DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 03:24:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf: free unused params immediately to reduce memory usage

Browse Source
This commit is contained in:
leejet committed 2023-08-17 00:55:36 +08:00
1 parent cbee3c9a4f
commit 8f34dd7cc7
4 files changed
+232 -73
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

README.md
+3 -2
View File
@@ -12,6 +12,7 @@ Inference of [Stable Diffusion](https://github.com/CompVis/stable-diffusion) in
- 16-bit, 32-bit float support
- 4-bit, 5-bit and 8-bit integer quantization support
- Accelerated memory-efficient CPU inference
- Only requires ~2.3GB when using txt2img with fp16 precision to generate a 512x512 image
- AVX, AVX2 and AVX512 support for x86 architectures
- Original `txt2img` and `img2img` mode
- Negative prompt
@@ -152,8 +153,8 @@ Using formats of different precisions will yield results of varying quality.
| precision | f32 | f16 |q8_0 |q5_0 |q5_1 |q4_0 |q4_1 |
| ---- | ---- |---- |---- |---- |---- |---- |---- |
| **Disk** | 2.8G | 2.0G | 1.7G | 1.6G | 1.6G | 1.5G | 1.5G |
| **Memory**(txt2img - 512 x 512) | ~4.9G | ~4.1G | ~3.8G | ~3.7G | ~3.7G | ~3.6G | ~3.6G |
| **Disk** | 2.7G | 2.0G | 1.7G | 1.6G | 1.6G | 1.5G | 1.5G |
| **Memory**(txt2img - 512 x 512) | ~2.8G | ~2.3G | ~2.1G | ~2.0G | ~2.0G | ~2.0G | ~2.0G |
## References