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:

deeplearning / DeepFilter / 0.6.0

Comments

Loading comments