Dgenerate

Fix missing ``upscaler-ncnn`` processor in Console UI recipe forms.

Backport fixes from: https://github.com/Teriks/dgenerate/tree/flux_newpipes

Fix optional arguments: ``--sdxl-refiner-inference-steps``, ``--sdxl-refiner-guidance-scales``, and ``--sdxl-refiner-guidance-rescales`` not being considered when calculating the number of generation steps displayed to the user.

Minor fix for example runner script, inform user when running from an environment where dgenerate is not accessible as an importable package. In this case, dgenerate will run in a subprocess by invoking the command in a shell if it is available.

Upgrade ``asteval`` to include error handling fixes from new release, instead of monkey patching it inside ``dgenerate``.

* Basic inpainting is now supported with Stable Diffusion 3

* Config directive ``\setp`` can be used to evaluate python ternary statements during template variable assignment. i.e. ``\setp my_var "Yes" if True else "No"``

* Improved config error reporting. 1 indexed line number in the interpreter to align with Console UI line numbering. Better pinpointing of the error line number inside "here template" control structures involving Jinja. Patches for issues with ``asteval`` affecting syntax error output.

* PyPI Packaging now supports installing dgenerate with the ROCm torch backend on Linux, allowing for use with AMD Cards / Accelerators. See installation documentation: [Linux with ROCm (AMD Cards)](https://github.com/Teriks/dgenerate?tab=readme-ov-file#linux-with-rocm-amd-cards)

HuggingFace repository file link for transformer involved in `Flux (Schnell quantized)` console recipe had moved. Updated link.

Better error message when a HuggingFace repository is not accessible due to lack of authentication.

Console output window `Clear` right click context menu functionality bug fix. Output window started in editable state, it should be disabled for text input and only enabled temporarily for writes internally. Improper state management resulted in inability to write new output to the window after using `Clear` from the UI menu, as the text box was left in a disabled UI state.

The Stable Cascade Decoder and SDXL Refiner now get placed on the correct device, they were defaulting to ``cuda`` instead of honoring ``--device``. This became apparent on MacOS where they were attempting to use CUDA instead of MPS causing an exception.