inbarhub / ddpm_inversion Goto Github PK

Hi expert,
Nice work and get key point about inversion with independent random noises.
But I can't understand which case of error accumulation could be affect zt and xt-1 in algorithm 1.
May you give me some examples about this?

Hi @inbarhub
First of all thanks for a very good and interesting paper, really enjoyed reading.

I wonder if it's possibly to apply the derived noise maps to schedulers other than DDPM/DDIM? For example have you tried substituting the noise maps in Euler Ancestral sampler? Since ddim/ddpm in general seems to produce lower quality results/requires larger number of steps

Hi,

first thank you for your amazing work, it is straightforward to get it working!

However, one question, in line

Best,
Sidney

Hi @inbarhub , thanks for your greate work.
Can you give some code about the Color manipulation in your paper?
Thanks again!

Dear @inbarhub ,

Thank you for sharing this great work.

Is there a way to make this repo support sdxl or sdxl turbo?

I appreciate your help.

Best Wishes,
Zongze

Hi authors,
I fail to understand why the randomly sampled epsilons are dependent in respect to the timestep axis. And likewise, I fail to understand why does epsilon_hat is independent. Thank you for the great work and eager for your reply!