Inference of Stable Diffusion in pure C/C++
- Plain C/C++ implementation based on ggml, working in the same way as llama.cpp
- 16-bit, 32-bit float support
- 4-bit, 5-bit and 8-bit integer quantization support
- Accelerated memory-efficient CPU inference
- AVX, AVX2 and AVX512 support for x86 architectures
- Original
txt2img
mode - Negative prompt
- Sampling method
Euler A
- Supported platforms
- Linux
- Mac OS
- Windows
- Original
img2img
mode - More sampling methods
- GPU support
- Make inference faster
- The current implementation of ggml_conv_2d is slow and has high memory usage
- Continuing to reduce memory usage (quantizing the weights of ggml_conv_2d)
- stable-diffusion-webui style tokenizer (eg: token weighting, ...)
- LoRA support
- k-quants support
git clone --recursive https://github.com/leejet/stable-diffusion.cpp
cd stable-diffusion.cpp
-
download original weights(.ckpt or .safetensors). For example
- Stable Diffusion v1.4 from https://huggingface.co/CompVis/stable-diffusion-v-1-4-original
- Stable Diffusion v1.5 from https://huggingface.co/runwayml/stable-diffusion-v1-5
curl -L -O https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt # curl -L -O https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors
-
convert weights to ggml model format
cd models pip install -r requirements.txt python convert.py [path to weights] --out_type [output precision] # For example, python convert.py sd-v1-4.ckpt --out_type f16
You can specify the output model format using the --out_type parameter
f16
for 16-bit floating-pointf32
for 32-bit floating-pointq8_0
for 8-bit integer quantizationq5_0
orq5_1
for 5-bit integer quantizationq4_0
orq4_1
for 4-bit integer quantization
mkdir build
cd build
cmake ..
cmake --build . --config Release
cmake .. -DGGML_OPENBLAS=ON
cmake --build . --config Release
usage: ./sd [arguments]
arguments:
-h, --help show this help message and exit
-t, --threads N number of threads to use during computation (default: -1).
If threads <= 0, then threads will be set to the number of CPU cores
-m, --model [MODEL] path to model
-o, --output OUTPUT path to write result image to (default: .\output.png)
-p, --prompt [PROMPT] the prompt to render
-n, --negative-prompt PROMPT the negative prompt (default: "")
--cfg-scale SCALE unconditional guidance scale: (default: 7.0)
-H, --height H image height, in pixel space (default: 512)
-W, --width W image width, in pixel space (default: 512)
--sample-method SAMPLE_METHOD sample method (default: "eular a")
--steps STEPS number of sample steps (default: 20)
-s SEED, --seed SEED RNG seed (default: 42, use random seed for < 0)
-v, --verbose print extra info
For example
./sd -m ../models/sd-v1-4-ggml-model-f16.bin -p "a lovely cat"
Using formats of different precisions will yield results of varying quality.
f32 | f16 | q8_0 | q5_0 | q5_1 | q4_0 | q4_1 |
---|---|---|---|---|---|---|
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
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 |