Source?
DreamFusion: Text-to-3D using 2D Diffusion
11–20 of 208 posts
Re: DreamFusion: Text-to-3D using 2D Diffusion
#12Anonymously authored research is very ominous.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#13Is there code for any of these models? Or a collab? Ajay Jain's colab doesn't work, but I would love to see a colab for this.
Silly replying to myself I know, but I had more thoughts. I'm an architect for 3D worlds and I am desperate, lol, for this kind of tool. I use both blender and grasshopper, but I use midjourney to think and prototype all the time. Obvious but it would be astonishing to have something like this for game worlds. I used another version of this to create "a forest emerging from an aircraft carrier" https://www.instagram.com/p/CiRfXKzpnLC/ but the technique didn't have good resolution yet (high fidelity).
Re: DreamFusion: Text-to-3D using 2D Diffusion
#14Did we hit some sort of technical inflection point in the last couple of weeks or is this just coincidence that all of these ML papers around high quality procedural generation are just dropping every other day?
Re: DreamFusion: Text-to-3D using 2D Diffusion
#15This is getting asymptotic.
Progress often happens in waves. There will be a trough again.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#16Did we hit some sort of technical inflection point in the last couple of weeks or is this just coincidence that all of these ML papers around high quality procedural generation are just dropping every other day?
yay
Re: DreamFusion: Text-to-3D using 2D Diffusion
#17Coincidentally came out the same day as Meta's text-to-video. I wonder if Google deliberately held out the release to make a bigger impact somehow?
Would they publish it anonymously? I'd bet they'd want to take credit somehow.
Someone posted the "correct" URL that has names: https://dreamfusion3d.github.io/
Re: DreamFusion: Text-to-3D using 2D Diffusion
#18Coincidentally came out the same day as Meta's text-to-video. I wonder if Google deliberately held out the release to make a bigger impact somehow?
I think it’s because of ICLR deadlines.
Re: DreamFusion: Text-to-3D using 2D Diffusion
#19Correct link with full demo: https://dreamfusion3d.github.io/
That link also has a link to the authors and the paper preprint.