adapted code from https://github.com/comfyanonymous/ComfyUI/pull/3370
TODO: check if virtual scheduler tcd is needed for using sampling_base ModelSamplingDiscreteDistilled or if it's better to use sgm_uniform directly without patching
* fix: load image number from preset (#2611)
* fix: add default_image_number to preset handling
* fix: use minimum image number of preset and config to prevent UI overflow
* fix: use correct base dimensions for outpaint mask padding (#2612)
* fix: add Civitai compatibility for LoRAs in a1111 metadata scheme by switching schema (#2615)
* feat: update sha256 generation functions
https://github.com/lllyasviel/stable-diffusion-webui-forge/blob/29be1da7cf2b5dccfc70fbdd33eb35c56a31ffb7/modules/hashes.py
* feat: add compatibility for LoRAs in a1111 metadata scheme
* feat: add backwards compatibility
* refactor: extract remove_special_loras
* fix: correctly apply LoRA weight for legacy schema
* docs: bump version number to 2.3.1, add changelog (#2616)
* feat:support download huggingface files from a mirror site
---------
Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com>
* feat: use consistent file name in gradio
returns and uses filepaths instead of numpy image by saving to temp dir
uses double the temp dir file storage on disk as it saves to temp dir and gradio temp dir when displaying the image, but reuses logged output image
* feat: delete temp images after yielding to gradio
* feat: use args temp path if given
* chore: code cleanup, remove redundant if statement
Manuel Schmid