(2/6)The tricky part is keeping our character consistent while applying variations.
So let's do just that. Copy the URL of the initial image (ensure to open it on browser first), use /imagine prompt:, and then paste the same prompt as before. But let's add a little modification
(3/6) Now, do the same, maintaining the original image url, but modifying his status. Lets say... bowing!
(4/6) And keep going on! Now Jimmy is prepared to run
(5/6) We can also add accesories, such as sunglasses
(6/6) I know the results can be improved, but certainly this can greatly accelerate the process of designing characters, animations... Give it a try and let me know!😊
• • •
Missing some Tweet in this thread? You can try to
force a refresh
I created my own South Park-style talking avatar in just 5 minutes.
Wanna try it too? (Sound ON 🔊)
I'll tell you everything below! 🧵👇
I recreated myself using my Flux LoRA, trained on Replicate along with this prompt:
a [lora_trigger_word] man with a beard as a South Park TV Show character. Simple illustration. White mountains and village background. Cartoonish, illustration. (South Park style:1.3)
If you’re unsure how to do it, here’s a tutorial I shared a few months ago that makes it super easy. And if you don’t want to train it, no worries! Just use the previous prompt, tweak it, and create your own character!
I think we're getting really close to crossing the uncanny valley with these AI videos...
And guess what? I’ll show you how you can make them too! 🧵👇
(Bookmark this thread for later!)
Here’s the plan:
· We’ll create our little kitty using Mystic by Magnific
· Animate it with @itsPolloAI
· Extract frames and create new scenes
· Touch up some of the frames with Photoshop
Let’s get started! ⬇️
Surprisingly, for this clip, I only created 2 images using Mystic v2.5 by @Magnific_AI. I used the super realistic mode and the prompts you can find in the image ALT text.