SD-XL 1.0-base GGUF Model Card
Quantized versions of stabilityai/stable-diffusion-xl-base-1.0 in GGUF format for use with stable-diffusion.cpp.
At the time of publishing, no ready-made GGUF weights for SDXL were available for sd.cpp runtime — so here we are.
Sample generation: "A lovely cat" · seed 357925 · Q8_0 · 1024×1024
Available Quantizations
| File | Type | Description |
|---|---|---|
sd_xl_base_1.0_0_bf16.gguf | BF16 | Best quality, largest size |
sd_xl_base_1.0_0_Q8_0.gguf | Q8_0 | Great balance of quality and size ✅ recommended |
sd_xl_base_1.0_0_Q4_K.gguf | Q4_K | Smaller size, good quality |
sd_xl_base_1.0_0_Q4_0.gguf | Q4_0 | Smallest size |
Quick Start
1. Download the model
# Recommended — Q8_0
wget https://huggingface.co/kostakoff/stable-diffusion-xl-base-1.0-GGUF/resolve/main/sd_xl_base_1.0_0_Q8_0.gguf
# Other quantizations:
# wget https://huggingface.co/kostakoff/stable-diffusion-xl-base-1.0-GGUF/resolve/main/sd_xl_base_1.0_0_bf16.gguf
# wget https://huggingface.co/kostakoff/stable-diffusion-xl-base-1.0-GGUF/resolve/main/sd_xl_base_1.0_0_Q4_K.gguf
# wget https://huggingface.co/kostakoff/stable-diffusion-xl-base-1.0-GGUF/resolve/main/sd_xl_base_1.0_0_Q4_0.gguf
2. Build stable-diffusion.cpp
Requirements: CUDA-capable GPU, CMake ≥ 3.18, CUDA Toolkit
git clone https://github.com/leejet/stable-diffusion.cpp
cd stable-diffusion.cpp
git submodule init
git submodule update
mkdir build && cd build
cmake .. -DSD_CUDA=ON
cmake --build . --config Release
Version used for conversion and testing:
stable-diffusion.cpp version master-520-d950627, commit d950627
3. Start the server
export CUDA_VISIBLE_DEVICES=0
./stable-diffusion.cpp/build/bin/sd-server \
-m ./sd_xl_base_1.0_0_Q8_0.gguf \
--vae-on-cpu \
--listen-ip 0.0.0.0 \
--listen-port 8081
⚠️ The
--vae-on-cpuflag is required! The VAE decoder consumes up to 10 GB of VRAM when converting the latent representation to PNG. Offloading VAE to CPU makes it possible to run the model on most consumer GPUs.
4. Generate an image
curl -s http://127.0.0.1:8081/v1/images/generations \
-H "Content-Type: application/json" \
-d '{
"model": "sdxl",
"prompt": "A lovely cat<sd_cpp_extra_args>{\"seed\": 357925}</sd_cpp_extra_args>",
"n": 1,
"size": "1024x1024",
"response_format": "b64_json"
}' | jq -r '.data[0].b64_json' | base64 --decode > out.png
Extra parameters are passed via <sd_cpp_extra_args> as a JSON snippet embedded directly in the prompt field.
How the weights were created
Converted from the original sd_xl_base_1.0_0.9vae.safetensors weights using the built-in sd-cli conversion tool:
# Q8_0
./stable-diffusion.cpp/build/bin/sd-cli -M convert \
-m ~/llm/models/sdxl/sd_xl_base_1.0_0.9vae.safetensors \
-o ./sd_xl_base_1.0_0_Q8_0.gguf -v --type q8_0
# BF16
./stable-diffusion.cpp/build/bin/sd-cli -M convert \
-m ~/llm/models/sdxl/sd_xl_base_1.0_0.9vae.safetensors \
-o ./sd_xl_base_1.0_0_bf16.gguf -v --type bf16
# Q4_0
./stable-diffusion.cpp/build/bin/sd-cli -M convert \
-m ~/llm/models/sdxl/sd_xl_base_1.0_0.9vae.safetensors \
-o ./sd_xl_base_1.0_0_Q4_0.gguf -v --type q4_0
# Q4_K
./stable-diffusion.cpp/build/bin/sd-cli -M convert \
-m ~/llm/models/sdxl/sd_xl_base_1.0_0.9vae.safetensors \
-o ./sd_xl_base_1.0_0_Q4_K.gguf -v --type q4_K
License
This model inherits the license of the original — CreativeML Open RAIL++-M