- AI-Enhanced Creator
- Posts
- All in one AI?
All in one AI?
Generate EVERYTHING
Hello AI Adventurer.
Thank you for being a subscriber 💛
If you like what I do, consider checking out my guides. Or sharing the newsletter with your friends. There is a referral link at the bottom of this post.
Let’s get to today’s topic - All in one creative AI.
I’ve been touching different areas of Generative AI - image, audio, video - and in my workflows, I have to go from one platform to another.
alt + tab
Constant window switching.
alt + tab
Today I want to introduce you to a platform that has all of the above in one place - FullJourney.
Like many of the AI Generators, it runs on Discord and the exciting part is, you can generate Images, Videos, and Audio all in one place.
Image.
The image generator works similarly to Midjourney. You type in the command and generate your images.
However, there are some additional commands like weights and replacements. You can also add a negative prompt.
There is also generative fill and Gif creation.
(Mamiya photography) (grainy film) cinematic (film still by Alessio Albi), kung fu master sitting surround by greeny bushes of sakura, depth of field, bokeh, messy cluttered background, captivating play of shadows
Video.
Similar to images, we use a command to generate a video with a text prompt.
We have additional options to upload an image and add a negative prompt as well.
The really exciting feature for me is the /movie and /deepfake Which will generate the whole thing for us.
Video generation is developing quickly, so I expect these results to be on par with image quality in the next months.
This video together with music came from a single text prompt:
Kung fu master practicing martial arts surrounded by greeny bushes of sakura, (Mamiya photography) (grainy film) cinematic (film still by Alessio Albi), depth of field, bokeh, messy cluttered background, captivating play of shadows
Audio.
I’m already excited about these possibilities and audio generation ties everything together for me.
We have two commands available for audio generation.
With a bunch of preset options.
Example Workflow.
We can pull all of this together into our creations:
Generate audio voiceover from text
Create an image of our character
Create a “deepfake” by uploading the audio and image.
Generate music.
Generate additional video assets, either with images or without.
put it together and you have your short story!
I hope you will enjoy exploring this new tool and workflow possibilities. As always, the AI world is freaking exciting!
You can stop by my website or social media and as always,
Keep creating and don't forget to have fun. ☀