---
license: openrail++
base_model: sd2-community/stable-diffusion-2
tags:
- text-to-image
- stable-diffusion
- gguf
- stable-diffusion.cpp
- sd.cpp
library_name: diffusers
pipeline_tag: text-to-image
inference: true
---

# Stable Diffusion v2 GGUF Model Card

Quantized versions of [stable-diffusion-2](https://huggingface.co/sd2-community/stable-diffusion-2) in **GGUF** format for use with [stable-diffusion.cpp](https://github.com/leejet/stable-diffusion.cpp).

At the time of publishing, no ready-made GGUF weights for SD2.0 were available for sd.cpp runtime — so here we are.

![Sample output](out.png)
*Sample generation: "A lovely cat" · Q8_0 · 768x768*

---

## Available Quantizations

| File | Quantization | Description |
|------|-------------|-------------|
| `v1-5-pruned_Q8_0.gguf` | Q8_0 | High quality, ~half the size of bf16 |
| `v1-5-pruned_Q4_K.gguf` | Q4_K | Balanced quality/size |
| `v1-5-pruned_Q4_0.gguf` | Q4_0 | Smallest, fastest, slight quality loss |

---

## Quick Start

### 1. Download the model

```bash
wget https://huggingface.co/kostakoff/stable-diffusion-2-GGUF/resolve/main/768-v-ema-Q8_0.gguf
# Other quantizations:
# wget https://huggingface.co/kostakoff/stable-diffusion-2-GGUF/resolve/main/768-v-ema-Q4_K.gguf
# wget https://huggingface.co/kostakoff/stable-diffusion-2-GGUF/resolve/main/768-v-ema-Q4_0.gguf
```

### 2. Build stable-diffusion.cpp

> **Requirements:** CUDA-capable GPU, CMake ≥ 3.18, CUDA Toolkit

```bash
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
```

This was tested on commit `d950627` (version `master-520-d950627`). Check your version with:

```bash
./build/bin/sd-cli --version
```

### 3. Start the server

```bash
export CUDA_VISIBLE_DEVICES=0
./stable-diffusion.cpp/build/bin/sd-server \
  -m ./768-v-ema-Q8_0.gguf \
  --listen-ip 0.0.0.0 \
  --listen-port 8081 \
  --seed -1
```

The server exposes an OpenAI-compatible `/v1/images/generations` endpoint.

### 4. Generate an image

```bash
curl -s http://127.0.0.1:8081/v1/images/generations \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sd2.0",
    "prompt": "A lovely cat",
    "n": 1,
    "size": "768x768",
    "response_format": "b64_json"
  }' | jq -r '.data[0].b64_json' | base64 --decode > output.png
```

Extra parameters can be 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 [768-v-ema.safetensors](https://huggingface.co/sd2-community/stable-diffusion-2/blob/main/768-v-ema.safetensors) weights using the built-in `sd-cli` conversion tool:

```bash
# Q4_0
./stable-diffusion.cpp/build/bin/sd-cli -M convert \
  -m ~/llm/models/sd2.0/768-v-ema.safetensors \
  -o 768-v-ema-Q4_0.gguf -v --type q4_0
# Q4_K
./stable-diffusion.cpp/build/bin/sd-cli -M convert \
  -m ~/llm/models/sd2.0/768-v-ema.safetensors \
  -o ./768-v-ema-Q4_K.gguf -v --type q4_K
# Q8_0
./stable-diffusion.cpp/build/bin/sd-cli -M convert \
  -m ~/llm/models/sd2.0/768-v-ema.safetensors \
  -o ./768-v-ema-Q8_0.gguf -v --type q8_0
```

---

## License

This model inherits the license of the original: **CreativeML Open RAIL++-M**