclb5islom4652o4lzih2i

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

31.8s

Created

almost 2 years ago

Input

image
width: 1024
height: 1024
prompt: In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, flowers
refine: no_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 50

{
  "image": "https://replicate.delivery/pbxt/JrdZjkIEQV2NdL6pgZt96QcqWc17CQBMh4597dgaT4KBZocy/Screenshot%202023-11-12%20at%2013.46.28.png",
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, flowers",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JrdZjkIEQV2NdL6pgZt96QcqWc17CQBMh4597dgaT4KBZocy/Screenshot%202023-11-12%20at%2013.46.28.png",
      width: 1024,
      height: 1024,
      prompt: "In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, flowers",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    input={
        "image": "https://replicate.delivery/pbxt/JrdZjkIEQV2NdL6pgZt96QcqWc17CQBMh4597dgaT4KBZocy/Screenshot%202023-11-12%20at%2013.46.28.png",
        "width": 1024,
        "height": 1024,
        "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, flowers",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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.

Run sidhq/vzug 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": "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    "input": {
      "image": "https://replicate.delivery/pbxt/JrdZjkIEQV2NdL6pgZt96QcqWc17CQBMh4597dgaT4KBZocy/Screenshot%202023-11-12%20at%2013.46.28.png",
      "width": 1024,
      "height": 1024,
      "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, flowers",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-12T12:50:03.236819Z",
  "created_at": "2023-11-12T12:49:31.397982Z",
  "data_removed": false,
  "error": null,
  "id": "ibdjfclb5islom4652o4lzih2i",
  "input": {
    "image": "https://replicate.delivery/pbxt/JrdZjkIEQV2NdL6pgZt96QcqWc17CQBMh4597dgaT4KBZocy/Screenshot%202023-11-12%20at%2013.46.28.png",
    "width": 1024,
    "height": 1024,
    "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, flowers",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 37800\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: In the style of <s0><s1>, a photo of a modern kitchen, white marble, wood large island with wine cooler, flowers\nimg2img mode\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:17,  2.21it/s]\n  5%|▌         | 2/40 [00:00<00:16,  2.24it/s]\n  8%|▊         | 3/40 [00:01<00:16,  2.24it/s]\n 10%|█         | 4/40 [00:01<00:16,  2.25it/s]\n 12%|█▎        | 5/40 [00:02<00:15,  2.25it/s]\n 15%|█▌        | 6/40 [00:02<00:15,  2.25it/s]\n 18%|█▊        | 7/40 [00:03<00:14,  2.25it/s]\n 20%|██        | 8/40 [00:03<00:14,  2.25it/s]\n 22%|██▎       | 9/40 [00:04<00:13,  2.25it/s]\n 25%|██▌       | 10/40 [00:04<00:13,  2.25it/s]\n 28%|██▊       | 11/40 [00:04<00:12,  2.25it/s]\n 30%|███       | 12/40 [00:05<00:12,  2.25it/s]\n 32%|███▎      | 13/40 [00:05<00:12,  2.25it/s]\n 35%|███▌      | 14/40 [00:06<00:11,  2.25it/s]\n 38%|███▊      | 15/40 [00:06<00:11,  2.25it/s]\n 40%|████      | 16/40 [00:07<00:10,  2.25it/s]\n 42%|████▎     | 17/40 [00:07<00:10,  2.25it/s]\n 45%|████▌     | 18/40 [00:08<00:09,  2.25it/s]\n 48%|████▊     | 19/40 [00:08<00:09,  2.25it/s]\n 50%|█████     | 20/40 [00:08<00:08,  2.25it/s]\n 52%|█████▎    | 21/40 [00:09<00:08,  2.25it/s]\n 55%|█████▌    | 22/40 [00:09<00:08,  2.24it/s]\n 57%|█████▊    | 23/40 [00:10<00:07,  2.24it/s]\n 60%|██████    | 24/40 [00:10<00:07,  2.24it/s]\n 62%|██████▎   | 25/40 [00:11<00:06,  2.24it/s]\n 65%|██████▌   | 26/40 [00:11<00:06,  2.24it/s]\n 68%|██████▊   | 27/40 [00:12<00:05,  2.24it/s]\n 70%|███████   | 28/40 [00:12<00:05,  2.24it/s]\n 72%|███████▎  | 29/40 [00:12<00:04,  2.24it/s]\n 75%|███████▌  | 30/40 [00:13<00:04,  2.24it/s]\n 78%|███████▊  | 31/40 [00:13<00:04,  2.24it/s]\n 80%|████████  | 32/40 [00:14<00:03,  2.23it/s]\n 82%|████████▎ | 33/40 [00:14<00:03,  2.23it/s]\n 85%|████████▌ | 34/40 [00:15<00:02,  2.23it/s]\n 88%|████████▊ | 35/40 [00:15<00:02,  2.23it/s]\n 90%|█████████ | 36/40 [00:16<00:01,  2.23it/s]\n 92%|█████████▎| 37/40 [00:16<00:01,  2.23it/s]\n 95%|█████████▌| 38/40 [00:16<00:00,  2.24it/s]\n 98%|█████████▊| 39/40 [00:17<00:00,  2.24it/s]\n100%|██████████| 40/40 [00:17<00:00,  2.24it/s]\n100%|██████████| 40/40 [00:17<00:00,  2.24it/s]",
  "metrics": {
    "predict_time": 22.220205,
    "total_time": 31.838837
  },
  "output": [
    "https://replicate.delivery/pbxt/3PNPpxdtL2a3F1fJlr6VjKLyV0lO4SdOYYExw7d0LNY93z7IA/out-0.png"
  ],
  "started_at": "2023-11-12T12:49:41.016614Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ibdjfclb5islom4652o4lzih2i",
    "cancel": "https://api.replicate.com/v1/predictions/ibdjfclb5islom4652o4lzih2i/cancel"
  },
  "version": "418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e"
}

Generated in

22.2 seconds

Tweak it Iterate in playground Share Report

Using seed: 37800
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: In the style of <s0><s1>, a photo of a modern kitchen, white marble, wood large island with wine cooler, flowers
img2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:17,  2.21it/s]
  5%|▌         | 2/40 [00:00<00:16,  2.24it/s]
  8%|▊         | 3/40 [00:01<00:16,  2.24it/s]
 10%|█         | 4/40 [00:01<00:16,  2.25it/s]
 12%|█▎        | 5/40 [00:02<00:15,  2.25it/s]
 15%|█▌        | 6/40 [00:02<00:15,  2.25it/s]
 18%|█▊        | 7/40 [00:03<00:14,  2.25it/s]
 20%|██        | 8/40 [00:03<00:14,  2.25it/s]
 22%|██▎       | 9/40 [00:04<00:13,  2.25it/s]
 25%|██▌       | 10/40 [00:04<00:13,  2.25it/s]
 28%|██▊       | 11/40 [00:04<00:12,  2.25it/s]
 30%|███       | 12/40 [00:05<00:12,  2.25it/s]
 32%|███▎      | 13/40 [00:05<00:12,  2.25it/s]
 35%|███▌      | 14/40 [00:06<00:11,  2.25it/s]
 38%|███▊      | 15/40 [00:06<00:11,  2.25it/s]
 40%|████      | 16/40 [00:07<00:10,  2.25it/s]
 42%|████▎     | 17/40 [00:07<00:10,  2.25it/s]
 45%|████▌     | 18/40 [00:08<00:09,  2.25it/s]
 48%|████▊     | 19/40 [00:08<00:09,  2.25it/s]
 50%|█████     | 20/40 [00:08<00:08,  2.25it/s]
 52%|█████▎    | 21/40 [00:09<00:08,  2.25it/s]
 55%|█████▌    | 22/40 [00:09<00:08,  2.24it/s]
 57%|█████▊    | 23/40 [00:10<00:07,  2.24it/s]
 60%|██████    | 24/40 [00:10<00:07,  2.24it/s]
 62%|██████▎   | 25/40 [00:11<00:06,  2.24it/s]
 65%|██████▌   | 26/40 [00:11<00:06,  2.24it/s]
 68%|██████▊   | 27/40 [00:12<00:05,  2.24it/s]
 70%|███████   | 28/40 [00:12<00:05,  2.24it/s]
 72%|███████▎  | 29/40 [00:12<00:04,  2.24it/s]
 75%|███████▌  | 30/40 [00:13<00:04,  2.24it/s]
 78%|███████▊  | 31/40 [00:13<00:04,  2.24it/s]
 80%|████████  | 32/40 [00:14<00:03,  2.23it/s]
 82%|████████▎ | 33/40 [00:14<00:03,  2.23it/s]
 85%|████████▌ | 34/40 [00:15<00:02,  2.23it/s]
 88%|████████▊ | 35/40 [00:15<00:02,  2.23it/s]
 90%|█████████ | 36/40 [00:16<00:01,  2.23it/s]
 92%|█████████▎| 37/40 [00:16<00:01,  2.23it/s]
 95%|█████████▌| 38/40 [00:16<00:00,  2.24it/s]
 98%|█████████▊| 39/40 [00:17<00:00,  2.24it/s]
100%|██████████| 40/40 [00:17<00:00,  2.24it/s]
100%|██████████| 40/40 [00:17<00:00,  2.24it/s]

Prediction

sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e

Model

sidhq/vzug:418eb37d

jqwnr7dbkcuzhhcpw6ih2726vm

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

79.5s

Created

almost 2 years ago

Input

image
width: 1024
height: 1024
prompt: In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, tulips
refine: no_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 4
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 50

{
  "image": "https://replicate.delivery/pbxt/JrdcA5OJnAYsVPkfhL3eqFul26KuhDHxS9wRQb4gf8Yg0N80/Screenshot%202023-11-12%20at%2013.46.28.png",
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, tulips",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 4,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JrdcA5OJnAYsVPkfhL3eqFul26KuhDHxS9wRQb4gf8Yg0N80/Screenshot%202023-11-12%20at%2013.46.28.png",
      width: 1024,
      height: 1024,
      prompt: "In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, tulips",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 4,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    input={
        "image": "https://replicate.delivery/pbxt/JrdcA5OJnAYsVPkfhL3eqFul26KuhDHxS9wRQb4gf8Yg0N80/Screenshot%202023-11-12%20at%2013.46.28.png",
        "width": 1024,
        "height": 1024,
        "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, tulips",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 4,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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.

Run sidhq/vzug 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": "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    "input": {
      "image": "https://replicate.delivery/pbxt/JrdcA5OJnAYsVPkfhL3eqFul26KuhDHxS9wRQb4gf8Yg0N80/Screenshot%202023-11-12%20at%2013.46.28.png",
      "width": 1024,
      "height": 1024,
      "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, tulips",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 4,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-12T12:53:23.877041Z",
  "created_at": "2023-11-12T12:52:04.426291Z",
  "data_removed": false,
  "error": null,
  "id": "jqwnr7dbkcuzhhcpw6ih2726vm",
  "input": {
    "image": "https://replicate.delivery/pbxt/JrdcA5OJnAYsVPkfhL3eqFul26KuhDHxS9wRQb4gf8Yg0N80/Screenshot%202023-11-12%20at%2013.46.28.png",
    "width": 1024,
    "height": 1024,
    "prompt": "In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, tulips",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 4,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 46442\nskipping loading .. weights already loaded\nPrompt: In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, tulips\nimg2img mode\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:01<01:06,  1.71s/it]\n  5%|▌         | 2/40 [00:03<01:04,  1.70s/it]\n  8%|▊         | 3/40 [00:05<01:03,  1.71s/it]\n 10%|█         | 4/40 [00:06<01:01,  1.71s/it]\n 12%|█▎        | 5/40 [00:08<00:59,  1.71s/it]\n 15%|█▌        | 6/40 [00:10<00:58,  1.71s/it]\n 18%|█▊        | 7/40 [00:11<00:56,  1.71s/it]\n 20%|██        | 8/40 [00:13<00:54,  1.71s/it]\n 22%|██▎       | 9/40 [00:15<00:52,  1.71s/it]\n 25%|██▌       | 10/40 [00:17<00:51,  1.71s/it]\n 28%|██▊       | 11/40 [00:18<00:49,  1.71s/it]\n 30%|███       | 12/40 [00:20<00:47,  1.71s/it]\n 32%|███▎      | 13/40 [00:22<00:46,  1.71s/it]\n 35%|███▌      | 14/40 [00:23<00:44,  1.71s/it]\n 38%|███▊      | 15/40 [00:25<00:42,  1.71s/it]\n 40%|████      | 16/40 [00:27<00:41,  1.71s/it]\n 42%|████▎     | 17/40 [00:29<00:39,  1.71s/it]\n 45%|████▌     | 18/40 [00:30<00:37,  1.71s/it]\n 48%|████▊     | 19/40 [00:32<00:36,  1.72s/it]\n 50%|█████     | 20/40 [00:34<00:34,  1.72s/it]\n 52%|█████▎    | 21/40 [00:35<00:32,  1.72s/it]\n 55%|█████▌    | 22/40 [00:37<00:30,  1.72s/it]\n 57%|█████▊    | 23/40 [00:39<00:29,  1.72s/it]\n 60%|██████    | 24/40 [00:41<00:27,  1.72s/it]\n 62%|██████▎   | 25/40 [00:42<00:25,  1.72s/it]\n 65%|██████▌   | 26/40 [00:44<00:24,  1.72s/it]\n 68%|██████▊   | 27/40 [00:46<00:22,  1.72s/it]\n 70%|███████   | 28/40 [00:47<00:20,  1.72s/it]\n 72%|███████▎  | 29/40 [00:49<00:18,  1.72s/it]\n 75%|███████▌  | 30/40 [00:51<00:17,  1.72s/it]\n 78%|███████▊  | 31/40 [00:53<00:15,  1.72s/it]\n 80%|████████  | 32/40 [00:54<00:13,  1.72s/it]\n 82%|████████▎ | 33/40 [00:56<00:12,  1.72s/it]\n 85%|████████▌ | 34/40 [00:58<00:10,  1.72s/it]\n 88%|████████▊ | 35/40 [01:00<00:08,  1.72s/it]\n 90%|█████████ | 36/40 [01:01<00:06,  1.72s/it]\n 92%|█████████▎| 37/40 [01:03<00:05,  1.72s/it]\n 95%|█████████▌| 38/40 [01:05<00:03,  1.72s/it]\n 98%|█████████▊| 39/40 [01:06<00:01,  1.72s/it]\n100%|██████████| 40/40 [01:08<00:00,  1.72s/it]\n100%|██████████| 40/40 [01:08<00:00,  1.72s/it]",
  "metrics": {
    "predict_time": 79.4818,
    "total_time": 79.45075
  },
  "output": [
    "https://replicate.delivery/pbxt/WPhEiffhdWnm1EJz541uEaKDCcCIfszeQG11AmSKF0KHMf8OC/out-0.png",
    "https://replicate.delivery/pbxt/H5ibOfeTlhhaj0VZ2Qgh7dXYrSGeBIwFfVNL69tem3gRYe5dE/out-1.png",
    "https://replicate.delivery/pbxt/tck6zQGAtOaYNddkCb5UhxgfIxeuzFKNrqNozfT4c7zEmPvjA/out-2.png",
    "https://replicate.delivery/pbxt/8RBmFNRLPZ4JM57tVYtXIo37LF4wjcDjaLZQRFQ00q2w85dE/out-3.png"
  ],
  "started_at": "2023-11-12T12:52:04.395241Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/jqwnr7dbkcuzhhcpw6ih2726vm",
    "cancel": "https://api.replicate.com/v1/predictions/jqwnr7dbkcuzhhcpw6ih2726vm/cancel"
  },
  "version": "418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e"
}

Generated in

79.5 seconds

Tweak it Iterate in playground Share Report

Using seed: 46442
skipping loading .. weights already loaded
Prompt: In the style of TOK, a photo of a modern kitchen, white marble, wood large island with wine cooler, tulips
img2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:01<01:06,  1.71s/it]
  5%|▌         | 2/40 [00:03<01:04,  1.70s/it]
  8%|▊         | 3/40 [00:05<01:03,  1.71s/it]
 10%|█         | 4/40 [00:06<01:01,  1.71s/it]
 12%|█▎        | 5/40 [00:08<00:59,  1.71s/it]
 15%|█▌        | 6/40 [00:10<00:58,  1.71s/it]
 18%|█▊        | 7/40 [00:11<00:56,  1.71s/it]
 20%|██        | 8/40 [00:13<00:54,  1.71s/it]
 22%|██▎       | 9/40 [00:15<00:52,  1.71s/it]
 25%|██▌       | 10/40 [00:17<00:51,  1.71s/it]
 28%|██▊       | 11/40 [00:18<00:49,  1.71s/it]
 30%|███       | 12/40 [00:20<00:47,  1.71s/it]
 32%|███▎      | 13/40 [00:22<00:46,  1.71s/it]
 35%|███▌      | 14/40 [00:23<00:44,  1.71s/it]
 38%|███▊      | 15/40 [00:25<00:42,  1.71s/it]
 40%|████      | 16/40 [00:27<00:41,  1.71s/it]
 42%|████▎     | 17/40 [00:29<00:39,  1.71s/it]
 45%|████▌     | 18/40 [00:30<00:37,  1.71s/it]
 48%|████▊     | 19/40 [00:32<00:36,  1.72s/it]
 50%|█████     | 20/40 [00:34<00:34,  1.72s/it]
 52%|█████▎    | 21/40 [00:35<00:32,  1.72s/it]
 55%|█████▌    | 22/40 [00:37<00:30,  1.72s/it]
 57%|█████▊    | 23/40 [00:39<00:29,  1.72s/it]
 60%|██████    | 24/40 [00:41<00:27,  1.72s/it]
 62%|██████▎   | 25/40 [00:42<00:25,  1.72s/it]
 65%|██████▌   | 26/40 [00:44<00:24,  1.72s/it]
 68%|██████▊   | 27/40 [00:46<00:22,  1.72s/it]
 70%|███████   | 28/40 [00:47<00:20,  1.72s/it]
 72%|███████▎  | 29/40 [00:49<00:18,  1.72s/it]
 75%|███████▌  | 30/40 [00:51<00:17,  1.72s/it]
 78%|███████▊  | 31/40 [00:53<00:15,  1.72s/it]
 80%|████████  | 32/40 [00:54<00:13,  1.72s/it]
 82%|████████▎ | 33/40 [00:56<00:12,  1.72s/it]
 85%|████████▌ | 34/40 [00:58<00:10,  1.72s/it]
 88%|████████▊ | 35/40 [01:00<00:08,  1.72s/it]
 90%|█████████ | 36/40 [01:01<00:06,  1.72s/it]
 92%|█████████▎| 37/40 [01:03<00:05,  1.72s/it]
 95%|█████████▌| 38/40 [01:05<00:03,  1.72s/it]
 98%|█████████▊| 39/40 [01:06<00:01,  1.72s/it]
100%|██████████| 40/40 [01:08<00:00,  1.72s/it]
100%|██████████| 40/40 [01:08<00:00,  1.72s/it]

Prediction

sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e

Model

sidhq/vzug:418eb37d

6xuqgvdbqr7scsvlu5owdzfwbe

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

83.6s

Created

almost 2 years ago

Input

image
width: 1024
height: 1024
prompt: In the style of TOK, a photo of a modern kitchen, oven, white marble island
refine: no_refiner
scheduler: K_EULER
lora_scale: 0.6
num_outputs: 4
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt
prompt_strength: 0.8
num_inference_steps: 50

{
  "image": "https://replicate.delivery/pbxt/JrdgbuPDC07wT8PHRXcUhOaaVlpqR6FjWGtAZ1R5tj4LqyAk/Screenshot%202023-11-12%20at%2013.46.28.png",
  "width": 1024,
  "height": 1024,
  "prompt": "In the style of TOK, a photo of a modern kitchen, oven, white marble island",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 4,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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

const output = await replicate.run(
  "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JrdgbuPDC07wT8PHRXcUhOaaVlpqR6FjWGtAZ1R5tj4LqyAk/Screenshot%202023-11-12%20at%2013.46.28.png",
      width: 1024,
      height: 1024,
      prompt: "In the style of TOK, a photo of a modern kitchen, oven, white marble island",
      refine: "no_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.6,
      num_outputs: 4,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

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

output = replicate.run(
    "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    input={
        "image": "https://replicate.delivery/pbxt/JrdgbuPDC07wT8PHRXcUhOaaVlpqR6FjWGtAZ1R5tj4LqyAk/Screenshot%202023-11-12%20at%2013.46.28.png",
        "width": 1024,
        "height": 1024,
        "prompt": "In the style of TOK, a photo of a modern kitchen, oven, white marble island",
        "refine": "no_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.6,
        "num_outputs": 4,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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.

Run sidhq/vzug 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": "sidhq/vzug:418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e",
    "input": {
      "image": "https://replicate.delivery/pbxt/JrdgbuPDC07wT8PHRXcUhOaaVlpqR6FjWGtAZ1R5tj4LqyAk/Screenshot%202023-11-12%20at%2013.46.28.png",
      "width": 1024,
      "height": 1024,
      "prompt": "In the style of TOK, a photo of a modern kitchen, oven, white marble island",
      "refine": "no_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.6,
      "num_outputs": 4,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-12T12:58:09.373010Z",
  "created_at": "2023-11-12T12:56:45.782381Z",
  "data_removed": false,
  "error": null,
  "id": "6xuqgvdbqr7scsvlu5owdzfwbe",
  "input": {
    "image": "https://replicate.delivery/pbxt/JrdgbuPDC07wT8PHRXcUhOaaVlpqR6FjWGtAZ1R5tj4LqyAk/Screenshot%202023-11-12%20at%2013.46.28.png",
    "width": 1024,
    "height": 1024,
    "prompt": "In the style of TOK, a photo of a modern kitchen, oven, white marble island",
    "refine": "no_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.6,
    "num_outputs": 4,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "negative_prompt": "",
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 44019\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: In the style of <s0><s1>, a photo of a modern kitchen, oven, white marble island\nimg2img mode\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:01<01:06,  1.71s/it]\n  5%|▌         | 2/40 [00:03<01:04,  1.70s/it]\n  8%|▊         | 3/40 [00:05<01:02,  1.70s/it]\n 10%|█         | 4/40 [00:06<01:01,  1.70s/it]\n 12%|█▎        | 5/40 [00:08<00:59,  1.70s/it]\n 15%|█▌        | 6/40 [00:10<00:57,  1.70s/it]\n 18%|█▊        | 7/40 [00:11<00:56,  1.70s/it]\n 20%|██        | 8/40 [00:13<00:54,  1.70s/it]\n 22%|██▎       | 9/40 [00:15<00:52,  1.70s/it]\n 25%|██▌       | 10/40 [00:17<00:51,  1.71s/it]\n 28%|██▊       | 11/40 [00:18<00:49,  1.71s/it]\n 30%|███       | 12/40 [00:20<00:47,  1.71s/it]\n 32%|███▎      | 13/40 [00:22<00:46,  1.71s/it]\n 35%|███▌      | 14/40 [00:23<00:44,  1.71s/it]\n 38%|███▊      | 15/40 [00:25<00:42,  1.71s/it]\n 40%|████      | 16/40 [00:27<00:40,  1.71s/it]\n 42%|████▎     | 17/40 [00:28<00:39,  1.71s/it]\n 45%|████▌     | 18/40 [00:30<00:37,  1.71s/it]\n 48%|████▊     | 19/40 [00:32<00:35,  1.71s/it]\n 50%|█████     | 20/40 [00:34<00:34,  1.71s/it]\n 52%|█████▎    | 21/40 [00:35<00:32,  1.71s/it]\n 55%|█████▌    | 22/40 [00:37<00:30,  1.71s/it]\n 57%|█████▊    | 23/40 [00:39<00:29,  1.71s/it]\n 60%|██████    | 24/40 [00:40<00:27,  1.71s/it]\n 62%|██████▎   | 25/40 [00:42<00:25,  1.71s/it]\n 65%|██████▌   | 26/40 [00:44<00:23,  1.71s/it]\n 68%|██████▊   | 27/40 [00:46<00:22,  1.71s/it]\n 70%|███████   | 28/40 [00:47<00:20,  1.71s/it]\n 72%|███████▎  | 29/40 [00:49<00:18,  1.71s/it]\n 75%|███████▌  | 30/40 [00:51<00:17,  1.71s/it]\n 78%|███████▊  | 31/40 [00:52<00:15,  1.71s/it]\n 80%|████████  | 32/40 [00:54<00:13,  1.71s/it]\n 82%|████████▎ | 33/40 [00:56<00:11,  1.71s/it]\n 85%|████████▌ | 34/40 [00:58<00:10,  1.71s/it]\n 88%|████████▊ | 35/40 [00:59<00:08,  1.71s/it]\n 90%|█████████ | 36/40 [01:01<00:06,  1.71s/it]\n 92%|█████████▎| 37/40 [01:03<00:05,  1.71s/it]\n 95%|█████████▌| 38/40 [01:04<00:03,  1.71s/it]\n 98%|█████████▊| 39/40 [01:06<00:01,  1.71s/it]\n100%|██████████| 40/40 [01:08<00:00,  1.71s/it]\n100%|██████████| 40/40 [01:08<00:00,  1.71s/it]",
  "metrics": {
    "predict_time": 78.273005,
    "total_time": 83.590629
  },
  "output": [
    "https://replicate.delivery/pbxt/gGjXsyAf0zVVEK7F7tWVcCuO2xYlsDkaxFjoL3yiKcyv7z7IA/out-0.png",
    "https://replicate.delivery/pbxt/eQRNclymiywyMK9NeVOT2u6PmsYTCS5Pjil5B3FB06Yg3n3RA/out-1.png",
    "https://replicate.delivery/pbxt/Uumee8JcRJjbNUuuAwTfDkBeD9UMf8YvdnTrnnGiskvA8e5dE/out-2.png",
    "https://replicate.delivery/pbxt/kNBGp8jfOP01BKeXTGZd69KLkI9E0I7FifXmAewD0iJGee5dE/out-3.png"
  ],
  "started_at": "2023-11-12T12:56:51.100005Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/6xuqgvdbqr7scsvlu5owdzfwbe",
    "cancel": "https://api.replicate.com/v1/predictions/6xuqgvdbqr7scsvlu5owdzfwbe/cancel"
  },
  "version": "418eb37d8a356b42e3aed25fb8bf44f49324c4a62738e61b6bf760b604f96f9e"
}

Generated in

78.3 seconds

Tweak it Iterate in playground Share Report

Using seed: 44019
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: In the style of <s0><s1>, a photo of a modern kitchen, oven, white marble island
img2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:01<01:06,  1.71s/it]
  5%|▌         | 2/40 [00:03<01:04,  1.70s/it]
  8%|▊         | 3/40 [00:05<01:02,  1.70s/it]
 10%|█         | 4/40 [00:06<01:01,  1.70s/it]
 12%|█▎        | 5/40 [00:08<00:59,  1.70s/it]
 15%|█▌        | 6/40 [00:10<00:57,  1.70s/it]
 18%|█▊        | 7/40 [00:11<00:56,  1.70s/it]
 20%|██        | 8/40 [00:13<00:54,  1.70s/it]
 22%|██▎       | 9/40 [00:15<00:52,  1.70s/it]
 25%|██▌       | 10/40 [00:17<00:51,  1.71s/it]
 28%|██▊       | 11/40 [00:18<00:49,  1.71s/it]
 30%|███       | 12/40 [00:20<00:47,  1.71s/it]
 32%|███▎      | 13/40 [00:22<00:46,  1.71s/it]
 35%|███▌      | 14/40 [00:23<00:44,  1.71s/it]
 38%|███▊      | 15/40 [00:25<00:42,  1.71s/it]
 40%|████      | 16/40 [00:27<00:40,  1.71s/it]
 42%|████▎     | 17/40 [00:28<00:39,  1.71s/it]
 45%|████▌     | 18/40 [00:30<00:37,  1.71s/it]
 48%|████▊     | 19/40 [00:32<00:35,  1.71s/it]
 50%|█████     | 20/40 [00:34<00:34,  1.71s/it]
 52%|█████▎    | 21/40 [00:35<00:32,  1.71s/it]
 55%|█████▌    | 22/40 [00:37<00:30,  1.71s/it]
 57%|█████▊    | 23/40 [00:39<00:29,  1.71s/it]
 60%|██████    | 24/40 [00:40<00:27,  1.71s/it]
 62%|██████▎   | 25/40 [00:42<00:25,  1.71s/it]
 65%|██████▌   | 26/40 [00:44<00:23,  1.71s/it]
 68%|██████▊   | 27/40 [00:46<00:22,  1.71s/it]
 70%|███████   | 28/40 [00:47<00:20,  1.71s/it]
 72%|███████▎  | 29/40 [00:49<00:18,  1.71s/it]
 75%|███████▌  | 30/40 [00:51<00:17,  1.71s/it]
 78%|███████▊  | 31/40 [00:52<00:15,  1.71s/it]
 80%|████████  | 32/40 [00:54<00:13,  1.71s/it]
 82%|████████▎ | 33/40 [00:56<00:11,  1.71s/it]
 85%|████████▌ | 34/40 [00:58<00:10,  1.71s/it]
 88%|████████▊ | 35/40 [00:59<00:08,  1.71s/it]
 90%|█████████ | 36/40 [01:01<00:06,  1.71s/it]
 92%|█████████▎| 37/40 [01:03<00:05,  1.71s/it]
 95%|█████████▌| 38/40 [01:04<00:03,  1.71s/it]
 98%|█████████▊| 39/40 [01:06<00:01,  1.71s/it]
100%|██████████| 40/40 [01:08<00:00,  1.71s/it]
100%|██████████| 40/40 [01:08<00:00,  1.71s/it]

Want to make some of these yourself?

Run this model