From 310d6b9075c6edb3b884bd2a41e1c17259b141e1 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 17 Feb 2024 11:35:36 +0300 Subject: [PATCH 01/28] update changelog --- CHANGELOG.md | 121 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 121 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 67429bbff..9fd366fa7 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,124 @@ +## 1.8.0-RC + +### Features: +* Update torch to version 2.1.2 +* Soft Inpainting ([#14208](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14208)) +* FP8 support ([#14031](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14031), [#14327](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14327)) +* Support for SDXL-Inpaint Model ([#14390](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14390)) +* Use Spandrel for upscaling and face restoration architectures ([#14425](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14425), [#14467](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14467), [#14473](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14473), [#14474](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14474), [#14477](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14477), [#14476](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14476), [#14484](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14484), [#14500](https://github.com/AUTOMATIC1111/stable-difusion-webui/pull/14500), [#14501](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14501), [#14504](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14504), [#14524](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14524), [#14809](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14809)) +* Automatic backwards version compatibility (when loading infotexts from old images with program version specified, will add compatibility settings) +* Implement zero terminal SNR noise schedule option (**[SEED BREAKING CHANGE](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Seed-breaking-changes#180-dev-170-225-2024-01-01---zero-terminal-snr-noise-schedule-option)**, [#14145](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14145)) +* Add a [✨] button to run hires fix on selected image in the gallery (with help from [#14598](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14598), [#14626](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14626), [#14728](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14728)) +* [Separate assets repository](https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets); serve fonts locally rather than from google's servers +* Official LCM Sampler Support ([#14583](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14583)) +* Add support for DAT upscaler models ([#14690](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14690)) +* Extra Networks Tree View ([#14588](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14588), [#14900](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14900)) +* NPU Support ([#14801](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14801)) +* Propmpt comments support + +### Minor: +* Allow pasting in WIDTHxHEIGHT strings into the width/height fields ([#14296](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14296)) +* add option: Live preview in full page image viewer ([#14230](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14230), [#14307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14307)) +* Add keyboard shortcuts for generate/skip/interrupt ([#14269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14269)) +* Better TCMALLOC support on different platforms ([#14227](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14227), [#14883](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14883), [#14910](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14910)) +* Lora not found warning ([#14464](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14464)) +* Adding negative prompts to Loras in extra networks ([#14475](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14475)) +* xyz_grid: allow varying the seed along an axis separate from axis options ([#12180](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12180)) +* option to convert VAE to bfloat16 (implementation of [#9295](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9295)) +* Better IPEX support ([#14229](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14229), [#14353](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14353), [#14559](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14559), [#14562](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14562), [#14597](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14597)) +* Option to interrupt after current generation rather than immediately ([#13653](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13653), [#14659](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14659)) +* Fullscreen Preview control fading/disable ([#14291](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14291)) +* Finer settings freezing control ([#13789](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13789)) +* Increase Upscaler Limits ([#14589](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14589)) +* Adjust brush size with hotkeys ([#14638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14638)) +* Add checkpoint info to csv log file when saving images ([#14663](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14663)) +* Make more columns resizable ([#14740](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14740), [#14884](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14884)) +* Add an option to not overlay original image for inpainting for #14727 +* Add Pad conds v0 option +* Add "Interrupting..." placeholder. +* Button for refresh extensions list ([#14857](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14857)) +* Add an option to disable normalization after calculating emphasis. ([#14874](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14874)) +* When counting tokens, also include enabled styles (can be disabled in settings to revert to previous behavior) + +### Extensions and API: +* Enable task ids for API ([#14314](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14314)) +* add override_settings support for infotext API +* rename generation_parameters_copypaste module to infotext_utils +* prevent crash due to Script __init__ exception ([#14407](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14407)) +* Bump numpy to 1.26.2 ([#14471](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14471)) +* Add utility to inspect a model's dtype/device ([#14478](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14478)) +* Implement general forward method for all method in built-in lora ext ([#14547](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14547)) +* Execute model_loaded_callback after moving to target device ([#14563](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14563)) +* Add self to CFGDenoiserParams ([#14573](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14573)) +* Allow TLS with API only mode (--nowebui) ([#14593](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14593)) +* New callback: postprocess_image_after_composite ([#14657](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14657)) +* modules/api/api.py: add api endpoint to refresh embeddings list ([#14715](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14715)) +* set_named_arg ([#14773](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14773)) +* add before_token_counter callback and use it for prompt comments + +### Performance +* Massive performance improvement for extra networks directories with a huge number of files in them in an attempt to tackle #14507 ([#14528](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14528)) +* Reduce unnecessary re-indexing extra networks directory ([#14512](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14512)) +* Avoid unnecessary `isfile`/`exists` calls ([#14527](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14527)) + +### Bug Fixes: +* fix multiple bugs related to styles multi-file support ([#14203](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14203), [#14276](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14276), [#14707](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14707)) +* Lora fixes ([#14300](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14300), [#14237](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14237), [#14546](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14546), [#14726](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14726)) +* Re-add setting lost as part of e294e46 ([#14266](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14266)) +* fix extras caption BLIP ([#14330](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14330)) +* include infotext into saved init image for img2img ([#14452](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14452)) +* xyz grid handle axis_type is None ([#14394](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14394)) +* Update Added (Fixed) IPV6 Functionality When there is No Webui Argument Passed webui.py ([#14354](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14354)) +* fix API thread safe issues of txt2img and img2img ([#14421](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14421)) +* handle selectable script_index is None ([#14487](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14487)) +* handle config.json failed to load ([#14525](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14525), [#14767](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14767)) +* paste infotext cast int as float ([#14523](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14523)) +* Ensure GRADIO_ANALYTICS_ENABLED is set early enough ([#14537](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14537)) +* Fix logging configuration again ([#14538](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14538)) +* Handle CondFunc exception when resolving attributes ([#14560](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14560)) +* Fix extras big batch crashes ([#14699](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14699)) +* Fix using wrong model caused by alias ([#14655](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14655)) +* Add # to the invalid_filename_chars list ([#14640](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14640)) +* Fix extension check for requirements ([#14639](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14639)) +* Fix tab indexes are reset after restart UI ([#14637](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14637)) +* Fix nested manual cast ([#14689](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14689)) +* Keep postprocessing upscale selected tab after restart ([#14702](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14702)) +* XYZ grid: filter out blank vals when axis is int or float type (like int axis seed) ([#14754](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14754)) +* fix CLIP Interrogator topN regex ([#14775](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14775)) +* Fix dtype error in MHA layer/change dtype checking mechanism for manual cast ([#14791](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14791)) +* catch load style.csv error ([#14814](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14814)) +* fix error when editing extra networks card +* fix extra networks metadata failing to work properly when you create the .json file with metadata for the first time. +* util.walk_files extensions case insensitive ([#14879](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14879)) +* if extensions page not loaded, prevent apply ([#14873](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14873)) +* call the right function for token counter in img2img +* Fix the bugs that search/reload will disappear when using other ExtraNetworks extensions ([#14939](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14939)) +* Gracefully handle mtime read exception from cache ([#14933](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14933)) +* Only trigger interrupt on `Esc` when interrupt button visible ([#14932](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14932)) +* Disable prompt token counters option actually disables token counting rather than just hiding results. + +### Other: +* Assign id for "extra_options". Replace numeric field with slider. ([#14270](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14270)) +* change state dict comparison to ref compare ([#14216](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14216)) +* Bump torch-rocm to 5.6/5.7 ([#14293](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14293)) +* Base output path off data path ([#14446](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14446)) +* reorder training preprocessing modules in extras tab ([#14367](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14367)) +* Remove `cleanup_models` code ([#14472](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14472)) +* only rewrite ui-config when there is change ([#14352](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14352)) +* Fix lint issue from 501993eb ([#14495](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14495)) +* Update README.md ([#14548](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14548)) +* hires button, fix seeds () +* Logging: set formatter correctly for fallback logger too ([#14618](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14618)) +* Read generation info from infotexts rather than json for internal needs (save, extract seed from generated pic) ([#14645](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14645)) +* improve get_crop_region ([#14709](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14709)) +* Bump safetensors' version to 0.4.2 ([#14782](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14782)) +* add tooltip create_submit_box ([#14803](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14803)) +* extensions tab table row hover highlight ([#14885](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14885)) +* Always add timestamp to displayed image ([#14890](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14890)) +* Added core.filemode=false so doesn't track changes in file permission… ([#14930](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14930)) +* Normalize command-line argument paths ([#14934](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14934)) +* Use original App Title in progress bar ([#14916](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14916)) + ## 1.7.0 ### Features: From 4652fc5ac36df57add76aa2b012a2d7da57963dd Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 17 Feb 2024 11:40:53 +0300 Subject: [PATCH 02/28] prevent escape button causing an interrupt when no generation has been made yet --- script.js | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/script.js b/script.js index 25cf0973a..f069b1ef0 100644 --- a/script.js +++ b/script.js @@ -167,7 +167,7 @@ document.addEventListener('keydown', function(e) { const lightboxModal = document.querySelector('#lightboxModal'); if (!globalPopup || globalPopup.style.display === 'none') { if (document.activeElement === lightboxModal) return; - if (interruptButton.style.display !== 'none') { + if (interruptButton.style.display === 'block') { interruptButton.click(); e.preventDefault(); } From 3345218439ab0e74e2b6ea6e9d6291885a6e8fb5 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 17 Feb 2024 13:21:08 +0300 Subject: [PATCH 03/28] Update comment for Pad prompt/negative prompt v0 to add a warning about truncation, make it override the v1 implementation --- modules/sd_samplers_cfg_denoiser.py | 6 +++--- modules/shared_options.py | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/modules/sd_samplers_cfg_denoiser.py b/modules/sd_samplers_cfg_denoiser.py index 941dff4b3..a73d3b036 100644 --- a/modules/sd_samplers_cfg_denoiser.py +++ b/modules/sd_samplers_cfg_denoiser.py @@ -220,10 +220,10 @@ class CFGDenoiser(torch.nn.Module): self.padded_cond_uncond = False self.padded_cond_uncond_v0 = False - if shared.opts.pad_cond_uncond and tensor.shape[1] != uncond.shape[1]: - tensor, uncond = self.pad_cond_uncond(tensor, uncond) - elif shared.opts.pad_cond_uncond_v0 and tensor.shape[1] != uncond.shape[1]: + if shared.opts.pad_cond_uncond_v0 and tensor.shape[1] != uncond.shape[1]: tensor, uncond = self.pad_cond_uncond_v0(tensor, uncond) + elif shared.opts.pad_cond_uncond and tensor.shape[1] != uncond.shape[1]: + tensor, uncond = self.pad_cond_uncond(tensor, uncond) if tensor.shape[1] == uncond.shape[1] or skip_uncond: if is_edit_model: diff --git a/modules/shared_options.py b/modules/shared_options.py index e1d11c8e0..25b47aa19 100644 --- a/modules/shared_options.py +++ b/modules/shared_options.py @@ -211,7 +211,7 @@ options_templates.update(options_section(('optimizations', "Optimizations", "sd" "token_merging_ratio_img2img": OptionInfo(0.0, "Token merging ratio for img2img", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}).info("only applies if non-zero and overrides above"), "token_merging_ratio_hr": OptionInfo(0.0, "Token merging ratio for high-res pass", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}, infotext='Token merging ratio hr').info("only applies if non-zero and overrides above"), "pad_cond_uncond": OptionInfo(False, "Pad prompt/negative prompt", infotext='Pad conds').info("improves performance when prompt and negative prompt have different lengths; changes seeds"), - "pad_cond_uncond_v0": OptionInfo(False, "Pad prompt/negative prompt (v0)", infotext='Pad conds v0').info("alternative implementation for the above; used prior to 1.6.0 for DDIM sampler; ignored if the above is set; changes seeds"), + "pad_cond_uncond_v0": OptionInfo(False, "Pad prompt/negative prompt (v0)", infotext='Pad conds v0').info("alternative implementation for the above; used prior to 1.6.0 for DDIM sampler; overrides the above if set; WARNING: truncates negative prompt if it's too long; changes seeds"), "persistent_cond_cache": OptionInfo(True, "Persistent cond cache").info("do not recalculate conds from prompts if prompts have not changed since previous calculation"), "batch_cond_uncond": OptionInfo(True, "Batch cond/uncond").info("do both conditional and unconditional denoising in one batch; uses a bit more VRAM during sampling, but improves speed; previously this was controlled by --always-batch-cond-uncond comandline argument"), "fp8_storage": OptionInfo("Disable", "FP8 weight", gr.Radio, {"choices": ["Disable", "Enable for SDXL", "Enable"]}).info("Use FP8 to store Linear/Conv layers' weight. Require pytorch>=2.1.0."), From cb52279c3e7cf145cc1b284b6a05c883e6995c9f Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 17 Feb 2024 21:30:21 +0300 Subject: [PATCH 04/28] Merge pull request #14947 from AUTOMATIC1111/open-button option "open image button" open the actual dir --- modules/shared_options.py | 1 + modules/ui_common.py | 52 ++++++++++++++++++++++++++------------- modules/ui_tempdir.py | 15 +++++++++++ 3 files changed, 51 insertions(+), 17 deletions(-) diff --git a/modules/shared_options.py b/modules/shared_options.py index 25b47aa19..bb3752ba6 100644 --- a/modules/shared_options.py +++ b/modules/shared_options.py @@ -284,6 +284,7 @@ options_templates.update(options_section(('ui_gallery', "Gallery", "ui"), { "sd_webui_modal_lightbox_icon_opacity": OptionInfo(1, "Full page image viewer: control icon unfocused opacity", gr.Slider, {"minimum": 0.0, "maximum": 1, "step": 0.01}, onchange=shared.reload_gradio_theme).info('for mouse only').needs_reload_ui(), "sd_webui_modal_lightbox_toolbar_opacity": OptionInfo(0.9, "Full page image viewer: tool bar opacity", gr.Slider, {"minimum": 0.0, "maximum": 1, "step": 0.01}, onchange=shared.reload_gradio_theme).info('for mouse only').needs_reload_ui(), "gallery_height": OptionInfo("", "Gallery height", gr.Textbox).info("can be any valid CSS value, for example 768px or 20em").needs_reload_ui(), + "open_dir_button_choice": OptionInfo("Subdirectory", "What directory the [📂] button opens", gr.Radio, {"choices": ["Output Root", "Subdirectory", "Subdirectory (even temp dir)"]}), })) options_templates.update(options_section(('ui_alternatives', "UI alternatives", "ui"), { diff --git a/modules/ui_common.py b/modules/ui_common.py index 29fe7d0e9..cf1b8b32c 100644 --- a/modules/ui_common.py +++ b/modules/ui_common.py @@ -9,7 +9,7 @@ import sys import gradio as gr import subprocess as sp -from modules import call_queue, shared +from modules import call_queue, shared, ui_tempdir from modules.infotext_utils import image_from_url_text import modules.images from modules.ui_components import ToolButton @@ -164,29 +164,43 @@ class OutputPanel: def create_output_panel(tabname, outdir, toprow=None): res = OutputPanel() - def open_folder(f): + def open_folder(f, images=None, index=None): + if shared.cmd_opts.hide_ui_dir_config: + return + + try: + if 'Sub' in shared.opts.open_dir_button_choice: + image_dir = os.path.split(images[index]["name"].rsplit('?', 1)[0])[0] + if 'temp' in shared.opts.open_dir_button_choice or not ui_tempdir.is_gradio_temp_path(image_dir): + f = image_dir + except Exception: + pass + if not os.path.exists(f): - print(f'Folder "{f}" does not exist. After you create an image, the folder will be created.') + msg = f'Folder "{f}" does not exist. After you create an image, the folder will be created.' + print(msg) + gr.Info(msg) return elif not os.path.isdir(f): - print(f""" + msg = f""" WARNING An open_folder request was made with an argument that is not a folder. This could be an error or a malicious attempt to run code on your computer. Requested path was: {f} -""", file=sys.stderr) +""" + print(msg, file=sys.stderr) + gr.Warning(msg) return - if not shared.cmd_opts.hide_ui_dir_config: - path = os.path.normpath(f) - if platform.system() == "Windows": - os.startfile(path) - elif platform.system() == "Darwin": - sp.Popen(["open", path]) - elif "microsoft-standard-WSL2" in platform.uname().release: - sp.Popen(["wsl-open", path]) - else: - sp.Popen(["xdg-open", path]) + path = os.path.normpath(f) + if platform.system() == "Windows": + os.startfile(path) + elif platform.system() == "Darwin": + sp.Popen(["open", path]) + elif "microsoft-standard-WSL2" in platform.uname().release: + sp.Popen(["wsl-open", path]) + else: + sp.Popen(["xdg-open", path]) with gr.Column(elem_id=f"{tabname}_results"): if toprow: @@ -213,8 +227,12 @@ Requested path was: {f} res.button_upscale = ToolButton('✨', elem_id=f'{tabname}_upscale', tooltip="Create an upscaled version of the current image using hires fix settings.") open_folder_button.click( - fn=lambda: open_folder(shared.opts.outdir_samples or outdir), - inputs=[], + fn=lambda images, index: open_folder(shared.opts.outdir_samples or outdir, images, index), + _js="(y, w) => [y, selected_gallery_index()]", + inputs=[ + res.gallery, + open_folder_button, # placeholder for index + ], outputs=[], ) diff --git a/modules/ui_tempdir.py b/modules/ui_tempdir.py index 91f40ea42..621ed1eca 100644 --- a/modules/ui_tempdir.py +++ b/modules/ui_tempdir.py @@ -81,3 +81,18 @@ def cleanup_tmpdr(): filename = os.path.join(root, name) os.remove(filename) + + +def is_gradio_temp_path(path): + """ + Check if the path is a temp dir used by gradio + """ + path = Path(path) + if shared.opts.temp_dir and path.is_relative_to(shared.opts.temp_dir): + return True + if gradio_temp_dir := os.environ.get("GRADIO_TEMP_DIR"): + if path.is_relative_to(gradio_temp_dir): + return True + if path.is_relative_to(Path(tempfile.gettempdir()) / "gradio"): + return True + return False From c7808825b12cc5591012b50d93f27e4bce99ec5c Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 17 Feb 2024 21:38:19 +0300 Subject: [PATCH 05/28] update changelog --- CHANGELOG.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9fd366fa7..cfebc11c7 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -39,8 +39,10 @@ * Button for refresh extensions list ([#14857](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14857)) * Add an option to disable normalization after calculating emphasis. ([#14874](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14874)) * When counting tokens, also include enabled styles (can be disabled in settings to revert to previous behavior) +* Configuration for the [📂] button for image gallery ([#14947](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14947)) ### Extensions and API: +* Removed packages from requirements: basicsr, gfpgan, realesrgan; as well as their dependencies: absl-py, addict, beautifulsoup4, future, gdown, grpcio, importlib-metadata, lmdb, lpips, Markdown, platformdirs, PySocks, soupsieve, tb-nightly, tensorboard-data-server, tomli, Werkzeug, yapf, zipp, soupsieve * Enable task ids for API ([#14314](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14314)) * add override_settings support for infotext API * rename generation_parameters_copypaste module to infotext_utils From 92ab0ef7d65ededa758f81e52cf4f48f72d13564 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Mon, 19 Feb 2024 10:05:30 +0300 Subject: [PATCH 06/28] Merge pull request #14871 from v0xie/boft Support inference with LyCORIS BOFT networks --- extensions-builtin/Lora/network_oft.py | 58 +++++++++++++++++++++----- 1 file changed, 48 insertions(+), 10 deletions(-) diff --git a/extensions-builtin/Lora/network_oft.py b/extensions-builtin/Lora/network_oft.py index d1c46a4b2..d658ad109 100644 --- a/extensions-builtin/Lora/network_oft.py +++ b/extensions-builtin/Lora/network_oft.py @@ -22,6 +22,8 @@ class NetworkModuleOFT(network.NetworkModule): self.org_module: list[torch.Module] = [self.sd_module] self.scale = 1.0 + self.is_kohya = False + self.is_boft = False # kohya-ss if "oft_blocks" in weights.w.keys(): @@ -29,13 +31,19 @@ class NetworkModuleOFT(network.NetworkModule): self.oft_blocks = weights.w["oft_blocks"] # (num_blocks, block_size, block_size) self.alpha = weights.w["alpha"] # alpha is constraint self.dim = self.oft_blocks.shape[0] # lora dim - # LyCORIS + # LyCORIS OFT elif "oft_diag" in weights.w.keys(): - self.is_kohya = False self.oft_blocks = weights.w["oft_diag"] # self.alpha is unused self.dim = self.oft_blocks.shape[1] # (num_blocks, block_size, block_size) + # LyCORIS BOFT + if weights.w["oft_diag"].dim() == 4: + self.is_boft = True + self.rescale = weights.w.get('rescale', None) + if self.rescale is not None: + self.rescale = self.rescale.reshape(-1, *[1]*(self.org_module[0].weight.dim() - 1)) + is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear] is_conv = type(self.sd_module) in [torch.nn.Conv2d] is_other_linear = type(self.sd_module) in [torch.nn.MultiheadAttention] # unsupported @@ -51,6 +59,13 @@ class NetworkModuleOFT(network.NetworkModule): self.constraint = self.alpha * self.out_dim self.num_blocks = self.dim self.block_size = self.out_dim // self.dim + elif self.is_boft: + self.constraint = None + self.boft_m = weights.w["oft_diag"].shape[0] + self.block_num = weights.w["oft_diag"].shape[1] + self.block_size = weights.w["oft_diag"].shape[2] + self.boft_b = self.block_size + #self.block_size, self.block_num = butterfly_factor(self.out_dim, self.dim) else: self.constraint = None self.block_size, self.num_blocks = factorization(self.out_dim, self.dim) @@ -68,14 +83,37 @@ class NetworkModuleOFT(network.NetworkModule): R = oft_blocks.to(orig_weight.device) - # This errors out for MultiheadAttention, might need to be handled up-stream - merged_weight = rearrange(orig_weight, '(k n) ... -> k n ...', k=self.num_blocks, n=self.block_size) - merged_weight = torch.einsum( - 'k n m, k n ... -> k m ...', - R, - merged_weight - ) - merged_weight = rearrange(merged_weight, 'k m ... -> (k m) ...') + if not self.is_boft: + # This errors out for MultiheadAttention, might need to be handled up-stream + merged_weight = rearrange(orig_weight, '(k n) ... -> k n ...', k=self.num_blocks, n=self.block_size) + merged_weight = torch.einsum( + 'k n m, k n ... -> k m ...', + R, + merged_weight + ) + merged_weight = rearrange(merged_weight, 'k m ... -> (k m) ...') + else: + # TODO: determine correct value for scale + scale = 1.0 + m = self.boft_m + b = self.boft_b + r_b = b // 2 + inp = orig_weight + for i in range(m): + bi = R[i] # b_num, b_size, b_size + if i == 0: + # Apply multiplier/scale and rescale into first weight + bi = bi * scale + (1 - scale) * eye + inp = rearrange(inp, "(c g k) ... -> (c k g) ...", g=2, k=2**i * r_b) + inp = rearrange(inp, "(d b) ... -> d b ...", b=b) + inp = torch.einsum("b i j, b j ... -> b i ...", bi, inp) + inp = rearrange(inp, "d b ... -> (d b) ...") + inp = rearrange(inp, "(c k g) ... -> (c g k) ...", g=2, k=2**i * r_b) + merged_weight = inp + + # Rescale mechanism + if self.rescale is not None: + merged_weight = self.rescale.to(merged_weight) * merged_weight updown = merged_weight.to(orig_weight.device) - orig_weight.to(merged_weight.dtype) output_shape = orig_weight.shape From 532c34082903ca03a17a847d5120647ef418190d Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Mon, 19 Feb 2024 10:07:57 +0300 Subject: [PATCH 07/28] update changelog --- CHANGELOG.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index cfebc11c7..c7bfc1c98 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -34,12 +34,13 @@ * Add checkpoint info to csv log file when saving images ([#14663](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14663)) * Make more columns resizable ([#14740](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14740), [#14884](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14884)) * Add an option to not overlay original image for inpainting for #14727 -* Add Pad conds v0 option +* Add Pad conds v0 option to support same generation with DDIM as before 1.6.0 * Add "Interrupting..." placeholder. * Button for refresh extensions list ([#14857](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14857)) * Add an option to disable normalization after calculating emphasis. ([#14874](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14874)) * When counting tokens, also include enabled styles (can be disabled in settings to revert to previous behavior) * Configuration for the [📂] button for image gallery ([#14947](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14947)) +* Support inference with LyCORIS BOFT networks ([#14871](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14871)) ### Extensions and API: * Removed packages from requirements: basicsr, gfpgan, realesrgan; as well as their dependencies: absl-py, addict, beautifulsoup4, future, gdown, grpcio, importlib-metadata, lmdb, lpips, Markdown, platformdirs, PySocks, soupsieve, tb-nightly, tensorboard-data-server, tomli, Werkzeug, yapf, zipp, soupsieve From 140d58b51213c0a025da475a40ef0b8efbc33587 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Mon, 19 Feb 2024 18:06:05 +0300 Subject: [PATCH 08/28] Merge pull request #14966 from light-and-ray/avoid_doble_upscaling_in_inpaint [bug] avoid doble upscaling in inpaint --- modules/processing.py | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/modules/processing.py b/modules/processing.py index f4aa165de..d208a922d 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -74,16 +74,18 @@ def uncrop(image, dest_size, paste_loc): def apply_overlay(image, paste_loc, overlay): if overlay is None: - return image + return image, image.copy() if paste_loc is not None: image = uncrop(image, (overlay.width, overlay.height), paste_loc) + original_denoised_image = image.copy() + image = image.convert('RGBA') image.alpha_composite(overlay) image = image.convert('RGB') - return image + return image, original_denoised_image def create_binary_mask(image, round=True): if image.mode == 'RGBA' and image.getextrema()[-1] != (255, 255): @@ -1021,7 +1023,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if p.color_corrections is not None and i < len(p.color_corrections): if save_samples and opts.save_images_before_color_correction: - image_without_cc = apply_overlay(image, p.paste_to, overlay_image) + image_without_cc, _ = apply_overlay(image, p.paste_to, overlay_image) images.save_image(image_without_cc, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-before-color-correction") image = apply_color_correction(p.color_corrections[i], image) @@ -1029,12 +1031,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: # that is being composited over the original image, # we need to keep the original image around # and use it in the composite step. - original_denoised_image = image.copy() - - if p.paste_to is not None: - original_denoised_image = uncrop(original_denoised_image, (overlay_image.width, overlay_image.height), p.paste_to) - - image = apply_overlay(image, p.paste_to, overlay_image) + image, original_denoised_image = apply_overlay(image, p.paste_to, overlay_image) if p.scripts is not None: pp = scripts.PostprocessImageArgs(image) From 052fbde3ac41cce7b97d6bd7aa67fb8922866575 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Thu, 22 Feb 2024 10:27:38 +0300 Subject: [PATCH 09/28] possible fix for reload button not appearing in some cases for extra networks. --- modules/ui_extra_networks.py | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/modules/ui_extra_networks.py b/modules/ui_extra_networks.py index c03b9f081..6874a0244 100644 --- a/modules/ui_extra_networks.py +++ b/modules/ui_extra_networks.py @@ -472,7 +472,7 @@ class ExtraNetworksPage: return f"" - def create_card_view_html(self, tabname: str) -> str: + def create_card_view_html(self, tabname: str, *, none_message) -> str: """Generates HTML for the network Card View section for a tab. This HTML goes into the `extra-networks-pane.html`
with @@ -480,6 +480,7 @@ class ExtraNetworksPage: Args: tabname: The name of the active tab. + none_message: HTML text to show when there are no cards. Returns: HTML formatted string. @@ -490,24 +491,28 @@ class ExtraNetworksPage: if res == "": dirs = "".join([f"
  • {x}
    • " for x in self.allowed_directories_for_previews()]) - res = shared.html("extra-networks-no-cards.html").format(dirs=dirs) + res = none_message or shared.html("extra-networks-no-cards.html").format(dirs=dirs) return res - def create_html(self, tabname): + def create_html(self, tabname, *, empty=False): """Generates an HTML string for the current pane. The generated HTML uses `extra-networks-pane.html` as a template. Args: tabname: The name of the active tab. + empty: create an empty HTML page with no items Returns: HTML formatted string. """ self.lister.reset() self.metadata = {} - self.items = {x["name"]: x for x in self.list_items()} + + items_list = [] if empty else self.list_items() + self.items = {x["name"]: x for x in items_list} + # Populate the instance metadata for each item. for item in self.items.values(): metadata = item.get("metadata") @@ -536,7 +541,7 @@ class ExtraNetworksPage: "tree_view_btn_extra_class": tree_view_btn_extra_class, "tree_view_div_extra_class": tree_view_div_extra_class, "tree_html": self.create_tree_view_html(tabname), - "items_html": self.create_card_view_html(tabname), + "items_html": self.create_card_view_html(tabname, none_message="Loading..." if empty else None), } ) @@ -655,7 +660,7 @@ def create_ui(interface: gr.Blocks, unrelated_tabs, tabname): pass elem_id = f"{tabname}_{page.extra_networks_tabname}_cards_html" - page_elem = gr.HTML('Loading...', elem_id=elem_id) + page_elem = gr.HTML(page.create_html(tabname, empty=True), elem_id=elem_id) ui.pages.append(page_elem) editor = page.create_user_metadata_editor(ui, tabname) editor.create_ui() From 726aaea0fe87b40e983be73aa3c2fcd29aaf9588 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Thu, 22 Feb 2024 21:27:10 +0300 Subject: [PATCH 10/28] make extra network card description plaintext by default, with an option to re-enable HTML as it was --- modules/shared_options.py | 1 + modules/ui_extra_networks.py | 6 +++++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/modules/shared_options.py b/modules/shared_options.py index bb3752ba6..64f8f1967 100644 --- a/modules/shared_options.py +++ b/modules/shared_options.py @@ -254,6 +254,7 @@ options_templates.update(options_section(('extra_networks', "Extra Networks", "s "extra_networks_card_height": OptionInfo(0, "Card height for Extra Networks").info("in pixels"), "extra_networks_card_text_scale": OptionInfo(1.0, "Card text scale", gr.Slider, {"minimum": 0.0, "maximum": 2.0, "step": 0.01}).info("1 = original size"), "extra_networks_card_show_desc": OptionInfo(True, "Show description on card"), + "extra_networks_card_description_is_html": OptionInfo(False, "Treat card description as HTML"), "extra_networks_card_order_field": OptionInfo("Path", "Default order field for Extra Networks cards", gr.Dropdown, {"choices": ['Path', 'Name', 'Date Created', 'Date Modified']}).needs_reload_ui(), "extra_networks_card_order": OptionInfo("Ascending", "Default order for Extra Networks cards", gr.Dropdown, {"choices": ['Ascending', 'Descending']}).needs_reload_ui(), "extra_networks_tree_view_default_enabled": OptionInfo(False, "Enables the Extra Networks directory tree view by default").needs_reload_ui(), diff --git a/modules/ui_extra_networks.py b/modules/ui_extra_networks.py index 6874a0244..34c46ed40 100644 --- a/modules/ui_extra_networks.py +++ b/modules/ui_extra_networks.py @@ -289,12 +289,16 @@ class ExtraNetworksPage: } ) + description = (item.get("description", "") or "" if shared.opts.extra_networks_card_show_desc else "") + if not shared.opts.extra_networks_card_description_is_html: + description = html.escape(description) + # Some items here might not be used depending on HTML template used. args = { "background_image": background_image, "card_clicked": onclick, "copy_path_button": btn_copy_path, - "description": (item.get("description", "") or "" if shared.opts.extra_networks_card_show_desc else ""), + "description": description, "edit_button": btn_edit_item, "local_preview": quote_js(item["local_preview"]), "metadata_button": btn_metadata, From b53989b195485430cc8083fad7508e201a00123a Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Thu, 22 Feb 2024 21:29:10 +0300 Subject: [PATCH 11/28] update changelog --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index c7bfc1c98..84d9c485e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -165,6 +165,7 @@ * add FP32 fallback support on sd_vae_approx ([#14046](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046)) * support XYZ scripts / split hires path from unet ([#14126](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14126)) * allow use of mutiple styles csv files ([#14125](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14125)) +* make extra network card description plaintext by default, with an option (Treat card description as HTML) to re-enable HTML as it was (originally by [#13241](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13241)) ### Extensions and API: * update gradio to 3.41.2 From 6bc35be10a025fdea649d0a948f076760581728f Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Thu, 22 Feb 2024 21:29:58 +0300 Subject: [PATCH 12/28] update changelog --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 84d9c485e..a8eaca962 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -99,6 +99,7 @@ * Gracefully handle mtime read exception from cache ([#14933](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14933)) * Only trigger interrupt on `Esc` when interrupt button visible ([#14932](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14932)) * Disable prompt token counters option actually disables token counting rather than just hiding results. +* avoid doble upscaling in inpaint ([#14966](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14966)) ### Other: * Assign id for "extra_options". Replace numeric field with slider. ([#14270](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14270)) From dfab42c949428c759f8ce3dcd3e492f3b6063e3a Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Thu, 22 Feb 2024 22:59:26 +0300 Subject: [PATCH 13/28] Merge pull request #15002 from light-and-ray/support_resizable_columns_for_touch_(tablets) support resizable columns for touch (tablets) --- javascript/resizeHandle.js | 87 +++++++++++++++++++++++++------------- 1 file changed, 58 insertions(+), 29 deletions(-) diff --git a/javascript/resizeHandle.js b/javascript/resizeHandle.js index 8c5c51692..f22aa51de 100644 --- a/javascript/resizeHandle.js +++ b/javascript/resizeHandle.js @@ -65,21 +65,31 @@ resizeHandle.classList.add('resize-handle'); parent.insertBefore(resizeHandle, rightCol); - resizeHandle.addEventListener('mousedown', (evt) => { - if (evt.button !== 0) return; + ['mousedown', 'touchstart'].forEach((eventType) => { + resizeHandle.addEventListener(eventType, (evt) => { + if (eventType.startsWith('mouse')) { + if (evt.button !== 0) return; + } else { + if (evt.changedTouches.length !== 1) return; + } - evt.preventDefault(); - evt.stopPropagation(); + evt.preventDefault(); + evt.stopPropagation(); - document.body.classList.add('resizing'); + document.body.classList.add('resizing'); - R.tracking = true; - R.parent = parent; - R.parentWidth = parent.offsetWidth; - R.handle = resizeHandle; - R.leftCol = leftCol; - R.leftColStartWidth = leftCol.offsetWidth; - R.screenX = evt.screenX; + R.tracking = true; + R.parent = parent; + R.parentWidth = parent.offsetWidth; + R.handle = resizeHandle; + R.leftCol = leftCol; + R.leftColStartWidth = leftCol.offsetWidth; + if (eventType.startsWith('mouse')) { + R.screenX = evt.screenX; + } else { + R.screenX = evt.changedTouches[0].screenX; + } + }); }); resizeHandle.addEventListener('dblclick', (evt) => { @@ -92,30 +102,49 @@ afterResize(parent); } - window.addEventListener('mousemove', (evt) => { - if (evt.button !== 0) return; + ['mousemove', 'touchmove'].forEach((eventType) => { + window.addEventListener(eventType, (evt) => { + if (eventType.startsWith('mouse')) { + if (evt.button !== 0) return; + } else { + if (evt.changedTouches.length !== 1) return; + } - if (R.tracking) { - evt.preventDefault(); - evt.stopPropagation(); + if (R.tracking) { + if (eventType.startsWith('mouse')) { + evt.preventDefault(); + } + evt.stopPropagation(); - const delta = R.screenX - evt.screenX; - const leftColWidth = Math.max(Math.min(R.leftColStartWidth - delta, R.parent.offsetWidth - GRADIO_MIN_WIDTH - PAD), GRADIO_MIN_WIDTH); - setLeftColGridTemplate(R.parent, leftColWidth); - } + let delta = 0; + if (eventType.startsWith('mouse')) { + delta = R.screenX - evt.screenX; + } else { + delta = R.screenX - evt.changedTouches[0].screenX; + } + const leftColWidth = Math.max(Math.min(R.leftColStartWidth - delta, R.parent.offsetWidth - GRADIO_MIN_WIDTH - PAD), GRADIO_MIN_WIDTH); + setLeftColGridTemplate(R.parent, leftColWidth); + } + }); }); - window.addEventListener('mouseup', (evt) => { - if (evt.button !== 0) return; + ['mouseup', 'touchend'].forEach((eventType) => { + window.addEventListener(eventType, (evt) => { + if (eventType.startsWith('mouse')) { + if (evt.button !== 0) return; + } else { + if (evt.changedTouches.length !== 1) return; + } - if (R.tracking) { - evt.preventDefault(); - evt.stopPropagation(); + if (R.tracking) { + evt.preventDefault(); + evt.stopPropagation(); - R.tracking = false; + R.tracking = false; - document.body.classList.remove('resizing'); - } + document.body.classList.remove('resizing'); + } + }); }); From 3069716510c8ae9a95b2d04061c3f86f67d1089c Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Thu, 22 Feb 2024 23:00:14 +0300 Subject: [PATCH 14/28] update changelog --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index a8eaca962..9d04dd527 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -41,6 +41,7 @@ * When counting tokens, also include enabled styles (can be disabled in settings to revert to previous behavior) * Configuration for the [📂] button for image gallery ([#14947](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14947)) * Support inference with LyCORIS BOFT networks ([#14871](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14871)) +* support resizable columns for touch (tablets) ([#15002](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15002)) ### Extensions and API: * Removed packages from requirements: basicsr, gfpgan, realesrgan; as well as their dependencies: absl-py, addict, beautifulsoup4, future, gdown, grpcio, importlib-metadata, lmdb, lpips, Markdown, platformdirs, PySocks, soupsieve, tb-nightly, tensorboard-data-server, tomli, Werkzeug, yapf, zipp, soupsieve From a10c8df8761c01801bac60d7977ae7e997ab51b0 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Mon, 26 Feb 2024 07:12:12 +0300 Subject: [PATCH 15/28] Merge pull request #14973 from AUTOMATIC1111/Fix-new-oft-boft Fix the OFT/BOFT bugs when using new LyCORIS implementation --- extensions-builtin/Lora/network_oft.py | 50 +++++++++++++------------- 1 file changed, 24 insertions(+), 26 deletions(-) diff --git a/extensions-builtin/Lora/network_oft.py b/extensions-builtin/Lora/network_oft.py index d658ad109..7821a8a7d 100644 --- a/extensions-builtin/Lora/network_oft.py +++ b/extensions-builtin/Lora/network_oft.py @@ -1,6 +1,5 @@ import torch import network -from lyco_helpers import factorization from einops import rearrange @@ -22,24 +21,24 @@ class NetworkModuleOFT(network.NetworkModule): self.org_module: list[torch.Module] = [self.sd_module] self.scale = 1.0 - self.is_kohya = False + self.is_R = False self.is_boft = False - # kohya-ss + # kohya-ss/New LyCORIS OFT/BOFT if "oft_blocks" in weights.w.keys(): - self.is_kohya = True self.oft_blocks = weights.w["oft_blocks"] # (num_blocks, block_size, block_size) - self.alpha = weights.w["alpha"] # alpha is constraint + self.alpha = weights.w.get("alpha", None) # alpha is constraint self.dim = self.oft_blocks.shape[0] # lora dim - # LyCORIS OFT + # Old LyCORIS OFT elif "oft_diag" in weights.w.keys(): + self.is_R = True self.oft_blocks = weights.w["oft_diag"] # self.alpha is unused self.dim = self.oft_blocks.shape[1] # (num_blocks, block_size, block_size) - # LyCORIS BOFT - if weights.w["oft_diag"].dim() == 4: - self.is_boft = True + # LyCORIS BOFT + if self.oft_blocks.dim() == 4: + self.is_boft = True self.rescale = weights.w.get('rescale', None) if self.rescale is not None: self.rescale = self.rescale.reshape(-1, *[1]*(self.org_module[0].weight.dim() - 1)) @@ -55,30 +54,29 @@ class NetworkModuleOFT(network.NetworkModule): elif is_other_linear: self.out_dim = self.sd_module.embed_dim - if self.is_kohya: - self.constraint = self.alpha * self.out_dim - self.num_blocks = self.dim - self.block_size = self.out_dim // self.dim + self.num_blocks = self.dim + self.block_size = self.out_dim // self.dim + self.constraint = (0 if self.alpha is None else self.alpha) * self.out_dim + if self.is_R: + self.constraint = None + self.block_size = self.dim + self.num_blocks = self.out_dim // self.dim elif self.is_boft: - self.constraint = None - self.boft_m = weights.w["oft_diag"].shape[0] - self.block_num = weights.w["oft_diag"].shape[1] - self.block_size = weights.w["oft_diag"].shape[2] + self.boft_m = self.oft_blocks.shape[0] + self.num_blocks = self.oft_blocks.shape[1] + self.block_size = self.oft_blocks.shape[2] self.boft_b = self.block_size - #self.block_size, self.block_num = butterfly_factor(self.out_dim, self.dim) - else: - self.constraint = None - self.block_size, self.num_blocks = factorization(self.out_dim, self.dim) def calc_updown(self, orig_weight): oft_blocks = self.oft_blocks.to(orig_weight.device) eye = torch.eye(self.block_size, device=oft_blocks.device) - if self.is_kohya: - block_Q = oft_blocks - oft_blocks.transpose(1, 2) # ensure skew-symmetric orthogonal matrix - norm_Q = torch.norm(block_Q.flatten()) - new_norm_Q = torch.clamp(norm_Q, max=self.constraint.to(oft_blocks.device)) - block_Q = block_Q * ((new_norm_Q + 1e-8) / (norm_Q + 1e-8)) + if not self.is_R: + block_Q = oft_blocks - oft_blocks.transpose(-1, -2) # ensure skew-symmetric orthogonal matrix + if self.constraint != 0: + norm_Q = torch.norm(block_Q.flatten()) + new_norm_Q = torch.clamp(norm_Q, max=self.constraint.to(oft_blocks.device)) + block_Q = block_Q * ((new_norm_Q + 1e-8) / (norm_Q + 1e-8)) oft_blocks = torch.matmul(eye + block_Q, (eye - block_Q).float().inverse()) R = oft_blocks.to(orig_weight.device) From 78e421e4ea833e163367f26232656256ddc0bbc8 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Mon, 26 Feb 2024 07:12:31 +0300 Subject: [PATCH 16/28] Merge pull request #14995 from dtlnor/14591-bug-the-categories-layout-is-different-when-localization-is-on Fix #14591 using translated content to do categories mapping --- javascript/settings.js | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/javascript/settings.js b/javascript/settings.js index e6009290a..b2d981c21 100644 --- a/javascript/settings.js +++ b/javascript/settings.js @@ -55,8 +55,8 @@ onOptionsChanged(function() { }); opts._categories.forEach(function(x) { - var section = x[0]; - var category = x[1]; + var section = localization[x[0]] ?? x[0]; + var category = localization[x[1]] ?? x[1]; var span = document.createElement('SPAN'); span.textContent = category; From e651ca8adb00b14704aa564dbeb0bef5f8698f0a Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Mon, 26 Feb 2024 07:16:24 +0300 Subject: [PATCH 17/28] Merge pull request #15004 from light-and-ray/ResizeHandleRow_-_allow_overriden_column_scale_parametr ResizeHandleRow - allow overriden column scale parametr --- javascript/resizeHandle.js | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/javascript/resizeHandle.js b/javascript/resizeHandle.js index f22aa51de..cd3e68c6c 100644 --- a/javascript/resizeHandle.js +++ b/javascript/resizeHandle.js @@ -1,6 +1,5 @@ (function() { const GRADIO_MIN_WIDTH = 320; - const GRID_TEMPLATE_COLUMNS = '1fr 16px 1fr'; const PAD = 16; const DEBOUNCE_TIME = 100; @@ -37,7 +36,7 @@ } function afterResize(parent) { - if (displayResizeHandle(parent) && parent.style.gridTemplateColumns != GRID_TEMPLATE_COLUMNS) { + if (displayResizeHandle(parent) && parent.style.gridTemplateColumns != parent.style.originalGridTemplateColumns) { const oldParentWidth = R.parentWidth; const newParentWidth = parent.offsetWidth; const widthL = parseInt(parent.style.gridTemplateColumns.split(' ')[0]); @@ -59,7 +58,9 @@ parent.style.display = 'grid'; parent.style.gap = '0'; - parent.style.gridTemplateColumns = GRID_TEMPLATE_COLUMNS; + const gridTemplateColumns = `${parent.children[0].style.flexGrow}fr ${PAD}px ${parent.children[1].style.flexGrow}fr`; + parent.style.gridTemplateColumns = gridTemplateColumns; + parent.style.originalGridTemplateColumns = gridTemplateColumns; const resizeHandle = document.createElement('div'); resizeHandle.classList.add('resize-handle'); @@ -96,7 +97,7 @@ evt.preventDefault(); evt.stopPropagation(); - parent.style.gridTemplateColumns = GRID_TEMPLATE_COLUMNS; + parent.style.gridTemplateColumns = parent.style.originalGridTemplateColumns; }); afterResize(parent); From f97e3548e54cfc914c195d6d4d48792e4d021261 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Mon, 26 Feb 2024 07:16:42 +0300 Subject: [PATCH 18/28] Merge pull request #15006 from imnodb/master fix: the `split_threshold` parameter does not work when running Split oversized images --- scripts/postprocessing_split_oversized.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/postprocessing_split_oversized.py b/scripts/postprocessing_split_oversized.py index c4a03160f..133e199b8 100644 --- a/scripts/postprocessing_split_oversized.py +++ b/scripts/postprocessing_split_oversized.py @@ -61,7 +61,7 @@ class ScriptPostprocessingSplitOversized(scripts_postprocessing.ScriptPostproces ratio = (pp.image.height * width) / (pp.image.width * height) inverse_xy = True - if ratio >= 1.0 and ratio > split_threshold: + if ratio >= 1.0 or ratio > split_threshold: return result, *others = split_pic(pp.image, inverse_xy, width, height, overlap_ratio) From eaf5e0289a2e71d39322c6258a1e2d7dc1fd2e34 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Mon, 26 Feb 2024 07:37:26 +0300 Subject: [PATCH 19/28] update cahngelog --- CHANGELOG.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9d04dd527..8fa3c47c5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -40,7 +40,7 @@ * Add an option to disable normalization after calculating emphasis. ([#14874](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14874)) * When counting tokens, also include enabled styles (can be disabled in settings to revert to previous behavior) * Configuration for the [📂] button for image gallery ([#14947](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14947)) -* Support inference with LyCORIS BOFT networks ([#14871](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14871)) +* Support inference with LyCORIS BOFT networks ([#14871](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14871), [#14973](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14973)) * support resizable columns for touch (tablets) ([#15002](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15002)) ### Extensions and API: @@ -59,6 +59,7 @@ * modules/api/api.py: add api endpoint to refresh embeddings list ([#14715](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14715)) * set_named_arg ([#14773](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14773)) * add before_token_counter callback and use it for prompt comments +* ResizeHandleRow - allow overriden column scale parameter ([#15004](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15004)) ### Performance * Massive performance improvement for extra networks directories with a huge number of files in them in an attempt to tackle #14507 ([#14528](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14528)) @@ -101,6 +102,8 @@ * Only trigger interrupt on `Esc` when interrupt button visible ([#14932](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14932)) * Disable prompt token counters option actually disables token counting rather than just hiding results. * avoid doble upscaling in inpaint ([#14966](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14966)) +* Fix #14591 using translated content to do categories mapping ([#14995](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14995)) +* fix: the `split_threshold` parameter does not work when running Split oversized images ([#15006](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15006)) ### Other: * Assign id for "extra_options". Replace numeric field with slider. ([#14270](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14270)) From b47756385d3fbd851ff52507cfa392807556c330 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Mon, 26 Feb 2024 12:52:34 +0300 Subject: [PATCH 20/28] Merge pull request #15010 from light-and-ray/fix_resize-handle_for_vertical_layout Fix resize-handle visability for vertical layout (mobile) --- javascript/resizeHandle.js | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/javascript/resizeHandle.js b/javascript/resizeHandle.js index cd3e68c6c..6560372cc 100644 --- a/javascript/resizeHandle.js +++ b/javascript/resizeHandle.js @@ -22,15 +22,11 @@ function displayResizeHandle(parent) { if (window.innerWidth < GRADIO_MIN_WIDTH * 2 + PAD * 4) { parent.style.display = 'flex'; - if (R.handle != null) { - R.handle.style.opacity = '0'; - } + parent.resizeHandle.style.display = "none"; return false; } else { parent.style.display = 'grid'; - if (R.handle != null) { - R.handle.style.opacity = '100'; - } + parent.resizeHandle.style.display = "block"; return true; } } @@ -65,6 +61,7 @@ const resizeHandle = document.createElement('div'); resizeHandle.classList.add('resize-handle'); parent.insertBefore(resizeHandle, rightCol); + parent.resizeHandle = resizeHandle; ['mousedown', 'touchstart'].forEach((eventType) => { resizeHandle.addEventListener(eventType, (evt) => { @@ -82,7 +79,6 @@ R.tracking = true; R.parent = parent; R.parentWidth = parent.offsetWidth; - R.handle = resizeHandle; R.leftCol = leftCol; R.leftColStartWidth = leftCol.offsetWidth; if (eventType.startsWith('mouse')) { From 024a32a09bb833f467fc351a6ea67132db5299c5 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Mon, 26 Feb 2024 12:53:21 +0300 Subject: [PATCH 21/28] Merge pull request #15012 from light-and-ray/register_tmp_file-also-with-mtime register_tmp_file also for mtime --- modules/ui_tempdir.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/modules/ui_tempdir.py b/modules/ui_tempdir.py index 621ed1eca..ecd6bdec3 100644 --- a/modules/ui_tempdir.py +++ b/modules/ui_tempdir.py @@ -35,7 +35,9 @@ def save_pil_to_file(self, pil_image, dir=None, format="png"): already_saved_as = getattr(pil_image, 'already_saved_as', None) if already_saved_as and os.path.isfile(already_saved_as): register_tmp_file(shared.demo, already_saved_as) - return f'{already_saved_as}?{os.path.getmtime(already_saved_as)}' + filename_with_mtime = f'{already_saved_as}?{os.path.getmtime(already_saved_as)}' + register_tmp_file(shared.demo, filename_with_mtime) + return filename_with_mtime if shared.opts.temp_dir != "": dir = shared.opts.temp_dir From 0b07a6cf26634ea758d9fd67b4d4222cf9ec1617 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 2 Mar 2024 06:35:46 +0300 Subject: [PATCH 22/28] Merge pull request #15035 from AUTOMATIC1111/fix/normalized-filepath-absolute Use `absolute` path for normalized filepath --- modules/paths_internal.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/paths_internal.py b/modules/paths_internal.py index 2ed1392a4..6058b0cde 100644 --- a/modules/paths_internal.py +++ b/modules/paths_internal.py @@ -7,7 +7,7 @@ import shlex from pathlib import Path -normalized_filepath = lambda filepath: str(Path(filepath).resolve()) +normalized_filepath = lambda filepath: str(Path(filepath).absolute()) commandline_args = os.environ.get('COMMANDLINE_ARGS', "") sys.argv += shlex.split(commandline_args) From d558cb69b0299cfbd15d693492d489a858b027f2 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 2 Mar 2024 06:37:19 +0300 Subject: [PATCH 23/28] Merge pull request #15065 from light-and-ray/resizeHandle_handle_double_tap resizeHandle handle double tap --- javascript/resizeHandle.js | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/javascript/resizeHandle.js b/javascript/resizeHandle.js index 6560372cc..c4e9de581 100644 --- a/javascript/resizeHandle.js +++ b/javascript/resizeHandle.js @@ -2,6 +2,7 @@ const GRADIO_MIN_WIDTH = 320; const PAD = 16; const DEBOUNCE_TIME = 100; + const DOUBLE_TAP_DELAY = 200; //ms const R = { tracking: false, @@ -10,6 +11,7 @@ leftCol: null, leftColStartWidth: null, screenX: null, + lastTapTime: null, }; let resizeTimer; @@ -47,6 +49,14 @@ } function setup(parent) { + + function onDoubleClick(evt) { + evt.preventDefault(); + evt.stopPropagation(); + + parent.style.gridTemplateColumns = parent.style.originalGridTemplateColumns; + } + const leftCol = parent.firstElementChild; const rightCol = parent.lastElementChild; @@ -69,6 +79,14 @@ if (evt.button !== 0) return; } else { if (evt.changedTouches.length !== 1) return; + + const currentTime = new Date().getTime(); + if (R.lastTapTime && currentTime - R.lastTapTime <= DOUBLE_TAP_DELAY) { + onDoubleClick(evt); + return; + } + + R.lastTapTime = currentTime; } evt.preventDefault(); @@ -89,12 +107,7 @@ }); }); - resizeHandle.addEventListener('dblclick', (evt) => { - evt.preventDefault(); - evt.stopPropagation(); - - parent.style.gridTemplateColumns = parent.style.originalGridTemplateColumns; - }); + resizeHandle.addEventListener('dblclick', onDoubleClick); afterResize(parent); } From 978c7fadb35e0955fdaf17afc9a8fb27f6c10e49 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 2 Mar 2024 06:38:50 +0300 Subject: [PATCH 24/28] Merge pull request #15039 from light-and-ray/dat_cmd_flag dat cmd flag --- modules/cmd_args.py | 1 + 1 file changed, 1 insertion(+) diff --git a/modules/cmd_args.py b/modules/cmd_args.py index 312dabffc..213cba98c 100644 --- a/modules/cmd_args.py +++ b/modules/cmd_args.py @@ -53,6 +53,7 @@ parser.add_argument("--gfpgan-models-path", type=normalized_filepath, help="Path parser.add_argument("--esrgan-models-path", type=normalized_filepath, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN')) parser.add_argument("--bsrgan-models-path", type=normalized_filepath, help="Path to directory with BSRGAN model file(s).", default=os.path.join(models_path, 'BSRGAN')) parser.add_argument("--realesrgan-models-path", type=normalized_filepath, help="Path to directory with RealESRGAN model file(s).", default=os.path.join(models_path, 'RealESRGAN')) +parser.add_argument("--dat-models-path", type=normalized_filepath, help="Path to directory with DAT model file(s).", default=os.path.join(models_path, 'DAT')) parser.add_argument("--clip-models-path", type=normalized_filepath, help="Path to directory with CLIP model file(s).", default=None) parser.add_argument("--xformers", action='store_true', help="enable xformers for cross attention layers") parser.add_argument("--force-enable-xformers", action='store_true', help="enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work") From 28bc85a20a282285710e17c4d86cf9db5e00d7db Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 2 Mar 2024 06:40:32 +0300 Subject: [PATCH 25/28] Merge pull request #14979 from drhead/refiner_cumprod_fix Protect alphas_cumprod during refiner switchover --- modules/processing.py | 28 +--------------------------- modules/sd_models.py | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+), 27 deletions(-) diff --git a/modules/processing.py b/modules/processing.py index d208a922d..411c7c3f4 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -915,33 +915,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if p.n_iter > 1: shared.state.job = f"Batch {n+1} out of {p.n_iter}" - def rescale_zero_terminal_snr_abar(alphas_cumprod): - alphas_bar_sqrt = alphas_cumprod.sqrt() - - # Store old values. - alphas_bar_sqrt_0 = alphas_bar_sqrt[0].clone() - alphas_bar_sqrt_T = alphas_bar_sqrt[-1].clone() - - # Shift so the last timestep is zero. - alphas_bar_sqrt -= (alphas_bar_sqrt_T) - - # Scale so the first timestep is back to the old value. - alphas_bar_sqrt *= alphas_bar_sqrt_0 / (alphas_bar_sqrt_0 - alphas_bar_sqrt_T) - - # Convert alphas_bar_sqrt to betas - alphas_bar = alphas_bar_sqrt**2 # Revert sqrt - alphas_bar[-1] = 4.8973451890853435e-08 - return alphas_bar - - if hasattr(p.sd_model, 'alphas_cumprod') and hasattr(p.sd_model, 'alphas_cumprod_original'): - p.sd_model.alphas_cumprod = p.sd_model.alphas_cumprod_original.to(shared.device) - - if opts.use_downcasted_alpha_bar: - p.extra_generation_params['Downcast alphas_cumprod'] = opts.use_downcasted_alpha_bar - p.sd_model.alphas_cumprod = p.sd_model.alphas_cumprod.half().to(shared.device) - if opts.sd_noise_schedule == "Zero Terminal SNR": - p.extra_generation_params['Noise Schedule'] = opts.sd_noise_schedule - p.sd_model.alphas_cumprod = rescale_zero_terminal_snr_abar(p.sd_model.alphas_cumprod).to(shared.device) + sd_models.apply_alpha_schedule_override(p.sd_model, p) with devices.without_autocast() if devices.unet_needs_upcast else devices.autocast(): samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts) diff --git a/modules/sd_models.py b/modules/sd_models.py index 2c0457715..fbd53adba 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -15,6 +15,7 @@ from ldm.util import instantiate_from_config from modules import paths, shared, modelloader, devices, script_callbacks, sd_vae, sd_disable_initialization, errors, hashes, sd_models_config, sd_unet, sd_models_xl, cache, extra_networks, processing, lowvram, sd_hijack, patches from modules.timer import Timer +from modules.shared import opts import tomesd import numpy as np @@ -549,6 +550,36 @@ def repair_config(sd_config): karlo_path = os.path.join(paths.models_path, 'karlo') sd_config.model.params.noise_aug_config.params.clip_stats_path = sd_config.model.params.noise_aug_config.params.clip_stats_path.replace("checkpoints/karlo_models", karlo_path) +def apply_alpha_schedule_override(sd_model, p=None): + def rescale_zero_terminal_snr_abar(alphas_cumprod): + alphas_bar_sqrt = alphas_cumprod.sqrt() + + # Store old values. + alphas_bar_sqrt_0 = alphas_bar_sqrt[0].clone() + alphas_bar_sqrt_T = alphas_bar_sqrt[-1].clone() + + # Shift so the last timestep is zero. + alphas_bar_sqrt -= (alphas_bar_sqrt_T) + + # Scale so the first timestep is back to the old value. + alphas_bar_sqrt *= alphas_bar_sqrt_0 / (alphas_bar_sqrt_0 - alphas_bar_sqrt_T) + + # Convert alphas_bar_sqrt to betas + alphas_bar = alphas_bar_sqrt**2 # Revert sqrt + alphas_bar[-1] = 4.8973451890853435e-08 + return alphas_bar + + if hasattr(sd_model, 'alphas_cumprod') and hasattr(sd_model, 'alphas_cumprod_original'): + sd_model.alphas_cumprod = sd_model.alphas_cumprod_original.to(shared.device) + + if opts.use_downcasted_alpha_bar: + if p is not None: + p.extra_generation_params['Downcast alphas_cumprod'] = opts.use_downcasted_alpha_bar + sd_model.alphas_cumprod = sd_model.alphas_cumprod.half().to(shared.device) + if opts.sd_noise_schedule == "Zero Terminal SNR": + if p is not None: + p.extra_generation_params['Noise Schedule'] = opts.sd_noise_schedule + sd_model.alphas_cumprod = rescale_zero_terminal_snr_abar(sd_model.alphas_cumprod).to(shared.device) sd1_clip_weight = 'cond_stage_model.transformer.text_model.embeddings.token_embedding.weight' sd2_clip_weight = 'cond_stage_model.model.transformer.resblocks.0.attn.in_proj_weight' @@ -812,6 +843,7 @@ def reload_model_weights(sd_model=None, info=None, forced_reload=False): sd_model = reuse_model_from_already_loaded(sd_model, checkpoint_info, timer) if not forced_reload and sd_model is not None and sd_model.sd_checkpoint_info.filename == checkpoint_info.filename: + apply_alpha_schedule_override(sd_model) return sd_model if sd_model is not None: From da67afe5f68497a04d1fd9173bbd256b73d9d251 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 2 Mar 2024 06:53:53 +0300 Subject: [PATCH 26/28] call apply_alpha_schedule_override in load_model_weights for #14979 --- modules/sd_models.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/modules/sd_models.py b/modules/sd_models.py index fbd53adba..db72e120f 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -428,6 +428,8 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer devices.dtype_unet = torch.float16 timer.record("apply half()") + apply_alpha_schedule_override(model) + for module in model.modules(): if hasattr(module, 'fp16_weight'): del module.fp16_weight @@ -843,7 +845,6 @@ def reload_model_weights(sd_model=None, info=None, forced_reload=False): sd_model = reuse_model_from_already_loaded(sd_model, checkpoint_info, timer) if not forced_reload and sd_model is not None and sd_model.sd_checkpoint_info.filename == checkpoint_info.filename: - apply_alpha_schedule_override(sd_model) return sd_model if sd_model is not None: From 141a17e9693065c33a2b1d30f04a0083bb687775 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 2 Mar 2024 06:54:11 +0300 Subject: [PATCH 27/28] style changes for #14979 --- modules/sd_models.py | 60 ++++++++++++++++++++++++++------------------ 1 file changed, 36 insertions(+), 24 deletions(-) diff --git a/modules/sd_models.py b/modules/sd_models.py index db72e120f..747fc39ee 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -552,36 +552,48 @@ def repair_config(sd_config): karlo_path = os.path.join(paths.models_path, 'karlo') sd_config.model.params.noise_aug_config.params.clip_stats_path = sd_config.model.params.noise_aug_config.params.clip_stats_path.replace("checkpoints/karlo_models", karlo_path) + +def rescale_zero_terminal_snr_abar(alphas_cumprod): + alphas_bar_sqrt = alphas_cumprod.sqrt() + + # Store old values. + alphas_bar_sqrt_0 = alphas_bar_sqrt[0].clone() + alphas_bar_sqrt_T = alphas_bar_sqrt[-1].clone() + + # Shift so the last timestep is zero. + alphas_bar_sqrt -= (alphas_bar_sqrt_T) + + # Scale so the first timestep is back to the old value. + alphas_bar_sqrt *= alphas_bar_sqrt_0 / (alphas_bar_sqrt_0 - alphas_bar_sqrt_T) + + # Convert alphas_bar_sqrt to betas + alphas_bar = alphas_bar_sqrt ** 2 # Revert sqrt + alphas_bar[-1] = 4.8973451890853435e-08 + return alphas_bar + + def apply_alpha_schedule_override(sd_model, p=None): - def rescale_zero_terminal_snr_abar(alphas_cumprod): - alphas_bar_sqrt = alphas_cumprod.sqrt() + """ + Applies an override to the alpha schedule of the model according to settings. + - downcasts the alpha schedule to half precision + - rescales the alpha schedule to have zero terminal SNR + """ - # Store old values. - alphas_bar_sqrt_0 = alphas_bar_sqrt[0].clone() - alphas_bar_sqrt_T = alphas_bar_sqrt[-1].clone() + if not hasattr(sd_model, 'alphas_cumprod') or not hasattr(sd_model, 'alphas_cumprod_original'): + return - # Shift so the last timestep is zero. - alphas_bar_sqrt -= (alphas_bar_sqrt_T) + sd_model.alphas_cumprod = sd_model.alphas_cumprod_original.to(shared.device) - # Scale so the first timestep is back to the old value. - alphas_bar_sqrt *= alphas_bar_sqrt_0 / (alphas_bar_sqrt_0 - alphas_bar_sqrt_T) + if opts.use_downcasted_alpha_bar: + if p is not None: + p.extra_generation_params['Downcast alphas_cumprod'] = opts.use_downcasted_alpha_bar + sd_model.alphas_cumprod = sd_model.alphas_cumprod.half().to(shared.device) - # Convert alphas_bar_sqrt to betas - alphas_bar = alphas_bar_sqrt**2 # Revert sqrt - alphas_bar[-1] = 4.8973451890853435e-08 - return alphas_bar + if opts.sd_noise_schedule == "Zero Terminal SNR": + if p is not None: + p.extra_generation_params['Noise Schedule'] = opts.sd_noise_schedule + sd_model.alphas_cumprod = rescale_zero_terminal_snr_abar(sd_model.alphas_cumprod).to(shared.device) - if hasattr(sd_model, 'alphas_cumprod') and hasattr(sd_model, 'alphas_cumprod_original'): - sd_model.alphas_cumprod = sd_model.alphas_cumprod_original.to(shared.device) - - if opts.use_downcasted_alpha_bar: - if p is not None: - p.extra_generation_params['Downcast alphas_cumprod'] = opts.use_downcasted_alpha_bar - sd_model.alphas_cumprod = sd_model.alphas_cumprod.half().to(shared.device) - if opts.sd_noise_schedule == "Zero Terminal SNR": - if p is not None: - p.extra_generation_params['Noise Schedule'] = opts.sd_noise_schedule - sd_model.alphas_cumprod = rescale_zero_terminal_snr_abar(sd_model.alphas_cumprod).to(shared.device) sd1_clip_weight = 'cond_stage_model.transformer.text_model.embeddings.token_embedding.weight' sd2_clip_weight = 'cond_stage_model.model.transformer.resblocks.0.attn.in_proj_weight' From 13984857890401e8605a3e53bd671e900a18d73f Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 2 Mar 2024 07:00:08 +0300 Subject: [PATCH 28/28] update changelog --- CHANGELOG.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 8fa3c47c5..f0c659811 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,11 +7,11 @@ * Support for SDXL-Inpaint Model ([#14390](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14390)) * Use Spandrel for upscaling and face restoration architectures ([#14425](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14425), [#14467](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14467), [#14473](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14473), [#14474](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14474), [#14477](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14477), [#14476](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14476), [#14484](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14484), [#14500](https://github.com/AUTOMATIC1111/stable-difusion-webui/pull/14500), [#14501](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14501), [#14504](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14504), [#14524](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14524), [#14809](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14809)) * Automatic backwards version compatibility (when loading infotexts from old images with program version specified, will add compatibility settings) -* Implement zero terminal SNR noise schedule option (**[SEED BREAKING CHANGE](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Seed-breaking-changes#180-dev-170-225-2024-01-01---zero-terminal-snr-noise-schedule-option)**, [#14145](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14145)) +* Implement zero terminal SNR noise schedule option (**[SEED BREAKING CHANGE](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Seed-breaking-changes#180-dev-170-225-2024-01-01---zero-terminal-snr-noise-schedule-option)**, [#14145](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14145), [#14979](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14979)) * Add a [✨] button to run hires fix on selected image in the gallery (with help from [#14598](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14598), [#14626](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14626), [#14728](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14728)) * [Separate assets repository](https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets); serve fonts locally rather than from google's servers * Official LCM Sampler Support ([#14583](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14583)) -* Add support for DAT upscaler models ([#14690](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14690)) +* Add support for DAT upscaler models ([#14690](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14690), [#15039](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15039)) * Extra Networks Tree View ([#14588](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14588), [#14900](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14900)) * NPU Support ([#14801](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14801)) * Propmpt comments support @@ -104,6 +104,7 @@ * avoid doble upscaling in inpaint ([#14966](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14966)) * Fix #14591 using translated content to do categories mapping ([#14995](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14995)) * fix: the `split_threshold` parameter does not work when running Split oversized images ([#15006](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15006)) +* Fix resize-handle for mobile ([#15010](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15010), [#15065](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15065)) ### Other: * Assign id for "extra_options". Replace numeric field with slider. ([#14270](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14270)) @@ -124,8 +125,9 @@ * extensions tab table row hover highlight ([#14885](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14885)) * Always add timestamp to displayed image ([#14890](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14890)) * Added core.filemode=false so doesn't track changes in file permission… ([#14930](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14930)) -* Normalize command-line argument paths ([#14934](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14934)) +* Normalize command-line argument paths ([#14934](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14934), [#15035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15035)) * Use original App Title in progress bar ([#14916](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14916)) +* register_tmp_file also for mtime ([#15012](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15012)) ## 1.7.0