huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-18 11:37:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Module Docs (#2624)

Browse Source 
* update whisper

* update llama2c

* update t5

* update phi and t5

* add a blip model

* qlamma doc

* add two new docs

* add docs and emoji

* additional models

* openclip

* pixtral

* edits on the  model docs

* update yu

* update a fe wmore models

* add persimmon

* add model-level doc

* names

* update module doc

* links in heira

* remove empty URL

* update more hyperlinks

* updated hyperlinks

* more links

* Update mod.rs

---------

Co-authored-by: Laurent Mazare <laurent.mazare@gmail.com>
This commit is contained in:
zachcp
2024-11-18 08:19:23 -05:00
committed by GitHub
parent 12d7e7b145
commit 386fd8abb4
39 changed files with 170 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
candle-transformers/src/models/stable_diffusion/euler_ancestral_discrete.rs
View File

@ -1,12 +1,7 @@
//! Ancestral sampling with Euler method steps.
//!
//! Reference implementation in Rust:
//!
//! https://github.com/pykeio/diffusers/blob/250b9ad1898af41e76a74c0d8d4292652823338a/src/schedulers/euler_ancestral_discrete.rs
//!
//! Based on the original [`k-diffusion` implementation by Katherine Crowson][kd].
//! Based on the original [`k-diffusion` implementation by Katherine Crowson]( https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L72).
///
/// [kd]: https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L72
use super::{
schedulers::{
betas_for_alpha_bar, BetaSchedule, PredictionType, Scheduler, SchedulerConfig,
@ -29,7 +24,7 @@ pub struct EulerAncestralDiscreteSchedulerConfig {
pub steps_offset: usize,
/// prediction type of the scheduler function, one of `epsilon` (predicting
/// the noise of the diffusion process), `sample` (directly predicting the noisy sample`)
/// or `v_prediction` (see section 2.4 https://imagen.research.google/video/paper.pdf)
/// or `v_prediction` (see [section 2.4](https://imagen.research.google/video/paper.pdf))
pub prediction_type: PredictionType,
/// number of diffusion steps used to train the model
pub train_timesteps: usize,