* 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>
* Add files via upload
In anime.json, at Line 36,
replace "Fooocus Negative" with "Fooocus Semi Realistic"
* Add files via upload
In sdxl_styles_fooocus.json, insert this text at Line 6:
{
"name": "Fooocus Semi Realistic",
"negative_prompt": "(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3)"
},
* Add files via upload
Popup image for the new "Fooocus Semi Realistic" style
* Update sdxl_styles_fooocus.json
Removed "grayscale, bw" from the proposed Fooocus Realistic entry at Line 6 of sdxl_styles_fooocus.json
* refactor: cleanup files
* feat: use default model to create thumbnail
juggernautv8, seed 0, 1024x1024, no LoRAs, only this style, positive prompt "cat"
---------
Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
Co-authored-by: Manuel Schmid <dev@mash1t.de>
* Raise Error on bad decode
* Move task arg pop to try block
* fix: prevent empty task from getting queued
---------
Co-authored-by: Manuel Schmid <dev@mash1t.de>
* add preset selection
uses meta parsing to set presets in user session (UI elements only)
* add LoRA handling
* use default config as fallback value
* add preset refresh on "Refresh All Files" click
* add special handling for default_styles and default_aspect_ratio
* sort styles after preset change
* code cleanup
* download missing models from preset
* set default refiner to "None" in preset realistic
* use state_is_generating for preset selection change
* DRY output parameter handling
* feat: add argument --disable-preset-selection
useful for cloud provisioning to prevent model switches and keep models loaded
* feat: keep prompt when not set in preset, use more robust syntax
* fix: add default return values when preset download is disabled
https://github.com/mashb1t/Fooocus/issues/20
* feat: add translation for preset label
* refactor: unify preset loading methods in config
* refactor: code cleanup
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.0.1+cu118 with CUDA 1108 (you have 2.1.0+cu121)
Python 3.10.11 (you have 3.10.9)
* colab: balance the use of RAM
enables the use of VRAM memory so as not to saturate the system RAM
* feat: use --always-high-vram by default for Colab, adjust readme
---------
Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
Manuel Schmid