anhappdev/test:7f7d040c – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

anhappdev /test:7f7d040c

Playground API

Input

method

string

The method to use

Default: "replace"

prompt

string

Shift + Return to add a new line

The prompt to guide the image generation. Use ++ to emphasize and -- to de-emphasize parts of the sentence

Default: "a photo of an astronaut++ riding a horse on mars"

negative_prompt

string

Shift + Return to add a new line

Specify things to not see in the output

Default: ""

image

*file

Preview

The image which will be inpainted.Parts of the image will be masked out with `mask_image` and repainted according to `prompt`.

mask_image

*file

Preview

A black and white image to use as mask for inpainting over the image provided. White pixels in the mask will be repainted, while black pixels will be preserved

num_outputs

integer

(minimum: 1, maximum: 8)

Number of images to output. Higher number of outputs may cause OOM.

Default: 3

num_inference_steps

integer

(minimum: 1, maximum: 50)

The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference

Default: 30

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

control_scale

number

(minimum: 0, maximum: 1)

Scale for ControlNet conditioning

Default: 0.5

seed

integer

Random seed. Leave blank to randomize the seed

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

npx create-replicate --model=anhappdev/test

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";
import fs from "node:fs";

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

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

const output = await replicate.run(
  "anhappdev/test:7f7d040c40f663a4dce135c3cb524f9b69ef394e72ee72b8e8e6a9a898206641",
  {
    input: {
      seed: 12345,
      image: "https://replicate.delivery/pbxt/Ia2E3MUrVDVXITRVSKCHcCYi9WMYGoTpqxtqZ0PuqRoaY3FW/1.jpg",
      method: "adjust",
      prompt: "a green leather couch",
      mask_image: "https://replicate.delivery/pbxt/Ia2E2SDOE51oEfLeToezFAIYKw84oX0wHJYNVO5GUr6YMFMi/1_mask.jpg",
      num_outputs: 4,
      control_scale: 0.5,
      guidance_scale: 8,
      negative_prompt: "",
      num_inference_steps: 30
    }
  }
);

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

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

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

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

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

Find your API token in your account settings.

Import the client:

import replicate

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

output = replicate.run(
    "anhappdev/test:7f7d040c40f663a4dce135c3cb524f9b69ef394e72ee72b8e8e6a9a898206641",
    input={
        "seed": 12345,
        "image": "https://replicate.delivery/pbxt/Ia2E3MUrVDVXITRVSKCHcCYi9WMYGoTpqxtqZ0PuqRoaY3FW/1.jpg",
        "method": "adjust",
        "prompt": "a green leather couch",
        "mask_image": "https://replicate.delivery/pbxt/Ia2E2SDOE51oEfLeToezFAIYKw84oX0wHJYNVO5GUr6YMFMi/1_mask.jpg",
        "num_outputs": 4,
        "control_scale": 0.5,
        "guidance_scale": 8,
        "negative_prompt": "",
        "num_inference_steps": 30
    }
)
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 anhappdev/test 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": "anhappdev/test:7f7d040c40f663a4dce135c3cb524f9b69ef394e72ee72b8e8e6a9a898206641",
    "input": {
      "seed": 12345,
      "image": "https://replicate.delivery/pbxt/Ia2E3MUrVDVXITRVSKCHcCYi9WMYGoTpqxtqZ0PuqRoaY3FW/1.jpg",
      "method": "adjust",
      "prompt": "a green leather couch",
      "mask_image": "https://replicate.delivery/pbxt/Ia2E2SDOE51oEfLeToezFAIYKw84oX0wHJYNVO5GUr6YMFMi/1_mask.jpg",
      "num_outputs": 4,
      "control_scale": 0.5,
      "guidance_scale": 8,
      "negative_prompt": "",
      "num_inference_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-04-30T09:08:18.740721Z",
  "created_at": "2023-04-30T09:06:48.057578Z",
  "data_removed": false,
  "error": null,
  "id": "pavvq3aqxfdcvpxnwus4vq746i",
  "input": {
    "seed": 12345,
    "image": "https://replicate.delivery/pbxt/Ia2E3MUrVDVXITRVSKCHcCYi9WMYGoTpqxtqZ0PuqRoaY3FW/1.jpg",
    "method": "adjust",
    "prompt": "a green leather couch",
    "mask_image": "https://replicate.delivery/pbxt/Ia2E2SDOE51oEfLeToezFAIYKw84oX0wHJYNVO5GUr6YMFMi/1_mask.jpg",
    "num_outputs": 4,
    "control_scale": 0.5,
    "guidance_scale": 8,
    "num_inference_steps": 30
  },
  "logs": "2023-04-30 09:07:12,255 [INFO] :: Using seed: 12345\n  0%|          | 0/30 [00:00<?, ?it/s][2023-04-30 09:07:19,285] torch._dynamo.convert_frame: [WARNING] torch._dynamo hit config.cache_size_limit (64)\nfunction: 'forward' (/root/.pyenv/versions/3.9.16/lib/python3.9/site-packages/diffusers/models/attention_processor.py:263)\nreasons:  tensor 'hidden_states' size mismatch at index 0. expected 6, actual 8\nto diagnose recompilation issues, see https://pytorch.org/docs/master/dynamo/troubleshooting.html.\n[2023-04-30 09:07:19,287] torch._dynamo.convert_frame: [WARNING] torch._dynamo hit config.cache_size_limit (64)\nfunction: '__call__' (/root/.pyenv/versions/3.9.16/lib/python3.9/site-packages/diffusers/models/attention_processor.py:714)\nreasons:  tensor 'hidden_states' size mismatch at index 0. expected 6, actual 8\nto diagnose recompilation issues, see https://pytorch.org/docs/master/dynamo/troubleshooting.html.\n  3%|▎         | 1/30 [00:55<26:44, 55.31s/it]\n  7%|▋         | 2/30 [00:55<10:39, 22.85s/it]\n 10%|█         | 3/30 [00:55<05:36, 12.46s/it]\n 17%|█▋        | 5/30 [00:55<02:16,  5.46s/it]\n 20%|██        | 6/30 [00:55<01:34,  3.92s/it]\n 27%|██▋       | 8/30 [00:56<00:48,  2.20s/it]\n 33%|███▎      | 10/30 [00:56<00:27,  1.37s/it]\n 40%|████      | 12/30 [00:56<00:16,  1.09it/s]\n 47%|████▋     | 14/30 [00:56<00:10,  1.56it/s]\n 53%|█████▎    | 16/30 [00:56<00:06,  2.16it/s]\n 60%|██████    | 18/30 [00:57<00:04,  2.88it/s]\n 67%|██████▋   | 20/30 [00:57<00:02,  3.71it/s]\n 73%|███████▎  | 22/30 [00:57<00:01,  4.60it/s]\n 80%|████████  | 24/30 [00:57<00:01,  5.52it/s]\n 87%|████████▋ | 26/30 [00:57<00:00,  6.40it/s]\n 93%|█████████▎| 28/30 [00:58<00:00,  7.19it/s]\n100%|██████████| 30/30 [00:58<00:00,  7.88it/s]\n100%|██████████| 30/30 [00:58<00:00,  1.94s/it]",
  "metrics": {
    "predict_time": 67.429766,
    "total_time": 90.683143
  },
  "output": [
    "https://replicate.delivery/pbxt/CWZ1F8mEmUaPMFYTVKQNieLjKwCNL9ix5MCxqyYbTU3fHethA/adjust-out-0.jpg",
    "https://replicate.delivery/pbxt/flNJ1u5Gbej7b0DfgXtMBKg8FJiizVyNQuZifPZ0v12Bg4bDB/adjust-out-1.jpg",
    "https://replicate.delivery/pbxt/JM4NtBUneux9RqnGaW6N2MEHaQAuDcN3DuC7JDnopFrAEf2QA/adjust-out-2.jpg",
    "https://replicate.delivery/pbxt/1fLY4ZJfguj0c0lTtQuW81dd0gql8Ee8S76G4uWu3EKEQ8thA/adjust-out-3.jpg"
  ],
  "started_at": "2023-04-30T09:07:11.310955Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/pavvq3aqxfdcvpxnwus4vq746i",
    "cancel": "https://api.replicate.com/v1/predictions/pavvq3aqxfdcvpxnwus4vq746i/cancel"
  },
  "version": "7f7d040c40f663a4dce135c3cb524f9b69ef394e72ee72b8e8e6a9a898206641"
}

Generated in

67.4 seconds

Tweak it Report

2023-04-30 09:07:12,255 [INFO] :: Using seed: 12345
  0%|          | 0/30 [00:00<?, ?it/s][2023-04-30 09:07:19,285] torch._dynamo.convert_frame: [WARNING] torch._dynamo hit config.cache_size_limit (64)
function: 'forward' (/root/.pyenv/versions/3.9.16/lib/python3.9/site-packages/diffusers/models/attention_processor.py:263)
reasons:  tensor 'hidden_states' size mismatch at index 0. expected 6, actual 8
to diagnose recompilation issues, see https://pytorch.org/docs/master/dynamo/troubleshooting.html.
[2023-04-30 09:07:19,287] torch._dynamo.convert_frame: [WARNING] torch._dynamo hit config.cache_size_limit (64)
function: '__call__' (/root/.pyenv/versions/3.9.16/lib/python3.9/site-packages/diffusers/models/attention_processor.py:714)
reasons:  tensor 'hidden_states' size mismatch at index 0. expected 6, actual 8
to diagnose recompilation issues, see https://pytorch.org/docs/master/dynamo/troubleshooting.html.
  3%|▎         | 1/30 [00:55<26:44, 55.31s/it]
  7%|▋         | 2/30 [00:55<10:39, 22.85s/it]
 10%|█         | 3/30 [00:55<05:36, 12.46s/it]
 17%|█▋        | 5/30 [00:55<02:16,  5.46s/it]
 20%|██        | 6/30 [00:55<01:34,  3.92s/it]
 27%|██▋       | 8/30 [00:56<00:48,  2.20s/it]
 33%|███▎      | 10/30 [00:56<00:27,  1.37s/it]
 40%|████      | 12/30 [00:56<00:16,  1.09it/s]
 47%|████▋     | 14/30 [00:56<00:10,  1.56it/s]
 53%|█████▎    | 16/30 [00:56<00:06,  2.16it/s]
 60%|██████    | 18/30 [00:57<00:04,  2.88it/s]
 67%|██████▋   | 20/30 [00:57<00:02,  3.71it/s]
 73%|███████▎  | 22/30 [00:57<00:01,  4.60it/s]
 80%|████████  | 24/30 [00:57<00:01,  5.52it/s]
 87%|████████▋ | 26/30 [00:57<00:00,  6.40it/s]
 93%|█████████▎| 28/30 [00:58<00:00,  7.19it/s]
100%|██████████| 30/30 [00:58<00:00,  7.88it/s]
100%|██████████| 30/30 [00:58<00:00,  1.94s/it]