1. Introduction

DeepFilter is an algorithm that uses Deep Learning to create interesting and creative photo filters.

Note: When using batched images and the default 5 minute timeout, a safe maximum batch size is 20.

Input:

  • (Required): Link to Image(s)
  • (Required): Link to Save Path(s)
  • (Required): Filter name or filter dataURL
  • (Optional): Mode (quality or fast) (default=fast)

Output:

  • Save Path(s)

2. Filters

List of filters: alien_goggles, aqua, blue_brush, blue_granite, bright_sand, cinnamon_rolls, clean_view, colorful_blocks, colorful_dream, crafty_painting, creativity, crunch_paper, dark_rain, dark_soul, deep_connections, dry_skin, far_away, gan_vogh, gred_mash, green_zuma, hot_spicy, neo_instinct, oily_mcoilface, plentiful, post_modern, purp_paper, purple_pond, purple_storm, rainbow_festival, really_hot, sand_paper, smooth_ride, space_pizza, spagetti_accident, sunday, yellow_collage, yellow_paper

3. Examples

Example 1.

  • Parameter 1: An image.
  • Parameter 2: A save path.
  • Parameter 3: Filter name.
    {
      "images": [
        "data://deeplearning/example_data/elon_musk.jpg"
      ],
      "savePaths": [
        "data://.my/temp/elon_space_pizza.jpg"
      ],
      "filterName": "space_pizza"
    }

Output:

    {
      "savePaths": [
        "data://.my/temp/elon_space_pizza.jpg"
      ]
    }

Example 2.

  • Parameter 1: A list of images.
  • Parameter 2: A list of save paths.
  • Parameter 3: Filter name.
    {
      "images": [
        "data://deeplearning/example_data/sample_image_1.png",
        "data://deeplearning/example_data/sample_image_2.png",
        "data://deeplearning/example_data/sample_image_3.png",
        "data://deeplearning/example_data/sample_image_4.png",
        "data://deeplearning/example_data/sample_image_5.png",
        "data://deeplearning/example_data/sample_image_6.png"
      ],
      "savePaths": [
        "data://.my/temp/output_1.jpg",
        "data://.my/temp/output_2.jpg",
        "data://.my/temp/output_3.jpg",
        "data://.my/temp/output_4.jpg",
        "data://.my/temp/output_5.jpg",
        "data://.my/temp/output_6.jpg"
      ],
      "filterName": "gan_vogh"
    }

Output:

    {
      "savePaths": [
        "data://.my/temp/output_1.jpg",
        "data://.my/temp/output_2.jpg",
        "data://.my/temp/output_3.jpg",
        "data://.my/temp/output_4.jpg",
        "data://.my/temp/output_5.jpg",
        "data://.my/temp/output_6.jpg"
      ]
    }

Example 3.

  • Parameter 1: A list of images.
  • Parameter 2: A list of save paths.
  • Parameter 3: Filter name.
  • Parameter 4: Quality mode.
    {
      "images": [
        "data://deeplearning/example_data/sample_image_1.png",
        "data://deeplearning/example_data/sample_image_2.png",
        "data://deeplearning/example_data/sample_image_3.png",
        "data://deeplearning/example_data/sample_image_4.png",
        "data://deeplearning/example_data/sample_image_5.png",
        "data://deeplearning/example_data/sample_image_6.png"
      ],
      "savePaths": [
        "data://.my/temp/output_1.jpg",
        "data://.my/temp/output_2.jpg",
        "data://.my/temp/output_3.jpg",
        "data://.my/temp/output_4.jpg",
        "data://.my/temp/output_5.jpg",
        "data://.my/temp/output_6.jpg"
      ],
      "filterName": "gan_vogh",
      "mode":"quality"
    }

Output:

    {
      "savePaths": [
        "data://.my/temp/output_1.jpg",
        "data://.my/temp/output_2.jpg",
        "data://.my/temp/output_3.jpg",
        "data://.my/temp/output_4.jpg",
        "data://.my/temp/output_5.jpg",
        "data://.my/temp/output_6.jpg"
      ]
    }

4. Credits

Algorithm is based on research done by: Texture Networks: Feed-forward Synthesis of Textures and Stylized Images

Images were retrieved from Unsplash & Wikipedia:

  1. https://unsplash.com/photos/HRZUzoX1e6w

  2. https://unsplash.com/photos/1kdh6jBZMeA

  3. https://unsplash.com/photos/lzYZEDJ8fbo

  4. https://unsplash.com/photos/nvj-PDU98WU

  5. https://unsplash.com/photos/cr6RJblqjyo

  6. https://unsplash.com/photos/5ylV-khwM9s

  7. https://en.wikipedia.org/wiki/Elon_Musk#/media/File:Elon_Musk_2015.jpg

Writing good docs:

Communicate Value

A good introduction should make it clear why someone might use your API.

Show and Tell

Give examples of using your API and explain those examples.

Easy to Skim

Ensure your docs are structured such that familiar users can quickly jump to the content they want.

Current

Revisit your docs after making breaking changes or adding new features to keep them up-to-date.