r/stable-diffusion-finetune
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

Alter credit in README

Browse source
This commit is contained in:
Katherine Crowson 2022-04-15 05:36:41 -07:00
parent 66df437e52
commit c8122e7917
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -56,7 +56,7 @@ Quality, sampling speed and diversity are best controlled via the `scale`, `ddim
As a rule of thumb, higher values of `scale` produce better samples at the cost of a reduced output diversity. As a rule of thumb, higher values of `scale` produce better samples at the cost of a reduced output diversity.
Furthermore, increasing `ddim_steps` generally also gives higher quality samples, but returns are diminishing for values > 250. Furthermore, increasing `ddim_steps` generally also gives higher quality samples, but returns are diminishing for values > 250.
Fast sampling (i.e. low values of `ddim_steps`) while retaining good quality can be achieved by using `--ddim_eta 0.0`. Fast sampling (i.e. low values of `ddim_steps`) while retaining good quality can be achieved by using `--ddim_eta 0.0`.
Faster sampling (i.e. even lower values of `ddim_steps`) while retaining good quality can be achieved by using `--ddim_eta 0.0` and `--plms` (added by Katherine Crowson, see [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://arxiv.org/abs/2202.09778)). Faster sampling (i.e. even lower values of `ddim_steps`) while retaining good quality can be achieved by using `--ddim_eta 0.0` and `--plms` (see [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://arxiv.org/abs/2202.09778)).
#### Beyond 256² #### Beyond 256²