Metadata-Version: 2.4
Name: dgenerate
Version: 5.0.0
Summary: Batch image generation and manipulation tool supporting Stable Diffusion and related techniques / algorithms, with support for video and animated image processing.
Home-page: https://github.com/Teriks/dgenerate
Author: Teriks
Author-email: Teriks@users.noreply.github.com
License: BSD 3-Clause
Classifier: Intended Audience :: Other Audience
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Developers
Classifier: Natural Language :: English
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX :: Linux
Classifier: Environment :: Console
Classifier: Environment :: GPU :: NVIDIA CUDA
Classifier: Topic :: Utilities
Classifier: Topic :: Artistic Software
Classifier: Topic :: Multimedia :: Graphics
Classifier: Topic :: Multimedia :: Video
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Processing
Requires-Python: >=3.11,<3.14
Description-Content-Type: text/x-rst
License-File: LICENSE
Requires-Dist: diffusers==0.35.1
Requires-Dist: datasets==4.1.1
Requires-Dist: hf_xet<2.0.0,>=1.1.10
Requires-Dist: peft==0.17.1
Requires-Dist: transformers==4.55.2
Requires-Dist: accelerate==1.10.1
Requires-Dist: DeepCache==0.1.1
Requires-Dist: patchmatch-cython<0.2.0,>=0.1.4
Requires-Dist: dynamicprompts==0.31.0
Requires-Dist: spacy==3.8.7
Requires-Dist: dgenerate-ultralytics-headless==8.3.205
Requires-Dist: langcodes<4.0.0,>=3.5.0
Requires-Dist: pytorch-lightning<3.0.0,>=2.5.5
Requires-Dist: lightning-utilities<0.16.0,>=0.15.2
Requires-Dist: charset-normalizer<4.0.0,>=3.4.3
Requires-Dist: lightning-fabric<3.0.0,>=2.5.5
Requires-Dist: omegaconf<3.0.0,>=2.3.0
Requires-Dist: requests<3.0.0,>=2.32.5
Requires-Dist: av<16.0.0,>=15.0.0
Requires-Dist: pillow<12.0.0,>=11.3.0
Requires-Dist: piexif<2.0.0,>=1.1.3
Requires-Dist: jinja2<4.0.0,>=3.1.6
Requires-Dist: torch==2.8.0
Requires-Dist: torchvision==0.23.0
Requires-Dist: torchsde==0.2.6
Requires-Dist: fake-useragent==2.2.0
Requires-Dist: opencv-python-headless<5.0.0.0,>=4.12.0.88
Requires-Dist: psutil<8.0.0,>=7.1.0
Requires-Dist: sentencepiece<0.3.0,>=0.2.1
Requires-Dist: ftfy<7.0.0,>=6.3.1
Requires-Dist: beautifulsoup4<5.0.0,>=4.14.2
Requires-Dist: matplotlib<4.0.0,>=3.10.6
Requires-Dist: filelock<4.0.0,>=3.19.1
Requires-Dist: importlib_metadata<9.0.0,>=8.7.0
Requires-Dist: scipy<2.0.0,>=1.16.2
Requires-Dist: einops<0.9.0,>=0.8.1
Requires-Dist: timm<2.0.0,>=1.0.20
Requires-Dist: scikit-image<0.26.0,>=0.25.2
Requires-Dist: numpy<3.0.0,>=2.2.6
Requires-Dist: spandrel<0.5.0,>=0.4.1
Requires-Dist: spandrel_extra_arches<0.3.0,>=0.2.0
Requires-Dist: asteval<2.0.0,>=1.0.6
Requires-Dist: pygments<3.0.0,>=2.19.2
Requires-Dist: toml<0.11.0,>=0.10.2
Requires-Dist: tklinenums<2.0.0,>=1.7.1
Requires-Dist: pyrfc6266<2.0.0,>=1.0.2
Requires-Dist: protobuf<7.0.0,>=6.32.1
Requires-Dist: lark<2.0.0,>=1.3.0
Requires-Dist: packaging<26.0.0,>=25.0.0
Requires-Dist: ctranslate2<5.0.0,>=4.6.0
Requires-Dist: sacremoses==0.1.1
Requires-Dist: preshed<4.0.0,>=3.0.10
Provides-Extra: ncnn
Requires-Dist: ncnn==1.0.20250916; extra == "ncnn"
Provides-Extra: console-ui-opengl
Requires-Dist: pyopengltk==0.0.4; extra == "console-ui-opengl"
Requires-Dist: pyopengl==3.1.10; extra == "console-ui-opengl"
Requires-Dist: pyopengl-accelerate==3.1.10; extra == "console-ui-opengl"
Provides-Extra: gpt4all
Requires-Dist: gpt4all==2.8.2; extra == "gpt4all"
Provides-Extra: dev
Requires-Dist: sphinx-rtd-theme==3.0.2; extra == "dev"
Requires-Dist: poetry~=2.1.4; extra == "dev"
Provides-Extra: readthedocs
Requires-Dist: sphinx-rtd-theme==3.0.2; extra == "readthedocs"
Provides-Extra: bitsandbytes
Requires-Dist: bitsandbytes==0.48.1; extra == "bitsandbytes"
Provides-Extra: xformers
Requires-Dist: xformers==0.0.32.post2; extra == "xformers"
Provides-Extra: gpt4all-cuda
Requires-Dist: gpt4all[cuda]==2.8.2; extra == "gpt4all-cuda"
Provides-Extra: triton-windows
Requires-Dist: triton-windows==3.4.0.post20; extra == "triton-windows"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: license-file
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

.. |Documentation| image:: https://readthedocs.org/projects/dgenerate/badge/?version=5.0.0
   :target: http://dgenerate.readthedocs.io/en/5.0.0/

.. |Latest Release| image:: https://img.shields.io/github/v/release/Teriks/dgenerate
   :target: https://github.com/Teriks/dgenerate/releases/latest
   :alt: GitHub Latest Release

.. |Support Dgenerate| image:: https://img.shields.io/badge/Ko–fi-support%20dgenerate%20-hotpink?logo=kofi&logoColor=white
   :target: https://ko-fi.com/teriks
   :alt: ko-fi

=========
dgenerate
=========

|Documentation| |Latest Release| |Support Dgenerate|

``dgenerate`` is a scriptable command-line tool (and library) for generating/editing images and processing animated inputs with AI.

Whether you're generating or editing single images, batch processing hundreds of variations, or transforming entire videos frame-by-frame,
dgenerate provides a flexible, scriptable interface for a multitude of image generation and editing tasks.

For the extensive usage manual, manual installation guide, and API documentation, visit `readthedocs <http://dgenerate.readthedocs.io/en/5.0.0/>`_.

What You Can Do
===============

Image Generation
----------------

* Generate images using a number of popular model architectures such as: SD, SDXL, SD3, Flux, and Kolors
* Batch process multiple parameter combinations combinatorially to generate variations
* Run large models on limited hardware with inference optimizations and quantization
* Utilize models from HuggingFace and CivitAI for generation
* Advanced prompt weighting (LPW), SD-WebUI (Common syntax), InvokeAI syntax, and ``llm4gen`` (SD1.5 only)
* Control Nets, T2I Adapters, IP Adapters, LoRA, and Textual Inversion (embeddings)
* Text to image, image to image, and inpainting
* Diffusion-based image upscaling

Image Processing
----------------

* Easily chain image processors together for advanced scripted image manipulation
* Utilize built-in image processors for edge detection, depth mapping, segmentation, feature detection, and more
* Run upscaling / image restoration models such as ESRGAN, SwinIR, etc... via `spandrel <https://github.com/chaiNNer-org/spandrel>`_
* Run image processors generically on any image

Animation & Video Processing
----------------------------

* Transform videos into artistic non-temporally consistent animations
* Process GIF, WebP, APNG, MP4, and any other video format supported by `av <https://github.com/PyAV-Org/PyAV>`_ (ffmpeg)
* Memory-efficient, streamed processing of video content from disk
* Apply image processors to any animated input, for example upscaling / classification / mask generation

Scripting
---------

* Utilize the built-in shell language to script generation tasks, work in REPL mode from the Console UI
* Write scripted workflows with intelligent VRAM/RAM memory management, garbage collection, and caching
* Write plugins such as image processors, prompt weighters, shell language features, etc. in Python if desired

Getting Started
===============

Quick Install
-------------

Download an install wizard for your platform from the `releases page <https://github.com/Teriks/dgenerate/releases>`_ for a hassle-free setup into an isolated Python environment.

Manual Install
--------------

* `Windows <https://dgenerate.readthedocs.io/en/5.0.0/manual.html#windows-install>`_
* `Linux / WSL <https://dgenerate.readthedocs.io/en/5.0.0/manual.html#linux-or-wsl-install>`_
* `Linux ROCm <https://dgenerate.readthedocs.io/en/5.0.0/manual.html#linux-with-rocm-amd-cards>`_
* `MacOS <https://dgenerate.readthedocs.io/en/5.0.0/manual.html#macos-install-apple-silicon-only>`_
* `Google Colab <https://dgenerate.readthedocs.io/en/5.0.0/manual.html#google-colab-install>`_
* `XPU (Intel) <https://dgenerate.readthedocs.io/en/5.0.0/manual.html#install-with-xpu-support>`_
* `Installing From Development Branches <https://dgenerate.readthedocs.io/en/5.0.0/manual.html#installing-from-development-branches>`_

System Requirements
-------------------

* **GPU**: NVIDIA (CUDA 12.1+), AMD (ROCm on Linux), or Apple Silicon
* **Python**: 3.11 to 3.13
* **OS**: Windows, macOS, or Linux

Note: CPU rendering is possible but extremely slow unless the given model is tailored for it.

Two Ways to Use dgenerate
=========================

Command Line
------------

Perfect for automation and batch processing:

.. code-block:: bash

    dgenerate stable-diffusion-v1-5/stable-diffusion-v1-5 --prompts "a cute cat" --inference-steps 15 20 30

    dgenerate --file workflow-config.dgen

Interactive GUI
---------------


.. code-block:: bash

    # launch the Console UI

    dgenerate --console


Features a syntax-highlighting console / editor:

* REPL / code editor for the built in shell language to assist with building complex workflows
* OpenGL accelerated image preview, featuring smooth zoom / pan, and bounding box / coordinate picker
* Various templating utilities (recipes, and URI builders) for quickly creating scripts and working interactively
* In editor documentation for all arguments, and built in image processors / plugins
* Lightweight multiplatform Tkinter-based UI

----

.. image:: https://raw.githubusercontent.com/Teriks/dgenerate-readme-embeds/master/ui5.gif
   :alt: Console UI Demo
