A small thread of interesting things you can do with my become-image Replicate model:

1. You can use animated inputs to reimagine them as real world people, with all of their exaggerated features 2. Bring a sculpture to life.

I'm currently experimenting with AnimateDiff to Zeroscope workflows:

- image generated via ToonYou
- use AnimateDiff to apply motion to image
- use motion as an init video to upscale and add more motion via Zeroscope

See thread for details Original GIF generated via AnimateDiff

AnimateDiff:


Using @camenduru’s colab:
https://t.co/sXx6aKH4Uh

Thanks for the heads up @angrypenguinPNG https://t.co/pg6teRlIrNgithub.com/guoyww/animate…
github.com/camenduru/Anim…

🧵 Announcing Prompter, an open-source tool (and npm package) for generating and sharing prompts:

prompter.fofr.ai

Use it with Midjourney, Stable Diffusion, Gen2, anything. It's great for quickly exploring models.

I've shared some of my fave prompts in the thread 👇 prompter.fofr.ai/?id=61992716-c…

"A film still of [character.scifi], [interaction.crowd], crowd scene, [cinematic.keyword], [cinematic.coloring], [cinematic.effect], set in [time.year] --ar 16:9"

🧵A follow-up thread on how to write prompts to get good animated cinematic images.

https://twitter.com/fofrAI/status/1654257512986574848

Taking the structure from before:

"a film still of two people having an argument, 35mm, over-the shoulder shot, duotone color grading, motion blur, adventure --ar 16:9"

Changes:
- put an animation type at the start
- use "animated film"
- remove the type of film (eg 35mm)

🧵 A big #Midjourney thread on how to write prompts to get good cinematic images.

In this thread I’ll build up a single prompt with cinematic elements, and show their effects.

Each prompt will use a 16:9 aspect ratio, and to minimise variation I've locked in a seed. Let's start with:

"a film still of [characters doing something]"

I've gone with something relatively simple:

"a film still of two people having an argument --ar 16:9 --seed X"

Here's how this starts off with our seed.

I asked Midjourney v5 to '/describe' some logos, to see how it would create prompts for them, and to see what it would create in response.

Starbucks Apple

I put some famous logos through ControlNet. I had to laugh a lot at this one.

I'm playing around with the InstructPix2Pix Google Colab (prompts to edit an image). It's really hard to get good results, but there might be art in the prompt.

It's best to randomise seeds and CFGs to explore what's possible.

colab.research.google.com/github/hugging… Sometimes it's just plain odd