Metadata-Version: 2.1
Name: gguf-diffuser
Version: 0.0.2
Summary: image/video/audio generator
Author-Email: gguf <info@gguf.us>
License: MIT
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Project-URL: Repository, https://github.com/gguf-org/gguf-desktop
Requires-Python: >=3.8
Description-Content-Type: text/markdown

## gguf-diffuser
Image/video/audio generation GUI for GGUF models.

## Install

```bash
pip install gguf-diffuser
```

Building the bundled engine requires a C/C++ toolchain and CMake ≥ 3.15
(on Windows: MSVC Build Tools). The engine source is resolved from a sibling
`diffusion` checkout, a vendored `vendor/diffusion`. GPU backends are
opt-in at build time via the engine's own options:

```bash
CMAKE_ARGS="-DSD_CUDA=ON"    pip install gguf-diffuser   # NVIDIA (CUDA)
CMAKE_ARGS="-DSD_HIPBLAS=ON" pip install gguf-diffuser   # AMD (ROCm/HIP)
CMAKE_ARGS="-DSD_METAL=ON"   pip install gguf-diffuser   # Apple (macOS)
CMAKE_ARGS="-DSD_VULKAN=ON"  pip install gguf-diffuser   # Vulkan
```

## Usage

```bash
python -m gguf_diffuser             # launch the GUI in the browser
gguf-diffuser                       # same
gguf-diffuser --port 8643 --no-browser
```

GUI features (as in the desktop app's diffusion panel):

- txt2img with the full model stack: `--model` / `--diffusion-model`, VAE,
  external text encoders (`--clip_l`, `--t5xxl`, `--llm`, …), additional
  models (ControlNet, TAESD, upscaler, PhotoMaker, …), tokenizer packs
- image inputs: init image (img2img), mask (inpainting), end frame,
  control image, reference images
- sampling controls: CFG scale, steps, size, seed, batch count, all engine
  sampling methods and schedules, flash attention, low-VRAM flags
- live progress and engine log, output gallery, saved workflows
  (localStorage + JSON export/import), copyable/editable CLI command

Engine CLI passthrough (runs the bundled `diffusion` binary):

```bash
python -m gguf_diffuser engine -- --diffusion-model model.gguf -p "a cat" -o cat.png
gguf-diffuser engine -- --help
```
