Stop using text-to-image. this blender + real-time latent consistency workflow is way more fun, and shows how you can use Generative AI collaboratively, instead of as a creative slot machine try it yourself here

Is the dataset for the model available? I want to make sure it isn't illegal.

This is the biggest productivity cheat code right now. Kiss reading documents goodbye. You can get an instant summary of any document with this tool.

@huggingface This is out of this world.

@huggingface I figured this workflow out months ago! It's pretty great to be honest. You can also get pre-made models and just get the camera at the angle you really need for a picture.

ok... how do you combine the two?

cool, where is th youtube video link?

How does this work

This is dumb. Almost model everything and then rely on a slot machine for output. Just finish the scene

This sounds fascinating! 🌟 It's always exciting to see new ways to blend tech and creativity. I'll definitely check out the link and give it a try. Thanks for sharing! 🤖🎨 #CreativeTech

I think you’ll see text to image and then image to model seamlessly. Course… maybe not… because maybe the text to model will be so good it won’t need to go through image first