diff options
| author | AUTOMATIC <16777216c@gmail.com> | 2022-08-29 13:42:00 +0000 |
|---|---|---|
| committer | AUTOMATIC <16777216c@gmail.com> | 2022-08-29 13:42:00 +0000 |
| commit | 340246105530667989f74db90a9db6ea1cd4e283 (patch) | |
| tree | b71ed4edb2e431c9fb5a913ae8714dd939c5bd90 /README.md | |
| parent | 2b0ac45966d6507aa9a0aba78c6e5dd1647ac61d (diff) | |
| download | stable-diffusion-webui-gfx803-340246105530667989f74db90a9db6ea1cd4e283.tar.gz stable-diffusion-webui-gfx803-340246105530667989f74db90a9db6ea1cd4e283.tar.bz2 stable-diffusion-webui-gfx803-340246105530667989f74db90a9db6ea1cd4e283.zip | |
gfpgan is not kept in memory
font selection setting
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -252,7 +252,7 @@ display(processed.images, processed.seed, processed.info) ### `--lowvram`
Optimizations for GPUs with low VRAM. This should make it possible to generate 512x512 images on videocards with 4GB memory.
-The original idea of those ideas is by basujindal: https://github.com/basujindal/stable-diffusion. Model is separated into modules,
+The original idea of those optimizations is by basujindal: https://github.com/basujindal/stable-diffusion. Model is separated into modules,
and only one module is kept in GPU memory; when another module needs to run, the previous is removed from GPU memory.
It should be obvious but the nature of those optimizations makes the processing run slower -- about 10 times slower
|