# Arts and graphics

## DALL·E 2

DALL·E 2 is a system able to generate images based on descriptions such as "a bird flying over a mountain, with a city on the background, in a pop-art style"

{% embed url="<https://openai.com/dall-e-2/>" %}

<figure><img src="https://4092288392-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FY8AeUFC5KYkaUv3lbFhX%2Fuploads%2FN43OglJoYqdk3ti5ylvV%2Fdalle2.gif?alt=media&#x26;token=3227740f-9bff-40fe-b0b9-5ab7575e7695" alt=""><figcaption></figcaption></figure>

This tool also includes different AI-driven techniques for editing the generated images (Image-to-Image), such as erasing part of an image and generate different content at that point (Image inpainting), or expanding the image on the sides:

<figure><img src="https://4092288392-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FY8AeUFC5KYkaUv3lbFhX%2Fuploads%2F3ZruxjUBWfZiBaFXIbwe%2Fdalle-erase.gif?alt=media&#x26;token=3548d659-c71f-4b0c-8f24-b75a89cd78ce" alt=""><figcaption><p>Erasing a part of an image to generate new content</p></figcaption></figure>

<figure><img src="https://4092288392-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FY8AeUFC5KYkaUv3lbFhX%2Fuploads%2FfTAbzKL9drUHGKmyI6a3%2Fdalle-moreimage.gif?alt=media&#x26;token=c7bf0084-ea59-4d93-a268-710da7e59162" alt=""><figcaption><p>Imagining how the picture "continues"</p></figcaption></figure>

> ***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.*
>
> \
> <https://huggingface.co/tasks/image-to-image>

## Midjourney

Midjourney is a new research lab focused on new mediums and tools for empowering people. Its Discord bot allows for generating images based on prompts, very similar to DALL·E 2.

{% embed url="<https://www.midjourney.com/home>" %}

<figure><img src="https://4092288392-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FY8AeUFC5KYkaUv3lbFhX%2Fuploads%2FI4Bi3WkC0JZrJ8Q1kAS3%2Fmidjourney.gif?alt=media&#x26;token=6a658b90-4f41-40ae-9ff9-fcbada610eb9" alt=""><figcaption></figcaption></figure>

## Lexica

This search engine looks for images that have been generated with Stable Diffusion in its own platform.

{% embed url="<https://lexica.art>" %}

<figure><img src="https://4092288392-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FY8AeUFC5KYkaUv3lbFhX%2Fuploads%2F6RDVaSt24kxwinyZrJ28%2Flexica.png?alt=media&#x26;token=0be95e64-20a9-4629-9998-10f454e73491" alt=""><figcaption></figcaption></figure>

## Playground AI

This tool is similar to Lexica. It allows for browsing and generating new images from prompts.

{% embed url="<https://playgroundai.com>" %}

<figure><img src="https://4092288392-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FY8AeUFC5KYkaUv3lbFhX%2Fuploads%2FSqtLZbZ4WkzmggHKR96C%2Fplaygroundai.gif?alt=media&#x26;token=353888f0-cffc-4a77-a06b-784ff4f4c790" alt=""><figcaption></figcaption></figure>

## Magician

Figma plugin for generating new icons

{% embed url="<https://magician.design/>" %}

<figure><img src="https://4092288392-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FY8AeUFC5KYkaUv3lbFhX%2Fuploads%2F22o9IyhxoJKntFwyzZPF%2Fmagiciangif.gif?alt=media&#x26;token=2eb4b5c7-ff29-495a-8a72-be08d9e47015" alt=""><figcaption></figcaption></figure>

## Alpaca

Plug-in for [Photoshop](https://adobe.prf.hn/click/camref:1100lriTb/destination:https%3A%2F%2Fwww.adobe.com%2Fproducts%2Fphotoshop.html) that combines Stable Diffusion's AI and human art. Artists can change any part of their picture, upscale it combine images ...

{% embed url="<https://www.getalpaca.io>" %}

{% embed url="<https://twitter.com/i/status/1563278101182054401>" %}

<figure><img src="https://i.gzn.jp/img/2022/08/30/stable-diffusion-photoshop-alpaca/00_m.png" alt=""><figcaption></figcaption></figure>

## Remove BG

Remove the background of the images

{% embed url="<https://www.remove.bg/es>" %}

<figure><img src="https://4092288392-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FY8AeUFC5KYkaUv3lbFhX%2Fuploads%2FEErUZxD2Ivu8aRnHMGDo%2FIm%C3%A1genes%20de%20muestra%20de%20resultados%20%E2%80%93%20remove.bg%20-%20Google%20Chrome%202023-01-21%2022-13-56%20(online-video-cutter.com).gif?alt=media&#x26;token=c349cd46-ab3f-4fed-856a-ac461ecdd31a" alt=""><figcaption></figcaption></figure>

## Avatar AI

Create photorealistic AI avatars

{% embed url="<https://avatarai.me/>" %}

<figure><img src="https://4092288392-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FY8AeUFC5KYkaUv3lbFhX%2Fuploads%2FjzOd6Xk5wmPX0CPgIewF%2Favataria.gif?alt=media&#x26;token=0fc6d811-11a0-4ae4-aa47-3b80623aebde" alt=""><figcaption></figcaption></figure>

## Plask

Extract motion from a video to create an animated humanoid rig (*Mocap*)

{% embed url="<https://plask.ai/>" %}

{% embed url="<https://plask.ai/landing/VideoContents_PC.mp4>" %}

<figure><img src="https://plask.ai/landing/VideoContents_PC.mp4" alt=""><figcaption></figcaption></figure>

## Luma

It captures three-dimensional images using  Neural Radiance Fields (NeRF)

{% embed url="<https://lumalabs.ai>" %}

{% embed url="<https://cdn-luma.com/public/lumalabs.ai/videos/21-Nov-2022.2/landscape.mp4>" %}