Dgenerate

v3.4.4 release with Windows installer.

Due to the size of the packaged python environment, the installer is within a multi-part zip file.

The multipart zip can be extracted using 7-Zip: https://www.7-zip.org/

Download both ``dgenerate_installer.zip.001`` and ``dgenerate_installer.zip.002`` to a folder.

Unzip ``dgenerate_installer.zip.001`` to a directory (Right click, 7-Zip -> Extract to "dgenerate_installer") and then run ``dgenerate_installer\dgenerate.msi`` to install.

dgenerate will be installed under ``C:\Program Files\dgenerate`` by default with an isolated python environment provided.

The install directory will be added to PATH, and dgenerate will be available from the command line.

Portable Install

A portable install is provided via ``dgenerate_portable.zip.001`` and ``dgenerate_portable.zip.002``, these contain
nothing but the dgenerate executable and a frozen python environment which can be placed anywhere.

Fixes

* Fix for Stable Cascade model type not properly honoring ``--unet`` and ``--unet2`` due to pipeline constructor argument naming differences.

Fixes

* Fix for Stable Cascade model type not honoring ``--batch-size`` value, multiple images can now be generated in batch at once by the prior model, and processed individually by the decoder model.

Fixes

* Fix for Stable Cascade models not honoring ``--seeds`` values, leading to the inability to produce deterministic output when specific seeds were provided for generation.

Fixes

* Fix broken pix2pix pipeline selection for stable diffusion and stable diffusion XL that rendered pix2pix unusable

New Features / Fixes

* Ability to generate images with Stable Cascade, supports txt2img and img2img mode, compatible with ``--loras``, see: [examples](https://github.com/Teriks/dgenerate/tree/v3.4.0/examples/stablecascade)
* Ability to specify a custom UNet for SDXL Refiners and Stable Cascade decoders using ``--unet2`` option
* Fix dependency issue preventing installation on nix* systems
* Fix to ``--output-metadata`` and ``--output-configs`` excluding last line of config if ending in an opt with no argument
* Fix ``dtype=float16`` mode of ``upscaler`` image processor for models that support ``float16``

New Features / Fixes

* diffusers v0.27.2
* latest torch & cuda, torch 2.2.2 - with cuda 12.1
* tile ``overlap`` plugin argument of the upscaler image processor can be set to 0 without error
* ``tile`` plugin argument of the upscaler image processor can be set to 0 to force disable tiling
* new ``force-tiling`` boolean argument of the upscaler image processor, allows forcing external tiling for models where it is discouraged
* ``dtype`` of upscaler models used by the upscaler image processor can be selected via a plugin argument ``dtype=float32`` or ``dtype=float16``, only some models may support ``float16``
* auto tile size estimation in the upscaler via ``tile=auto`` plugin argument value
* ``--auth-token`` bug fixes, not being honored correctly in some cases