extern/easydiffusion
1
0
Fork 1
mirror of https://github.com/easydiffusion/easydiffusion.git synced 2025-06-20 09:57:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

added detail about "dpm_adaptive"

GoldMath 2023-03-12 01:37:10 +01:00
parent cb80da4be4
commit f657079bf6
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
How-to-Use.md

@ -22,7 +22,8 @@ Here is a rough overview of the behaviors of different sampler implementations:
Most samplers are deterministic. If re-run with the same seed and settings, it will generate the same image. You can also increase the step size to see if artifacts in the image clear up, but it may be a slightly different image. Most samplers are deterministic. If re-run with the same seed and settings, it will generate the same image. You can also increase the step size to see if artifacts in the image clear up, but it may be a slightly different image.
Note that **Ancestral** sampler, `euler_a`, `dpm2_a` and `dpmpp_2s_a` are *not always* deterministic. They can create different images when run in different batch sizes. Note that **Ancestral** sampler, `euler_a`, `dpm2_a` and `dpmpp_2s_a` are *not always* deterministic. They can create different images when run in different batch sizes.
`dpm_adaptive` use an automatic steps count algorithm, ignoring the user Inference Steps setting.
[![SD2](https://user-images.githubusercontent.com/7282547/222918227-052d5c8f-f6db-4bcb-bfe8-2902228171db.jpg)](https://user-images.githubusercontent.com/7282547/222918227-052d5c8f-f6db-4bcb-bfe8-2902228171db.jpg) [![SD2](https://user-images.githubusercontent.com/7282547/222918227-052d5c8f-f6db-4bcb-bfe8-2902228171db.jpg)](https://user-images.githubusercontent.com/7282547/222918227-052d5c8f-f6db-4bcb-bfe8-2902228171db.jpg)