1.8.0-RC

[AUTOMATIC1111]

1.8.0-RC

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)
• 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)
• Extra Networks Tree View (#14588, #14900)
• NPU Support (#14801)
• Propmpt 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 Removed forced overlay #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 [Issue]: Long wait times before generation and display of Extra Networks after every launch, due to large amounts of Loras and Checkpoints #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 [Bug]: The categories layout is different when localization is on #14591 using translated content to do categories mapping (#14995)
• fix: the split_threshold parameter does not work when running Split oversized images (#15006)

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 ()
• 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)
• Use original App Title in progress bar (#14916)

Full Changelog: v1.7.0...v1.8.0-RC

---

This discussion was created from the release 1.8.0-RC.

[noisefloordev]

Soft inpainting sounds big. For ages I've been doing this manually, inpainting at a higher strength, then inpainting with a lower strength and masking them together to blend things back together. This mighit save a bunch of those steps and do the same thing a lot more smoothly.

[sirdystically]

stable-cascade support?

[bobba84]

PLEASE guys let us know if this is in the pipeline? :D

[madman404]

The release candidate appears to have broken soft inpainting or moved it without saying where to. The extension is enabled but the option is gone.

[w-e-w]

seems to be showing normally for me

[emotionaldreams]

it wont send png info to txt2img, img2,img etc.. first issue i have

[w-e-w]

cannot reproduce issue

[emotionaldreams]

got it working now. didn't do nothing but it seems to be working at the moment

[clayne]

Not sure if it's something on my end, but I'm getting double listings for upscalers in selection boxes. It's not every upscaler though...

I also see the same thing in img2img settings for default upscaler, so it's something lower level that affects whatever enumerates upscalers.

[Soulreaver90]

Same issue, easily reproduced. Also where do we put the DAT upscalers?

[clayne]

#15035

[noisefloordev]

The soft inpainting foldout is really big, and it's always visible when soft inpainting is enabled, so I have to scroll up and down twice as much as before when using it. It'd be nice if the settings were a separate foldout down with extension UIs at the bottom, and enabling it was just a checkbox instead of having to have the settings visible all the time when it's enabled.

[w-e-w]

you can directly click the checkbox to enable / disable it

[inferenceus]

Xformers 0.20 is not compatible with PyTorch 2.1.2 and fails to install when updating to stable-diffusion-webui 1.8.0-RC and running .webui-user.sh with --reinstall-torch argument. Is this a known issue or must it wait until upstream makes it compatible?

[ashleykleynhans]

xformers 0.0.23.post1 is compatible with torch 2.1.2, but you need CUDA 12.1+.

[inferenceus]

I have torch2.1.2+cu121 installed, as well as the latest Nvidia proprietary production driver with CUDA 12.4 support. Xformers states it's not compatible with Torch 2.1.2 when I attempt to install it. Perhaps I have to manually install it, but stable-diffusion-webui isn't doing it for me.

[SachiaLanlus]

Is it possible to use fp8 for storage on the device which does not support fp8 computation like pascal lineup?
Can it use fp8 to store the fp32 model and inference in fp32 precision?
Because some old device do not support fp16 compute.

[MikeKarakachanov]

Any Possible way to Use this Version with Intel Arc?
(Intel Ultra 7 155H , Intel Arc iGPU)

[KohakuBlueleaf]

Wait IPEX team to support Arc iGPU
Arc A770/A750/A380 can be used in this version.

[iedoma]

Could anyone use DEFORUM or INFINITE ZOOM with this 1.8-RC version?
In my case, after installing everything again it still doesn't show the TABS of those extensions... (I haven't tried installing others extension).
Thanks and kind regards!

[kotofey33]

similar problem with 1.8-RC version. Does not work DEFORUM and INFINITE ZOOM