alphard/stable-diffusion.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: update docs/flux.md

Browse Source
This commit is contained in:
leejet 2024-08-25 13:11:34 +08:00
parent c837c5d9cc
commit 28a614769a
2 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
assets/flux/flux1-dev-q4_k.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 468 KiB

15
docs/flux.md
View File

@ -4,14 +4,17 @@ You can run Flux using stable-diffusion.cpp with a GPU that has 6GB or even 4GB
## Download weights
- Download flux-dev from https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/flux1-dev.safetensors
- Download flux-schnell from https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/main/flux1-schnell.safetensors
- Download flux
- If you don't want to do the conversion yourself, download the preconverted gguf model 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)
- Otherwise, download flux-dev from https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/flux1-dev.safetensors or flux-schnell from https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/main/flux1-schnell.safetensors
- Download vae from https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/ae.safetensors
- Download clip_l from https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/clip_l.safetensors
- Download t5xxl from https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/t5xxl_fp16.safetensors
## Convert flux weights
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:
```
.\bin\Release\sd.exe -M convert -m ..\..\ComfyUI\models\unet\flux1-dev.sft -o ..\models\flux1-dev-q8_0.gguf -v --type q8_0
@ -30,10 +33,10 @@ For example:
Using formats of different precisions will yield results of varying quality.
| Type | q8_0 | q4_0 | q3_k | q2_k |
|---- | ---- |---- |---- |---- |
| **Memory** | 12068.09 MB | 6394.53 MB | 4888.16 MB | 3735.73 MB |
| **Result** | ![](../assets/flux/flux1-dev-q8_0.png) |![](../assets/flux/flux1-dev-q4_0.png) |![](../assets/flux/flux1-dev-q3_k.png) |![](../assets/flux/flux1-dev-q2_k.png)|
| Type | q8_0 | q4_0 | q4_k | q3_k | q2_k |
|---- | ---- |---- |---- |---- |---- |
| **Memory** | 12068.09 MB | 6394.53 MB | 6395.17 MB | 4888.16 MB | 3735.73 MB |
| **Result** | ![](../assets/flux/flux1-dev-q8_0.png) |![](../assets/flux/flux1-dev-q4_0.png) |![](../assets/flux/flux1-dev-q4_k.png) |![](../assets/flux/flux1-dev-q3_k.png) |![](../assets/flux/flux1-dev-q2_k.png)|