diff --git a/tasks/assets/image-to-image/image-to-image-input.jpeg b/tasks/assets/image-to-image/image-to-image-input.jpeg
new file mode 100644
index 000000000..b59d26c8d
Binary files /dev/null and b/tasks/assets/image-to-image/image-to-image-input.jpeg differ
diff --git a/tasks/assets/image-to-image/image-to-image-output.png b/tasks/assets/image-to-image/image-to-image-output.png
new file mode 100644
index 000000000..aaa37f451
Binary files /dev/null and b/tasks/assets/image-to-image/image-to-image-output.png differ
diff --git a/tasks/src/image-to-image/about.md b/tasks/src/image-to-image/about.md
new file mode 100644
index 000000000..289d4dd82
--- /dev/null
+++ b/tasks/src/image-to-image/about.md
@@ -0,0 +1,28 @@
+## Use Cases
+
+### Style transfer
+
+One of the most popular use cases of image to image is the style transfer. Style transfer models can convert a regular photography into a painting in the style of a famous painter.
+
+## Task Variants
+
+### Image inpainting
+
+Image inpainting is widely used during photography editing to remove unwanted objects, such as poles, wires or sensor
+dust.
+
+### Image colorization
+
+Old, black and white images can be brought up to life using an image colorization model.
+
+### Super Resolution
+
+Super resolution models increase the resolution of an image, allowing for higher quality viewing and printing.
+
+## Inference
+
+This section should have useful information about how to pull a model from Hugging Face Hub that is a part of a library specialized in a task and use it.
+
+## Useful Resources
+
+In this area, you can insert useful resources about how to train or use a model for this task.
diff --git a/tasks/src/image-to-image/data.ts b/tasks/src/image-to-image/data.ts
new file mode 100644
index 000000000..33d5f8918
--- /dev/null
+++ b/tasks/src/image-to-image/data.ts
@@ -0,0 +1,62 @@
+import { type TaskDataCustom } from "../Types";
+
+const taskData: TaskDataCustom = {
+	datasets: [
+		{
+			description: "Synthetic dataset, for image relighting",
+			id: "VIDIT"
+		},
+		{
+			description: "Multiple images of celebrities, used for facial expression translation"
+			id: "huggan/CelebA-faces"
+		}
+	],
+	demo:     {
+		inputs: [
+			{
+				filename: "image-to-image-input.jpeg",
+				type:     "img",
+			},
+		],
+		outputs: [
+			{
+				filename: "image-to-image-output.png",
+				type:     "img",
+			},
+		]
+	},
+	isPlaceholder: false,
+	metrics:       [
+		{
+			description: "Peak Signal to Noise Ratio (PSNR) is an approximation of the human perception, considering the ratio of the absolute intensity with respect to the variations. Measured in dB, a high value indicates a high fidelity.",
+			id:          "PSNR"
+		},
+		{
+			description: "Structural Similarity Index (SSIM) is a perceptual metric which compares the luminance, contrast and structure of two images. The values of SSIM range between -1 and 1, and higher values indicate closer resemblance to the original image.",
+			id:          "SSIM"
+		},
+		{
+			description: "Inception Score (IS) is an analysis of the labels predicted by an image classification model when presented with a sample of the generated images.",
+			id:          "IS"
+		},
+	],
+	models:        [
+		{
+			description: "A model that enhances images captured in low light conditions.",
+			id: "keras-io/low-light-image-enhancement"
+		},
+		{
+			description: "A model that increases the resolution of an image.",
+			id: "keras-io/super-resolution"
+		},
+		{
+			description: "A model that creates a set of variations of the imput image in the style of DALL-E using Stable Diffusion.",
+			id: "lambdalabs/sd-image-variations-diffusers"
+		}
+	],
+	summary:       "Image to image is the task of transforming a source image to match the characteristics of a target image or a target image domain. Any image manipulation and enhancement is possible with image to image models."
+	widgetModels:  [""],
+	youtubeId:     "",
+};
+
+export default taskData;