Prediction

ID

louy6oezfrdq7dihi4pcuyg5kq

Status

Succeeded

Source

Web

Hardware

–

Total duration

20.9s

Created

over 2 years ago

Input

seed: 3730721345
width: "768"
height: "1024"
prompt: analog style closeup portrait of cowboy bfirsh
scheduler: K_EULER
num_outputs: 1
guidance_scale: 7.5
negative_prompt: blue haze
prompt_strength: 0.8
num_inference_steps: "20"

{
  "seed": 3730721345,
  "width": "768",
  "height": "1024",
  "prompt": "analog style closeup portrait of cowboy bfirsh",
  "scheduler": "K_EULER",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "negative_prompt": "blue haze",
  "prompt_strength": 0.8,
  "num_inference_steps": "20"
}

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 anotherjesse/bfirshbooth-ad using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
  {
    input: {
      seed: 3730721345,
      width: "768",
      height: "1024",
      prompt: "analog style closeup portrait of cowboy bfirsh",
      scheduler: "K_EULER",
      num_outputs: 1,
      guidance_scale: 7.5,
      negative_prompt: "blue haze",
      prompt_strength: 0.8,
      num_inference_steps: "20"
    }
  }
);

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

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

Run anotherjesse/bfirshbooth-ad using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
    input={
        "seed": 3730721345,
        "width": "768",
        "height": "1024",
        "prompt": "analog style closeup portrait of cowboy bfirsh",
        "scheduler": "K_EULER",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "blue haze",
        "prompt_strength": 0.8,
        "num_inference_steps": "20"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run anotherjesse/bfirshbooth-ad 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": "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
    "input": {
      "seed": 3730721345,
      "width": "768",
      "height": "1024",
      "prompt": "analog style closeup portrait of cowboy bfirsh",
      "scheduler": "K_EULER",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "blue haze",
      "prompt_strength": 0.8,
      "num_inference_steps": "20"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-12-22T01:53:08.980880Z",
  "created_at": "2022-12-22T01:52:48.062615Z",
  "data_removed": false,
  "error": null,
  "id": "louy6oezfrdq7dihi4pcuyg5kq",
  "input": {
    "seed": 3730721345,
    "width": "768",
    "height": "1024",
    "prompt": "analog style closeup portrait of cowboy bfirsh",
    "scheduler": "K_EULER",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "negative_prompt": "blue haze",
    "prompt_strength": 0.8,
    "num_inference_steps": "20"
  },
  "logs": "Using seed: 3730721345\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:18,  1.03it/s]\n 10%|█         | 2/20 [00:01<00:17,  1.05it/s]\n 15%|█▌        | 3/20 [00:02<00:16,  1.05it/s]\n 20%|██        | 4/20 [00:03<00:15,  1.05it/s]\n 25%|██▌       | 5/20 [00:04<00:14,  1.05it/s]\n 30%|███       | 6/20 [00:05<00:13,  1.05it/s]\n 35%|███▌      | 7/20 [00:06<00:12,  1.05it/s]\n 40%|████      | 8/20 [00:07<00:11,  1.06it/s]\n 45%|████▌     | 9/20 [00:08<00:10,  1.06it/s]\n 50%|█████     | 10/20 [00:09<00:09,  1.06it/s]\n 55%|█████▌    | 11/20 [00:10<00:08,  1.05it/s]\n 60%|██████    | 12/20 [00:11<00:07,  1.05it/s]\n 65%|██████▌   | 13/20 [00:12<00:06,  1.06it/s]\n 70%|███████   | 14/20 [00:13<00:05,  1.06it/s]\n 75%|███████▌  | 15/20 [00:14<00:04,  1.06it/s]\n 80%|████████  | 16/20 [00:15<00:03,  1.05it/s]\n 85%|████████▌ | 17/20 [00:16<00:02,  1.05it/s]\n 90%|█████████ | 18/20 [00:17<00:01,  1.05it/s]\n 95%|█████████▌| 19/20 [00:18<00:00,  1.05it/s]\n100%|██████████| 20/20 [00:18<00:00,  1.05it/s]\n100%|██████████| 20/20 [00:18<00:00,  1.05it/s]",
  "metrics": {
    "predict_time": 20.882233,
    "total_time": 20.918265
  },
  "output": [
    "https://replicate.delivery/pbxt/UO9RkYQizBLXK9VdS7fZk479u1n4ysW2Y7SAVL6ueQwEqWMQA/out-0.png"
  ],
  "started_at": "2022-12-22T01:52:48.098647Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/louy6oezfrdq7dihi4pcuyg5kq",
    "cancel": "https://api.replicate.com/v1/predictions/louy6oezfrdq7dihi4pcuyg5kq/cancel"
  },
  "version": "37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01"
}

Generated in

20.9 seconds

anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01

Prediction

Model

ID

kbruiyd5jbdlxmm4tdgfn24xda

Status

Succeeded

Source

Web

Hardware

–

Total duration

21.4s

Created

over 2 years ago

Input

seed: 1624745865
width: "768"
height: "1024"
prompt: analog style portrait of cosmonaut bfirsh
scheduler: DPMSolverMultistep
num_outputs: 1
guidance_scale: 7.5
prompt_strength: 0.8
num_inference_steps: "20"

{
  "seed": 1624745865,
  "width": "768",
  "height": "1024",
  "prompt": "analog style portrait of cosmonaut bfirsh",
  "scheduler": "DPMSolverMultistep",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "prompt_strength": 0.8,
  "num_inference_steps": "20"
}

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 anotherjesse/bfirshbooth-ad using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
  {
    input: {
      seed: 1624745865,
      width: "768",
      height: "1024",
      prompt: "analog style portrait of cosmonaut bfirsh",
      scheduler: "DPMSolverMultistep",
      num_outputs: 1,
      guidance_scale: 7.5,
      prompt_strength: 0.8,
      num_inference_steps: "20"
    }
  }
);

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

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

Run anotherjesse/bfirshbooth-ad using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
    input={
        "seed": 1624745865,
        "width": "768",
        "height": "1024",
        "prompt": "analog style portrait of cosmonaut bfirsh",
        "scheduler": "DPMSolverMultistep",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "prompt_strength": 0.8,
        "num_inference_steps": "20"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run anotherjesse/bfirshbooth-ad 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": "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
    "input": {
      "seed": 1624745865,
      "width": "768",
      "height": "1024",
      "prompt": "analog style portrait of cosmonaut bfirsh",
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "prompt_strength": 0.8,
      "num_inference_steps": "20"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-12-22T01:55:03.612342Z",
  "created_at": "2022-12-22T01:54:42.260867Z",
  "data_removed": false,
  "error": null,
  "id": "kbruiyd5jbdlxmm4tdgfn24xda",
  "input": {
    "seed": 1624745865,
    "width": "768",
    "height": "1024",
    "prompt": "analog style portrait of cosmonaut bfirsh",
    "scheduler": "DPMSolverMultistep",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "prompt_strength": 0.8,
    "num_inference_steps": "20"
  },
  "logs": "Using seed: 1624745865\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:18,  1.01it/s]\n 10%|█         | 2/20 [00:01<00:17,  1.04it/s]\n 15%|█▌        | 3/20 [00:02<00:16,  1.05it/s]\n 20%|██        | 4/20 [00:03<00:15,  1.05it/s]\n 25%|██▌       | 5/20 [00:04<00:14,  1.05it/s]\n 30%|███       | 6/20 [00:05<00:13,  1.05it/s]\n 35%|███▌      | 7/20 [00:06<00:12,  1.05it/s]\n 40%|████      | 8/20 [00:07<00:11,  1.05it/s]\n 45%|████▌     | 9/20 [00:08<00:10,  1.05it/s]\n 50%|█████     | 10/20 [00:09<00:09,  1.04it/s]\n 55%|█████▌    | 11/20 [00:10<00:08,  1.04it/s]\n 60%|██████    | 12/20 [00:11<00:07,  1.04it/s]\n 65%|██████▌   | 13/20 [00:12<00:06,  1.04it/s]\n 70%|███████   | 14/20 [00:13<00:05,  1.04it/s]\n 75%|███████▌  | 15/20 [00:14<00:04,  1.03it/s]\n 80%|████████  | 16/20 [00:15<00:03,  1.03it/s]\n 85%|████████▌ | 17/20 [00:16<00:02,  1.03it/s]\n 90%|█████████ | 18/20 [00:17<00:01,  1.03it/s]\n 95%|█████████▌| 19/20 [00:18<00:00,  1.03it/s]\n100%|██████████| 20/20 [00:19<00:00,  1.03it/s]\n100%|██████████| 20/20 [00:19<00:00,  1.04it/s]",
  "metrics": {
    "predict_time": 21.315915,
    "total_time": 21.351475
  },
  "output": [
    "https://replicate.delivery/pbxt/3CUknNPxkr4fVqOCFaC4YIN4fTT9Tk7f2zycD81rLYYsXtYgA/out-0.png"
  ],
  "started_at": "2022-12-22T01:54:42.296427Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/kbruiyd5jbdlxmm4tdgfn24xda",
    "cancel": "https://api.replicate.com/v1/predictions/kbruiyd5jbdlxmm4tdgfn24xda/cancel"
  },
  "version": "37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01"
}

Generated in

21.3 seconds

anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01

Prediction

Model

ID

bwot33mb4zftjmaf3yirgx5tsa

Status

Succeeded

Source

Web

Hardware

–

Total duration

21.1s

Created

over 2 years ago

Input

seed: 1624745865
width: "768"
height: "1024"
prompt: analog style closeup portrait of bfirsh, background futuristic neon at night storefront
scheduler: DPMSolverMultistep
num_outputs: 1
guidance_scale: 7.5
prompt_strength: 0.8
num_inference_steps: "20"

{
  "seed": 1624745865,
  "width": "768",
  "height": "1024",
  "prompt": "analog style closeup portrait of bfirsh, background futuristic neon at night storefront",
  "scheduler": "DPMSolverMultistep",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "prompt_strength": 0.8,
  "num_inference_steps": "20"
}

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 anotherjesse/bfirshbooth-ad using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
  {
    input: {
      seed: 1624745865,
      width: "768",
      height: "1024",
      prompt: "analog style closeup portrait of bfirsh, background futuristic neon at night storefront",
      scheduler: "DPMSolverMultistep",
      num_outputs: 1,
      guidance_scale: 7.5,
      prompt_strength: 0.8,
      num_inference_steps: "20"
    }
  }
);

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

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

Run anotherjesse/bfirshbooth-ad using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
    input={
        "seed": 1624745865,
        "width": "768",
        "height": "1024",
        "prompt": "analog style closeup portrait of bfirsh, background futuristic neon at night storefront",
        "scheduler": "DPMSolverMultistep",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "prompt_strength": 0.8,
        "num_inference_steps": "20"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run anotherjesse/bfirshbooth-ad 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": "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
    "input": {
      "seed": 1624745865,
      "width": "768",
      "height": "1024",
      "prompt": "analog style closeup portrait of bfirsh, background futuristic neon at night storefront",
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "prompt_strength": 0.8,
      "num_inference_steps": "20"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-12-22T01:57:16.589150Z",
  "created_at": "2022-12-22T01:56:55.480911Z",
  "data_removed": false,
  "error": null,
  "id": "bwot33mb4zftjmaf3yirgx5tsa",
  "input": {
    "seed": 1624745865,
    "width": "768",
    "height": "1024",
    "prompt": "analog style closeup portrait of bfirsh, background futuristic neon at night storefront",
    "scheduler": "DPMSolverMultistep",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "prompt_strength": 0.8,
    "num_inference_steps": "20"
  },
  "logs": "Using seed: 1624745865\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:18,  1.02it/s]\n 10%|█         | 2/20 [00:01<00:17,  1.04it/s]\n 15%|█▌        | 3/20 [00:02<00:16,  1.05it/s]\n 20%|██        | 4/20 [00:03<00:15,  1.06it/s]\n 25%|██▌       | 5/20 [00:04<00:14,  1.06it/s]\n 30%|███       | 6/20 [00:05<00:13,  1.06it/s]\n 35%|███▌      | 7/20 [00:06<00:12,  1.06it/s]\n 40%|████      | 8/20 [00:07<00:11,  1.06it/s]\n 45%|████▌     | 9/20 [00:08<00:10,  1.05it/s]\n 50%|█████     | 10/20 [00:09<00:09,  1.05it/s]\n 55%|█████▌    | 11/20 [00:10<00:08,  1.05it/s]\n 60%|██████    | 12/20 [00:11<00:07,  1.05it/s]\n 65%|██████▌   | 13/20 [00:12<00:06,  1.05it/s]\n 70%|███████   | 14/20 [00:13<00:05,  1.05it/s]\n 75%|███████▌  | 15/20 [00:14<00:04,  1.05it/s]\n 80%|████████  | 16/20 [00:15<00:03,  1.04it/s]\n 85%|████████▌ | 17/20 [00:16<00:02,  1.04it/s]\n 90%|█████████ | 18/20 [00:17<00:01,  1.04it/s]\n 95%|█████████▌| 19/20 [00:18<00:00,  1.04it/s]\n100%|██████████| 20/20 [00:19<00:00,  1.03it/s]\n100%|██████████| 20/20 [00:19<00:00,  1.05it/s]",
  "metrics": {
    "predict_time": 21.07372,
    "total_time": 21.108239
  },
  "output": [
    "https://replicate.delivery/pbxt/VUOe88L7Soxf7keelEpjxbfejZ6R3ov9ZgnaCHfblpi09WLGIA/out-0.png"
  ],
  "started_at": "2022-12-22T01:56:55.515430Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/bwot33mb4zftjmaf3yirgx5tsa",
    "cancel": "https://api.replicate.com/v1/predictions/bwot33mb4zftjmaf3yirgx5tsa/cancel"
  },
  "version": "37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01"
}

Generated in

21.1 seconds

anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01

Prediction

Model

ID

gozxv7fmizd2fp7mhale2lazbu

Status

Succeeded

Source

Web

Hardware

–

Total duration

21.1s

Created

over 2 years ago

Input

seed: 1624745865
width: "768"
height: "1024"
prompt: analog style portrait of young bfirsh 1950s hollywood glamour
scheduler: DPMSolverMultistep
num_outputs: 1
guidance_scale: 7.5
negative_prompt: blue haze
prompt_strength: 0.8
num_inference_steps: "20"

{
  "seed": 1624745865,
  "width": "768",
  "height": "1024",
  "prompt": "analog style portrait of young bfirsh 1950s hollywood glamour",
  "scheduler": "DPMSolverMultistep",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "negative_prompt": "blue haze",
  "prompt_strength": 0.8,
  "num_inference_steps": "20"
}

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 anotherjesse/bfirshbooth-ad using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
  {
    input: {
      seed: 1624745865,
      width: "768",
      height: "1024",
      prompt: "analog style portrait of young bfirsh 1950s hollywood glamour",
      scheduler: "DPMSolverMultistep",
      num_outputs: 1,
      guidance_scale: 7.5,
      negative_prompt: "blue haze",
      prompt_strength: 0.8,
      num_inference_steps: "20"
    }
  }
);

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

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

Run anotherjesse/bfirshbooth-ad using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
    input={
        "seed": 1624745865,
        "width": "768",
        "height": "1024",
        "prompt": "analog style portrait of young bfirsh 1950s hollywood glamour",
        "scheduler": "DPMSolverMultistep",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "blue haze",
        "prompt_strength": 0.8,
        "num_inference_steps": "20"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run anotherjesse/bfirshbooth-ad 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": "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
    "input": {
      "seed": 1624745865,
      "width": "768",
      "height": "1024",
      "prompt": "analog style portrait of young bfirsh 1950s hollywood glamour",
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "blue haze",
      "prompt_strength": 0.8,
      "num_inference_steps": "20"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-12-22T01:57:54.960004Z",
  "created_at": "2022-12-22T01:57:33.867043Z",
  "data_removed": false,
  "error": null,
  "id": "gozxv7fmizd2fp7mhale2lazbu",
  "input": {
    "seed": 1624745865,
    "width": "768",
    "height": "1024",
    "prompt": "analog style portrait of young bfirsh 1950s hollywood glamour",
    "scheduler": "DPMSolverMultistep",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "negative_prompt": "blue haze",
    "prompt_strength": 0.8,
    "num_inference_steps": "20"
  },
  "logs": "Using seed: 1624745865\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:18,  1.05it/s]\n 10%|█         | 2/20 [00:01<00:17,  1.06it/s]\n 15%|█▌        | 3/20 [00:02<00:16,  1.06it/s]\n 20%|██        | 4/20 [00:03<00:15,  1.06it/s]\n 25%|██▌       | 5/20 [00:04<00:14,  1.06it/s]\n 30%|███       | 6/20 [00:05<00:13,  1.06it/s]\n 35%|███▌      | 7/20 [00:06<00:12,  1.06it/s]\n 40%|████      | 8/20 [00:07<00:11,  1.06it/s]\n 45%|████▌     | 9/20 [00:08<00:10,  1.06it/s]\n 50%|█████     | 10/20 [00:09<00:09,  1.06it/s]\n 55%|█████▌    | 11/20 [00:10<00:08,  1.06it/s]\n 60%|██████    | 12/20 [00:11<00:07,  1.05it/s]\n 65%|██████▌   | 13/20 [00:12<00:06,  1.05it/s]\n 70%|███████   | 14/20 [00:13<00:05,  1.05it/s]\n 75%|███████▌  | 15/20 [00:14<00:04,  1.05it/s]\n 80%|████████  | 16/20 [00:15<00:03,  1.05it/s]\n 85%|████████▌ | 17/20 [00:16<00:02,  1.05it/s]\n 90%|█████████ | 18/20 [00:17<00:01,  1.05it/s]\n 95%|█████████▌| 19/20 [00:18<00:00,  1.05it/s]\n100%|██████████| 20/20 [00:18<00:00,  1.05it/s]\n100%|██████████| 20/20 [00:18<00:00,  1.05it/s]",
  "metrics": {
    "predict_time": 21.054471,
    "total_time": 21.092961
  },
  "output": [
    "https://replicate.delivery/pbxt/fhgpYv8XPZT3e0Q0lZ7O3XhcG11qjeieMSVhpH7u2ypL6axAB/out-0.png"
  ],
  "started_at": "2022-12-22T01:57:33.905533Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/gozxv7fmizd2fp7mhale2lazbu",
    "cancel": "https://api.replicate.com/v1/predictions/gozxv7fmizd2fp7mhale2lazbu/cancel"
  },
  "version": "37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01"
}

Generated in

21.1 seconds

anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01

Prediction

Model

ID

u5gbl4e4dnbc5czvvu4rjdrloa

Status

Succeeded

Source

Web

Hardware

–

Total duration

21.3s

Created

over 2 years ago

Input

width: "768"
height: "1024"
prompt: analog style film still of bfirsh at a neon convenience storefront
scheduler: DPMSolverMultistep
num_outputs: 1
guidance_scale: 7.5
negative_prompt: blue haze hdr
prompt_strength: 0.8
num_inference_steps: "20"

{
  "width": "768",
  "height": "1024",
  "prompt": "analog style film still of bfirsh at a neon convenience storefront",
  "scheduler": "DPMSolverMultistep",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "negative_prompt": "blue haze hdr",
  "prompt_strength": 0.8,
  "num_inference_steps": "20"
}

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 anotherjesse/bfirshbooth-ad using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
  {
    input: {
      width: "768",
      height: "1024",
      prompt: "analog style film still of bfirsh at a neon convenience storefront",
      scheduler: "DPMSolverMultistep",
      num_outputs: 1,
      guidance_scale: 7.5,
      negative_prompt: "blue haze hdr",
      prompt_strength: 0.8,
      num_inference_steps: "20"
    }
  }
);

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

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

Run anotherjesse/bfirshbooth-ad using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
    input={
        "width": "768",
        "height": "1024",
        "prompt": "analog style film still of bfirsh at a neon convenience storefront",
        "scheduler": "DPMSolverMultistep",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "blue haze hdr",
        "prompt_strength": 0.8,
        "num_inference_steps": "20"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run anotherjesse/bfirshbooth-ad 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": "anotherjesse/bfirshbooth-ad:37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01",
    "input": {
      "width": "768",
      "height": "1024",
      "prompt": "analog style film still of bfirsh at a neon convenience storefront",
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "blue haze hdr",
      "prompt_strength": 0.8,
      "num_inference_steps": "20"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2022-12-22T01:59:06.010414Z",
  "created_at": "2022-12-22T01:58:44.737933Z",
  "data_removed": false,
  "error": null,
  "id": "u5gbl4e4dnbc5czvvu4rjdrloa",
  "input": {
    "width": "768",
    "height": "1024",
    "prompt": "analog style film still of bfirsh at a neon convenience storefront",
    "scheduler": "DPMSolverMultistep",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "negative_prompt": "blue haze hdr",
    "prompt_strength": 0.8,
    "num_inference_steps": "20"
  },
  "logs": "Using seed: 8524\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:18,  1.03it/s]\n 10%|█         | 2/20 [00:01<00:17,  1.03it/s]\n 15%|█▌        | 3/20 [00:02<00:16,  1.04it/s]\n 20%|██        | 4/20 [00:03<00:15,  1.04it/s]\n 25%|██▌       | 5/20 [00:04<00:14,  1.04it/s]\n 30%|███       | 6/20 [00:05<00:13,  1.04it/s]\n 35%|███▌      | 7/20 [00:06<00:12,  1.04it/s]\n 40%|████      | 8/20 [00:07<00:11,  1.04it/s]\n 45%|████▌     | 9/20 [00:08<00:10,  1.04it/s]\n 50%|█████     | 10/20 [00:09<00:09,  1.04it/s]\n 55%|█████▌    | 11/20 [00:10<00:08,  1.04it/s]\n 60%|██████    | 12/20 [00:11<00:07,  1.04it/s]\n 65%|██████▌   | 13/20 [00:12<00:06,  1.04it/s]\n 70%|███████   | 14/20 [00:13<00:05,  1.04it/s]\n 75%|███████▌  | 15/20 [00:14<00:04,  1.04it/s]\n 80%|████████  | 16/20 [00:15<00:03,  1.04it/s]\n 85%|████████▌ | 17/20 [00:16<00:02,  1.04it/s]\n 90%|█████████ | 18/20 [00:17<00:01,  1.04it/s]\n 95%|█████████▌| 19/20 [00:18<00:00,  1.04it/s]\n100%|██████████| 20/20 [00:19<00:00,  1.04it/s]\n100%|██████████| 20/20 [00:19<00:00,  1.04it/s]",
  "metrics": {
    "predict_time": 21.235174,
    "total_time": 21.272481
  },
  "output": [
    "https://replicate.delivery/pbxt/OV4QKO17ka4QIBbRPF5U8MuSYejm1yTTUjolcTLx3kj0XLGIA/out-0.png"
  ],
  "started_at": "2022-12-22T01:58:44.775240Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/u5gbl4e4dnbc5czvvu4rjdrloa",
    "cancel": "https://api.replicate.com/v1/predictions/u5gbl4e4dnbc5czvvu4rjdrloa/cancel"
  },
  "version": "37df7a99a4f34ad0e432f66bd7d0635078e141ea39aa3e9e20414ac69e42eb01"
}

Generated in

21.2 seconds