diff options
| author | AUTOMATIC <16777216c@gmail.com> | 2022-08-29 07:23:57 +0000 |
|---|---|---|
| committer | AUTOMATIC <16777216c@gmail.com> | 2022-08-29 07:23:57 +0000 |
| commit | d7acb9975462acc53deb36369d0265cc7a2d446d (patch) | |
| tree | 7637e9879efefd20c4374650286105192f55b357 | |
| parent | 808590654eba1414ec9753a33715cdac0be436d4 (diff) | |
| download | stable-diffusion-webui-gfx803-d7acb9975462acc53deb36369d0265cc7a2d446d.tar.gz stable-diffusion-webui-gfx803-d7acb9975462acc53deb36369d0265cc7a2d446d.tar.bz2 stable-diffusion-webui-gfx803-d7acb9975462acc53deb36369d0265cc7a2d446d.zip | |
readme for --lowvram
| -rw-r--r-- | README.md | 14 |
1 files changed, 14 insertions, 0 deletions
@@ -248,3 +248,17 @@ print("Seed was: " + str(processed.seed)) 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,
+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
+compared to normal operation on my RTX 3090.
+
+This is an independent implementation that does not require any modification to original Stable Diffusion code, and
+with all code concenrated in one place rather than scattered around the program.
+
+
|