gileslerockeur/mbappe – Run with an API on Replicate

gileslerockeur / mbappe

Creates stunning images of the best soccer player in the world 💙🤍❤️

Warm

Public
89 runs
L40S
SDXL fine-tune
GitHub

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.

Input prompt

Default: "An astronaut riding a rainbow unicorn"

negative_prompt

string

Shift + Return to add a new line

PSG
Paris Saint Germain
Dark blue jerseyPSG
Paris Saint Germain
Dark blue jersey

Input Negative Prompt

Default: ""

image

file

Input image for img2img or inpaint mode

mask

file

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

width

integer

Width of output image

Default: 1024

height

integer

Height of output image

Default: 1024

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

scheduler

string

scheduler

Default: "K_EULER"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 7.5

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.8

seed

integer

Random seed. Leave blank to randomize the seed

refine

string

Which refine style to use

Default: "no_refiner"

high_noise_frac

number

(minimum: 0, maximum: 1)

For expert_ensemble_refiner, the fraction of noise to use

Default: 0.8

refine_steps

integer

For base_image_refiner, the number of steps to refine, defaults to num_inference_steps

apply_watermark

boolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Default: true

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.6

disable_safety_checker

boolean

Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety

Default: false

Run this model in Node.js with one line of code:

npx create-replicate --model=gileslerockeur/mbappe

or set up a project from scratch

Install Replicate’s Node.js client library

npm install replicate

Set the REPLICATE_API_TOKEN environment variable

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "gileslerockeur/mbappe:b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.",
      refine: "expert_ensemble_refiner",
      scheduler: "K_EULER",
      lora_scale: 0.85,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.95,
      negative_prompt: "PSG\nParis Saint Germain\nDark blue jersey",
      prompt_strength: 0.8,
      num_inference_steps: 100
    }
  }
);
console.log(output);

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

Install Replicate’s Python client library

pip install replicate

Set the REPLICATE_API_TOKEN environment variable

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client

import replicate

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

output = replicate.run(
    "gileslerockeur/mbappe:b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.",
        "refine": "expert_ensemble_refiner",
        "scheduler": "K_EULER",
        "lora_scale": 0.85,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.95,
        "negative_prompt": "PSG\nParis Saint Germain\nDark blue jersey",
        "prompt_strength": 0.8,
        "num_inference_steps": 100
    }
)
print(output)

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

Set the REPLICATE_API_TOKEN environment variable

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run gileslerockeur/mbappe 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": "b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.",
      "refine": "expert_ensemble_refiner",
      "scheduler": "K_EULER",
      "lora_scale": 0.85,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.95,
      "negative_prompt": "PSG\\nParis Saint Germain\\nDark blue jersey",
      "prompt_strength": 0.8,
      "num_inference_steps": 100
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-02-15T23:05:20.098382Z",
  "created_at": "2024-02-15T23:04:45.230786Z",
  "data_removed": false,
  "error": null,
  "id": "guwljetbiwrxasjy64lfyvcyhy",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.",
    "refine": "expert_ensemble_refiner",
    "scheduler": "K_EULER",
    "lora_scale": 0.85,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.95,
    "negative_prompt": "PSG\nParis Saint Germain\nDark blue jersey",
    "prompt_strength": 0.8,
    "num_inference_steps": 100
  },
  "logs": "Using seed: 12659\nEnsuring enough disk space...\nFree disk space: 1585451642880\nDownloading weights: https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar\n2024-02-15T23:04:48Z | INFO  | [ Initiating ] dest=/src/weights-cache/0eda00f750189c5b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar\n2024-02-15T23:04:49Z | INFO  | [ Complete ] dest=/src/weights-cache/0eda00f750189c5b size=\"186 MB\" total_elapsed=0.646s url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar\nb''\nDownloaded weights in 0.8245742321014404 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A photo of <s0><s1>, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.\ntxt2img mode\n  0%|          | 0/95 [00:00<?, ?it/s]\n  1%|          | 1/95 [00:00<00:25,  3.69it/s]\n  2%|▏         | 2/95 [00:00<00:25,  3.68it/s]\n  3%|▎         | 3/95 [00:00<00:25,  3.68it/s]\n  4%|▍         | 4/95 [00:01<00:24,  3.67it/s]\n  5%|▌         | 5/95 [00:01<00:24,  3.67it/s]\n  6%|▋         | 6/95 [00:01<00:24,  3.68it/s]\n  7%|▋         | 7/95 [00:01<00:23,  3.68it/s]\n  8%|▊         | 8/95 [00:02<00:23,  3.67it/s]\n  9%|▉         | 9/95 [00:02<00:23,  3.67it/s]\n 11%|█         | 10/95 [00:02<00:23,  3.67it/s]\n 12%|█▏        | 11/95 [00:02<00:22,  3.67it/s]\n 13%|█▎        | 12/95 [00:03<00:22,  3.67it/s]\n 14%|█▎        | 13/95 [00:03<00:22,  3.67it/s]\n 15%|█▍        | 14/95 [00:03<00:22,  3.67it/s]\n 16%|█▌        | 15/95 [00:04<00:21,  3.67it/s]\n 17%|█▋        | 16/95 [00:04<00:21,  3.67it/s]\n 18%|█▊        | 17/95 [00:04<00:21,  3.67it/s]\n 19%|█▉        | 18/95 [00:04<00:20,  3.67it/s]\n 20%|██        | 19/95 [00:05<00:20,  3.67it/s]\n 21%|██        | 20/95 [00:05<00:20,  3.67it/s]\n 22%|██▏       | 21/95 [00:05<00:20,  3.66it/s]\n 23%|██▎       | 22/95 [00:05<00:19,  3.66it/s]\n 24%|██▍       | 23/95 [00:06<00:19,  3.66it/s]\n 25%|██▌       | 24/95 [00:06<00:19,  3.66it/s]\n 26%|██▋       | 25/95 [00:06<00:19,  3.66it/s]\n 27%|██▋       | 26/95 [00:07<00:18,  3.66it/s]\n 28%|██▊       | 27/95 [00:07<00:18,  3.66it/s]\n 29%|██▉       | 28/95 [00:07<00:18,  3.66it/s]\n 31%|███       | 29/95 [00:07<00:18,  3.66it/s]\n 32%|███▏      | 30/95 [00:08<00:17,  3.66it/s]\n 33%|███▎      | 31/95 [00:08<00:17,  3.65it/s]\n 34%|███▎      | 32/95 [00:08<00:17,  3.66it/s]\n 35%|███▍      | 33/95 [00:09<00:16,  3.65it/s]\n 36%|███▌      | 34/95 [00:09<00:16,  3.65it/s]\n 37%|███▋      | 35/95 [00:09<00:16,  3.65it/s]\n 38%|███▊      | 36/95 [00:09<00:16,  3.65it/s]\n 39%|███▉      | 37/95 [00:10<00:15,  3.65it/s]\n 40%|████      | 38/95 [00:10<00:15,  3.65it/s]\n 41%|████      | 39/95 [00:10<00:15,  3.65it/s]\n 42%|████▏     | 40/95 [00:10<00:15,  3.65it/s]\n 43%|████▎     | 41/95 [00:11<00:14,  3.65it/s]\n 44%|████▍     | 42/95 [00:11<00:14,  3.65it/s]\n 45%|████▌     | 43/95 [00:11<00:14,  3.65it/s]\n 46%|████▋     | 44/95 [00:12<00:13,  3.65it/s]\n 47%|████▋     | 45/95 [00:12<00:13,  3.65it/s]\n 48%|████▊     | 46/95 [00:12<00:13,  3.65it/s]\n 49%|████▉     | 47/95 [00:12<00:13,  3.65it/s]\n 51%|█████     | 48/95 [00:13<00:12,  3.65it/s]\n 52%|█████▏    | 49/95 [00:13<00:12,  3.65it/s]\n 53%|█████▎    | 50/95 [00:13<00:12,  3.65it/s]\n 54%|█████▎    | 51/95 [00:13<00:12,  3.65it/s]\n 55%|█████▍    | 52/95 [00:14<00:11,  3.64it/s]\n 56%|█████▌    | 53/95 [00:14<00:11,  3.64it/s]\n 57%|█████▋    | 54/95 [00:14<00:11,  3.65it/s]\n 58%|█████▊    | 55/95 [00:15<00:10,  3.65it/s]\n 59%|█████▉    | 56/95 [00:15<00:10,  3.64it/s]\n 60%|██████    | 57/95 [00:15<00:10,  3.64it/s]\n 61%|██████    | 58/95 [00:15<00:10,  3.64it/s]\n 62%|██████▏   | 59/95 [00:16<00:09,  3.64it/s]\n 63%|██████▎   | 60/95 [00:16<00:09,  3.65it/s]\n 64%|██████▍   | 61/95 [00:16<00:09,  3.64it/s]\n 65%|██████▌   | 62/95 [00:16<00:09,  3.64it/s]\n 66%|██████▋   | 63/95 [00:17<00:08,  3.64it/s]\n 67%|██████▋   | 64/95 [00:17<00:08,  3.64it/s]\n 68%|██████▊   | 65/95 [00:17<00:08,  3.64it/s]\n 69%|██████▉   | 66/95 [00:18<00:07,  3.64it/s]\n 71%|███████   | 67/95 [00:18<00:07,  3.64it/s]\n 72%|███████▏  | 68/95 [00:18<00:07,  3.64it/s]\n 73%|███████▎  | 69/95 [00:18<00:07,  3.64it/s]\n 74%|███████▎  | 70/95 [00:19<00:06,  3.64it/s]\n 75%|███████▍  | 71/95 [00:19<00:06,  3.64it/s]\n 76%|███████▌  | 72/95 [00:19<00:06,  3.64it/s]\n 77%|███████▋  | 73/95 [00:19<00:06,  3.64it/s]\n 78%|███████▊  | 74/95 [00:20<00:05,  3.64it/s]\n 79%|███████▉  | 75/95 [00:20<00:05,  3.64it/s]\n 80%|████████  | 76/95 [00:20<00:05,  3.64it/s]\n 81%|████████  | 77/95 [00:21<00:04,  3.64it/s]\n 82%|████████▏ | 78/95 [00:21<00:04,  3.63it/s]\n 83%|████████▎ | 79/95 [00:21<00:04,  3.64it/s]\n 84%|████████▍ | 80/95 [00:21<00:04,  3.64it/s]\n 85%|████████▌ | 81/95 [00:22<00:03,  3.64it/s]\n 86%|████████▋ | 82/95 [00:22<00:03,  3.64it/s]\n 87%|████████▋ | 83/95 [00:22<00:03,  3.63it/s]\n 88%|████████▊ | 84/95 [00:23<00:03,  3.63it/s]\n 89%|████████▉ | 85/95 [00:23<00:02,  3.64it/s]\n 91%|█████████ | 86/95 [00:23<00:02,  3.64it/s]\n 92%|█████████▏| 87/95 [00:23<00:02,  3.64it/s]\n 93%|█████████▎| 88/95 [00:24<00:01,  3.64it/s]\n 94%|█████████▎| 89/95 [00:24<00:01,  3.64it/s]\n 95%|█████████▍| 90/95 [00:24<00:01,  3.64it/s]\n 96%|█████████▌| 91/95 [00:24<00:01,  3.64it/s]\n 97%|█████████▋| 92/95 [00:25<00:00,  3.64it/s]\n 98%|█████████▊| 93/95 [00:25<00:00,  3.64it/s]\n 99%|█████████▉| 94/95 [00:25<00:00,  3.64it/s]\n100%|██████████| 95/95 [00:26<00:00,  3.64it/s]\n100%|██████████| 95/95 [00:26<00:00,  3.65it/s]\n  0%|          | 0/5 [00:00<?, ?it/s]\n 20%|██        | 1/5 [00:00<00:00,  4.25it/s]\n 40%|████      | 2/5 [00:00<00:00,  4.22it/s]\n 60%|██████    | 3/5 [00:00<00:00,  4.21it/s]\n 80%|████████  | 4/5 [00:00<00:00,  4.21it/s]\n100%|██████████| 5/5 [00:01<00:00,  4.20it/s]\n100%|██████████| 5/5 [00:01<00:00,  4.21it/s]",
  "metrics": {
    "predict_time": 31.235973,
    "total_time": 34.867596
  },
  "output": [
    "https://replicate.delivery/pbxt/OvDwcCq58YJIM5xf0JsKtlXUdrlcw9lM14q7n8AejPuuqEXSA/out-0.png"
  ],
  "started_at": "2024-02-15T23:04:48.862409Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/guwljetbiwrxasjy64lfyvcyhy",
    "cancel": "https://api.replicate.com/v1/predictions/guwljetbiwrxasjy64lfyvcyhy/cancel"
  },
  "version": "b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450"
}

Generated in

31.2 seconds

Tweak itReport

Using seed: 12659
Ensuring enough disk space...
Free disk space: 1585451642880
Downloading weights: https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar
2024-02-15T23:04:48Z | INFO  | [ Initiating ] dest=/src/weights-cache/0eda00f750189c5b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar
2024-02-15T23:04:49Z | INFO  | [ Complete ] dest=/src/weights-cache/0eda00f750189c5b size="186 MB" total_elapsed=0.646s url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar
b''
Downloaded weights in 0.8245742321014404 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: A photo of <s0><s1>, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.
txt2img mode
  0%|          | 0/95 [00:00<?, ?it/s]
  1%|          | 1/95 [00:00<00:25,  3.69it/s]
  2%|▏         | 2/95 [00:00<00:25,  3.68it/s]
  3%|▎         | 3/95 [00:00<00:25,  3.68it/s]
  4%|▍         | 4/95 [00:01<00:24,  3.67it/s]
  5%|▌         | 5/95 [00:01<00:24,  3.67it/s]
  6%|▋         | 6/95 [00:01<00:24,  3.68it/s]
  7%|▋         | 7/95 [00:01<00:23,  3.68it/s]
  8%|▊         | 8/95 [00:02<00:23,  3.67it/s]
  9%|▉         | 9/95 [00:02<00:23,  3.67it/s]
 11%|█         | 10/95 [00:02<00:23,  3.67it/s]
 12%|█▏        | 11/95 [00:02<00:22,  3.67it/s]
 13%|█▎        | 12/95 [00:03<00:22,  3.67it/s]
 14%|█▎        | 13/95 [00:03<00:22,  3.67it/s]
 15%|█▍        | 14/95 [00:03<00:22,  3.67it/s]
 16%|█▌        | 15/95 [00:04<00:21,  3.67it/s]
 17%|█▋        | 16/95 [00:04<00:21,  3.67it/s]
 18%|█▊        | 17/95 [00:04<00:21,  3.67it/s]
 19%|█▉        | 18/95 [00:04<00:20,  3.67it/s]
 20%|██        | 19/95 [00:05<00:20,  3.67it/s]
 21%|██        | 20/95 [00:05<00:20,  3.67it/s]
 22%|██▏       | 21/95 [00:05<00:20,  3.66it/s]
 23%|██▎       | 22/95 [00:05<00:19,  3.66it/s]
 24%|██▍       | 23/95 [00:06<00:19,  3.66it/s]
 25%|██▌       | 24/95 [00:06<00:19,  3.66it/s]
 26%|██▋       | 25/95 [00:06<00:19,  3.66it/s]
 27%|██▋       | 26/95 [00:07<00:18,  3.66it/s]
 28%|██▊       | 27/95 [00:07<00:18,  3.66it/s]
 29%|██▉       | 28/95 [00:07<00:18,  3.66it/s]
 31%|███       | 29/95 [00:07<00:18,  3.66it/s]
 32%|███▏      | 30/95 [00:08<00:17,  3.66it/s]
 33%|███▎      | 31/95 [00:08<00:17,  3.65it/s]
 34%|███▎      | 32/95 [00:08<00:17,  3.66it/s]
 35%|███▍      | 33/95 [00:09<00:16,  3.65it/s]
 36%|███▌      | 34/95 [00:09<00:16,  3.65it/s]
 37%|███▋      | 35/95 [00:09<00:16,  3.65it/s]
 38%|███▊      | 36/95 [00:09<00:16,  3.65it/s]
 39%|███▉      | 37/95 [00:10<00:15,  3.65it/s]
 40%|████      | 38/95 [00:10<00:15,  3.65it/s]
 41%|████      | 39/95 [00:10<00:15,  3.65it/s]
 42%|████▏     | 40/95 [00:10<00:15,  3.65it/s]
 43%|████▎     | 41/95 [00:11<00:14,  3.65it/s]
 44%|████▍     | 42/95 [00:11<00:14,  3.65it/s]
 45%|████▌     | 43/95 [00:11<00:14,  3.65it/s]
 46%|████▋     | 44/95 [00:12<00:13,  3.65it/s]
 47%|████▋     | 45/95 [00:12<00:13,  3.65it/s]
 48%|████▊     | 46/95 [00:12<00:13,  3.65it/s]
 49%|████▉     | 47/95 [00:12<00:13,  3.65it/s]
 51%|█████     | 48/95 [00:13<00:12,  3.65it/s]
 52%|█████▏    | 49/95 [00:13<00:12,  3.65it/s]
 53%|█████▎    | 50/95 [00:13<00:12,  3.65it/s]
 54%|█████▎    | 51/95 [00:13<00:12,  3.65it/s]
 55%|█████▍    | 52/95 [00:14<00:11,  3.64it/s]
 56%|█████▌    | 53/95 [00:14<00:11,  3.64it/s]
 57%|█████▋    | 54/95 [00:14<00:11,  3.65it/s]
 58%|█████▊    | 55/95 [00:15<00:10,  3.65it/s]
 59%|█████▉    | 56/95 [00:15<00:10,  3.64it/s]
 60%|██████    | 57/95 [00:15<00:10,  3.64it/s]
 61%|██████    | 58/95 [00:15<00:10,  3.64it/s]
 62%|██████▏   | 59/95 [00:16<00:09,  3.64it/s]
 63%|██████▎   | 60/95 [00:16<00:09,  3.65it/s]
 64%|██████▍   | 61/95 [00:16<00:09,  3.64it/s]
 65%|██████▌   | 62/95 [00:16<00:09,  3.64it/s]
 66%|██████▋   | 63/95 [00:17<00:08,  3.64it/s]
 67%|██████▋   | 64/95 [00:17<00:08,  3.64it/s]
 68%|██████▊   | 65/95 [00:17<00:08,  3.64it/s]
 69%|██████▉   | 66/95 [00:18<00:07,  3.64it/s]
 71%|███████   | 67/95 [00:18<00:07,  3.64it/s]
 72%|███████▏  | 68/95 [00:18<00:07,  3.64it/s]
 73%|███████▎  | 69/95 [00:18<00:07,  3.64it/s]
 74%|███████▎  | 70/95 [00:19<00:06,  3.64it/s]
 75%|███████▍  | 71/95 [00:19<00:06,  3.64it/s]
 76%|███████▌  | 72/95 [00:19<00:06,  3.64it/s]
 77%|███████▋  | 73/95 [00:19<00:06,  3.64it/s]
 78%|███████▊  | 74/95 [00:20<00:05,  3.64it/s]
 79%|███████▉  | 75/95 [00:20<00:05,  3.64it/s]
 80%|████████  | 76/95 [00:20<00:05,  3.64it/s]
 81%|████████  | 77/95 [00:21<00:04,  3.64it/s]
 82%|████████▏ | 78/95 [00:21<00:04,  3.63it/s]
 83%|████████▎ | 79/95 [00:21<00:04,  3.64it/s]
 84%|████████▍ | 80/95 [00:21<00:04,  3.64it/s]
 85%|████████▌ | 81/95 [00:22<00:03,  3.64it/s]
 86%|████████▋ | 82/95 [00:22<00:03,  3.64it/s]
 87%|████████▋ | 83/95 [00:22<00:03,  3.63it/s]
 88%|████████▊ | 84/95 [00:23<00:03,  3.63it/s]
 89%|████████▉ | 85/95 [00:23<00:02,  3.64it/s]
 91%|█████████ | 86/95 [00:23<00:02,  3.64it/s]
 92%|█████████▏| 87/95 [00:23<00:02,  3.64it/s]
 93%|█████████▎| 88/95 [00:24<00:01,  3.64it/s]
 94%|█████████▎| 89/95 [00:24<00:01,  3.64it/s]
 95%|█████████▍| 90/95 [00:24<00:01,  3.64it/s]
 96%|█████████▌| 91/95 [00:24<00:01,  3.64it/s]
 97%|█████████▋| 92/95 [00:25<00:00,  3.64it/s]
 98%|█████████▊| 93/95 [00:25<00:00,  3.64it/s]
 99%|█████████▉| 94/95 [00:25<00:00,  3.64it/s]
100%|██████████| 95/95 [00:26<00:00,  3.64it/s]
100%|██████████| 95/95 [00:26<00:00,  3.65it/s]
  0%|          | 0/5 [00:00<?, ?it/s]
 20%|██        | 1/5 [00:00<00:00,  4.25it/s]
 40%|████      | 2/5 [00:00<00:00,  4.22it/s]
 60%|██████    | 3/5 [00:00<00:00,  4.21it/s]
 80%|████████  | 4/5 [00:00<00:00,  4.21it/s]
100%|██████████| 5/5 [00:01<00:00,  4.20it/s]
100%|██████████| 5/5 [00:01<00:00,  4.21it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.038 to run on Replicate, or 26 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 39 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.