Features:

• Update torch to version 2.1.2
• Soft Inpainting (#14208)
• FP8 support (#14031, #14327)
• Support for SDXL-Inpaint Model (#14390)
• Use Spandrel for upscaling and face restoration architectures (#14425, #14467, #14473, #14474, #14477, #14476, #14484, #14500, #14501, #14504, #14524, #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, #14145, #14979)
• Add a [✨] button to run hires fix on selected image in the gallery (with help from #14598, #14626, #14728)
• Separate assets repository; serve fonts locally rather than from google's servers
• Official LCM Sampler Support (#14583)
• Add support for DAT upscaler models (#14690, #15039)
• Extra Networks Tree View (#14588, #14900)
• NPU Support (#14801)
• Prompt comments support

Minor:

• Allow pasting in WIDTHxHEIGHT strings into the width/height fields (#14296)
• add option: Live preview in full page image viewer (#14230, #14307)
• Add keyboard shortcuts for generate/skip/interrupt (#14269)
• Better TCMALLOC support on different platforms (#14227, #14883, #14910)
• Lora not found warning (#14464)
• Adding negative prompts to Loras in extra networks (#14475)
• xyz_grid: allow varying the seed along an axis separate from axis options (#12180)
• option to convert VAE to bfloat16 (implementation of #9295)
• Better IPEX support (#14229, #14353, #14559, #14562, #14597)
• Option to interrupt after current generation rather than immediately (#13653, #14659)
• Fullscreen Preview control fading/disable (#14291)
• Finer settings freezing control (#13789)
• Increase Upscaler Limits (#14589)
• Adjust brush size with hotkeys (#14638)
• Add checkpoint info to csv log file when saving images (#14663)
• Make more columns resizable (#14740, #14884)
• Add an option to not overlay original image for inpainting for #14727
• 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)
• Add an option to disable normalization after calculating emphasis. (#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)
• Support inference with LyCORIS BOFT networks (#14871, #14973)
• support resizable columns for touch (tablets) (#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
• Enable task ids for API (#14314)
• add override_settings support for infotext API
• rename generation_parameters_copypaste module to infotext_utils
• prevent crash due to Script __init__ exception (#14407)
• Bump numpy to 1.26.2 (#14471)
• Add utility to inspect a model's dtype/device (#14478)
• Implement general forward method for all method in built-in lora ext (#14547)
• Execute model_loaded_callback after moving to target device (#14563)
• Add self to CFGDenoiserParams (#14573)
• Allow TLS with API only mode (--nowebui) (#14593)
• New callback: postprocess_image_after_composite (#14657)
• modules/api/api.py: add api endpoint to refresh embeddings list (#14715)
• set_named_arg (#14773)
• add before_token_counter callback and use it for prompt comments
• ResizeHandleRow - allow overriden column scale parameter (#15004)

Performance

• Massive performance improvement for extra networks directories with a huge number of files in them in an attempt to tackle #14507 (#14528)
• Reduce unnecessary re-indexing extra networks directory (#14512)
• Avoid unnecessary isfile/exists calls (#14527)

Bug Fixes:

• fix multiple bugs related to styles multi-file support (#14203, #14276, #14707)
• Lora fixes (#14300, #14237, #14546, #14726)
• Re-add setting lost as part of e294e46 (#14266)
• fix extras caption BLIP (#14330)
• include infotext into saved init image for img2img (#14452)
• xyz grid handle axis_type is None (#14394)
• Update Added (Fixed) IPV6 Functionality When there is No Webui Argument Passed webui.py (#14354)
• fix API thread safe issues of txt2img and img2img (#14421)
• handle selectable script_index is None (#14487)
• handle config.json failed to load (#14525, #14767)
• paste infotext cast int as float (#14523)
• Ensure GRADIO_ANALYTICS_ENABLED is set early enough (#14537)
• Fix logging configuration again (#14538)
• Handle CondFunc exception when resolving attributes (#14560)
• Fix extras big batch crashes (#14699)
• Fix using wrong model caused by alias (#14655)
• Add # to the invalid_filename_chars list (#14640)
• Fix extension check for requirements (#14639)
• Fix tab indexes are reset after restart UI (#14637)
• Fix nested manual cast (#14689)
• Keep postprocessing upscale selected tab after restart (#14702)
• XYZ grid: filter out blank vals when axis is int or float type (like int axis seed) (#14754)
• fix CLIP Interrogator topN regex (#14775)
• Fix dtype error in MHA layer/change dtype checking mechanism for manual cast (#14791)
• catch load style.csv error (#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)
• if extensions page not loaded, prevent apply (#14873)
• call the right function for token counter in img2img
• Fix the bugs that search/reload will disappear when using other ExtraNetworks extensions (#14939)
• Gracefully handle mtime read exception from cache (#14933)
• Only trigger interrupt on Esc when interrupt button visible (#14932)
• Disable prompt token counters option actually disables token counting rather than just hiding results.
• avoid doble upscaling in inpaint (#14966)
• Fix #14591 using translated content to do categories mapping (#14995)
• fix: the split_threshold parameter does not work when running Split oversized images (#15006)
• Fix resize-handle for mobile (#15010, #15065)

Other:

• Assign id for "extra_options". Replace numeric field with slider. (#14270)
• change state dict comparison to ref compare (#14216)
• Bump torch-rocm to 5.6/5.7 (#14293)
• Base output path off data path (#14446)
• reorder training preprocessing modules in extras tab (#14367)
• Remove cleanup_models code (#14472)
• only rewrite ui-config when there is change (#14352)
• Fix lint issue from 501993e (#14495)
• Update README.md (#14548)
• hires button, fix seeds (#14598)
• Logging: set formatter correctly for fallback logger too (#14618)
• Read generation info from infotexts rather than json for internal needs (save, extract seed from generated pic) (#14645)
• improve get_crop_region (#14709)
• Bump safetensors' version to 0.4.2 (#14782)
• add tooltip create_submit_box (#14803)
• extensions tab table row hover highlight (#14885)
• Always add timestamp to displayed image (#14890)
• Added core.filemode=false so doesn't track changes in file permission… (#14930)
• Normalize command-line argument paths (#14934, #15035)
• Use original App Title in progress bar (#14916)
• register_tmp_file also for mtime (#15012)

Full Changelog: v1.7.0...v1.8.0