Replies: 1 comment
-
Cc: @patil-suraj |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
First of all as shown in HuggingFace [https://huggingface.co/docs/diffusers/api/schedulers/edm_euler](official doc) the EDMEulerScheduler is a implementation of Algorithm 2 from the Elucidating the Design Space of Diffusion-Based Generative Models paper. Here is my question in the$F _\theta (c _{in} \sigma) x ; c _{noise} (\sigma) $ , not the $F _\theta (c _{in} \sigma) \hat{x} ; c _{noise} (\sigma) $ .
step
function shown in below, the procedure end inprev_sample = sample + derivative * dt
which is exactly line 8 in Algorithm 2 in the paper. But then the function does not apply second order correction? Second, in this linepred_original_sample = self.precondition_outputs(sample, model_output, sigma_hat)
, it follows line 7 the $ D _{\theta} (\hat{x} _i ; \hat{t} _{i} ) $ , butmodel_output
is obtained outside ofstep
function, and it isBeta Was this translation helpful? Give feedback.
All reactions