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

feat: do not convert bf16 to f32 (#1055)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2025-12-06 23:55:51 +08:00
1 parent 689e44c9a8
commit bfbb929790
4 files changed
+6 -33
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/flux.md
+1 -1
View File
@@ -15,7 +15,7 @@ You can run Flux using stable-diffusion.cpp with a GPU that has 6GB or even 4GB
You can download the preconverted gguf weights from [FLUX.1-dev-gguf](https://huggingface.co/leejet/FLUX.1-dev-gguf) or [FLUX.1-schnell](https://huggingface.co/leejet/FLUX.1-schnell-gguf), this way you don't have to do the conversion yourself.
Using fp16 will lead to overflow, but ggml's support for bf16 is not yet fully developed. Therefore, we need to convert flux to gguf format here, which also saves VRAM. For example:
For example:
```
.\bin\Release\sd.exe -M convert -m ..\..\ComfyUI\models\unet\flux1-dev.sft -o ..\models\flux1-dev-q8_0.gguf -v --type q8_0
```