Cartoon style avatars in a couple of clicks

Upload your photo to Magicsnap, choose a style and your avatar is ready!

There is only one free generation available. So arm yourself with other google accounts and generate in other browsers or incognito mode.

#service

Generate Midjourney images in one click without requiring access to Discord or Midjourney AI credentials.

This is done by the Feng My Shui neural network, or rather just a web shell for Midjourney. A collection of promts is also available.

We generated 4 pictures, but didn't see a free generation counter.

#service

A simple free AI will create a short animation out of a picture.

It preserves the unity of style and composition of the source.

Create here.

#service

There's a new video-to-video AI that can even do outpainting!

Meet MagicEdit! What can it do? Video styling, local editing, video-MagicMix and object coloring.

The creators are ByteDance, the company that owns TikTok.

The code is not yet made available for everyone to use, we are waiting.

#service

Now you can easily change faces on any video locally

All you need is a photo and a video.

FaceFusion is an open source AI with a simple web interface.

A guide to installing the basic but slow version.
A guide to installing the accelerated version.

Works on both Windows and Mac.

#service

ChatGPT turned out to be smarter than 17 doctors. The Daily Mail told the story of Alex who, after 4 years, stopped growing, started experiencing pain, heavier movement and impulsive behavior. For 3 years, none of the doctors were ever able to diagnose him.

ChatGPT came to the rescue and determined that the child had a split spine and spinal cord malformation. After that, a surgery was performed and the boy's health returned to normal.

#chatgpt #news

Control your composition with camera angles

Add the right angle to the promt:

Macro
Close-up
Wide Angle
Diagonal Angle
Aerial
High Angle
Low Angle
Oblique Angle

#guide #Midjourney #useful

It's happening! You can clone any voice for free and generate it in another language

AI XTTS only needs 3 seconds of a reference voice to generate audio from your text promt. It's free.

We have tried this miracle, it turned out quite well, but the accents in words are still incorrect. They need to improve it.

You can record your voice from a microphone. Clone your voice here.

#useful #service

I can't think of anything that can't be done with neural networks!

Imagine, you can make any picture come to life just by uploading it to Generative Image Dynamics. But that's not all, pictures become interactive: if you pull an object in the image with your mouse and release it, it will move by inertia. Awesome!

You can create something as in the video here.

#service #useful

How to make a movie cover in Midjourney

1. Create an image using the structure of this query:
[YOUR OBJECT], in the style of movie cover, [YOUR COLORS], [YOUR STYLE].

You can also use "in the style of movie poster" instead of "in the style of movie cover".

Promt to the attached picture:
astronaut, in the style of movie cover, light indigo and dark beige, photo, muted tones

2. Add text using Photoshop.

#guide #midjourney

HuggingFace showed off the new text-to-image neural network Würstchen

"Another picture generator?" - you say. "There are tons of these picture generators out there."

Yes, but Würstchen can generate images much faster than models like Stable Diffusion XL, while using a lot less memory.

"How so?" - you ask. And the fact is that when trained, the new AI extremely compresses the image - it provides 42 times the spatial compression! While other picture generators use 4-8-fold spatial compression. Würstchen uses two stages for compression: Stage A is VQGAN, and Stage B is a diffusion autoencoder. And then there is Stage C, in which the neural network is trained in a highly compressed space.

You can play the demo here.

At this rate, we may be able to generate pictures even on a smart watch

#service

Stability has an addition: they've unveiled their Stable Audio neural network.

As the name implies, the neural network generates music and sounds by text promt.

It was trained using data from the online music library AudioSparx.

It is free to generate 20 tracks per month up to 45 seconds long.

#service