1.7.0-RC

[AUTOMATIC1111]

Features:

• settings tab rework: add search field, add categories, split UI settings page into many
• add altdiffusion-m18 support (#13364)
• support inference with LyCORIS GLora networks (#13610)
• add lora-embedding bundle system (#13568)
• option to move prompt from top row into generation parameters
• add support for SSD-1B (#13865)
• support inference with OFT networks (#13692)
• script metadata and DAG sorting mechanism (#13944)
• support HyperTile optimization (#13948)
• add support for SD 2.1 Turbo (#14170)
• remove Train->Preprocessing tab and put all its functionality into Extras tab
• initial IPEX support for Intel Arc GPU (#14171)

Minor:

• allow reading model hash from images in img2img batch mode (#12767)
• add option to align with sgm repo's sampling implementation (#12818)
• extra field for lora metadata viewer: ss_output_name (#12838)
• add action in settings page to calculate all SD checkpoint hashes (#12909)
• add button to copy prompt to style editor (#12975)
• add --skip-load-model-at-start option (#13253)
• write infotext to gif images
• read infotext from gif images (#13068)
• allow configuring the initial state of InputAccordion in ui-config.json (#13189)
• allow editing whitespace delimiters for ctrl+up/ctrl+down prompt editing (#13444)
• prevent accidentally closing popup dialogs (#13480)
• added option to play notification sound or not (#13631)
• show the preview image in the full screen image viewer if available (#13459)
• support for webui.settings.bat (#13638)
• add an option to not print stack traces on ctrl+c
• start/restart generation by Ctrl (Alt) + Enter (#13644)
• update prompts_from_file script to allow concatenating entries with the general prompt (#13733)
• added a visible checkbox to input accordion
• added an option to hide all txt2img/img2img parameters in an accordion (#13826)
• added 'Path' sorting option for Extra network cards (#13968)
• enable prompt hotkeys in style editor (#13931)
• option to show batch img2img results in UI (#14009)
• infotext updates: add option to disregard certain infotext fields, add option to not include VAE in infotext, add explanation to infotext settings page, move some options to infotext settings page
• add FP32 fallback support on sd_vae_approx (#14046)
• support XYZ scripts / split hires path from unet (#14126)
• allow use of mutiple styles csv files (#14125)

Extensions and API:

• update gradio to 3.41.2
• support installed extensions list api (#12774)
• update pnginfo API to return dict with parsed values
• add noisy latent to ExtraNoiseParams for callback (#12856)
• show extension datetime in UTC (#12864, #12865, #13281)
• add an option to choose how to combine hires fix and refiner
• include program version in info response. (#13135)
• sd_unet support for SDXL
• patch DDPM.register_betas so that users can put given_betas in model yaml (#13276)
• xyz_grid: add prepare (#13266)
• allow multiple localization files with same language in extensions (#13077)
• add onEdit function for js and rework token-counter.js to use it
• fix the key error exception when processing override_settings keys (#13567)
• ability for extensions to return custom data via api in response.images (#13463)
• call state.jobnext() before postproces*() (#13762)
• add option to set notification sound volume (#13884)
• update Ruff to 0.1.6 (#14059)
• add Block component creation callback (#14119)
• catch uncaught exception with ui creation scripts (#14120)
• use extension name for determining an extension is installed in the index (#14063)
• update is_installed() from launch_utils.py to fix reinstalling already installed packages (#14192)

Bug Fixes:

• fix pix2pix producing bad results
• fix defaults settings page breaking when any of main UI tabs are hidden
• fix error that causes some extra networks to be disabled if both lora: and lyco: are present in the prompt
• fix for Reload UI function: if you reload UI on one tab, other opened tabs will no longer stop working
• prevent duplicate resize handler (#12795)
• small typo: vae resolve bug (#12797)
• hide broken image crop tool (#12792)
• don't show hidden samplers in dropdown for XYZ script (#12780)
• fix style editing dialog breaking if it's opened in both img2img and txt2img tabs
• hide --gradio-auth and --api-auth values from /internal/sysinfo report
• add missing infotext for RNG in options (#12819)
• fix notification not playing when built-in webui tab is inactive (#12834)
• honor --skip-install for extension installers (#12832)
• don't print blank stdout in extension installers (#12833, #12855)
• get progressbar to display correctly in extensions tab
• keep order in list of checkpoints when loading model that doesn't have a checksum
• fix inpainting models in txt2img creating black pictures
• fix generation params regex (#12876)
• fix batch img2img output dir with script (#12926)
• fix [Bug]: Colab error while training hypernetwork #13080 - Hypernetwork/TI preview generation (#13084)
• fix bug with sigma min/max overrides. (#12995)
• more accurate check for enabling cuDNN benchmark on 16XX cards (#12924)
• don't use multicond parser for negative prompt counter (#13118)
• fix data-sort-name containing spaces (#13412)
• update card on correct tab when editing metadata (#13411)
• fix viewing/editing metadata when filename contains an apostrophe (#13395)
• fix: --sd_model in "Prompts from file or textbox" script is not working (#13302)
• better Support for Portable Git (#13231)
• fix issues when webui_dir is not work_dir (#13210)
• fix: lora-bias-backup don't reset cache (#13178)
• account for customizable extra network separators whyen removing extra network text from the prompt (#12877)
• re fix batch img2img output dir with script (#13170)
• fix --ckpt-dir path separator and option use short name for checkpoint dropdown (#13139)
• consolidated allowed preview formats, Fix extra network .gif not woking as preview (#13121)
• fix venv_dir=- environment variable not working as expected on linux (#13469)
• repair unload sd checkpoint button
• edit-attention fixes (#13533)
• fix bug when using --gfpgan-models-path (#13718)
• properly apply sort order for extra network cards when selected from dropdown
• fixes generation restart not working for some users when 'Ctrl+Enter' is pressed (#13962)
• thread safe extra network list_items (#13014)
• fix not able to exit metadata popup when pop up is too big (#14156)
• fix auto focal point crop for opencv >= 4.8 (#14121)
• make 'use-cpu all' actually apply to 'all' (#14131)
• extras tab batch: actually use original filename
• make webui not crash when running with --disable-all-extensions option

Other:

• non-local condition (#12814)
• fix minor typos (#12827)
• remove xformers Python version check (#12842)
• style: file-metadata word-break (#12837)
• revert SGM noise multiplier change for img2img because it breaks hires fix
• do not change quicksettings dropdown option when value returned is None (#12854)
• [RC 1.6.0 - zoom is partly hidden] Update style.css (#12839)
• chore: change extension time format (#12851)
• WEBUI.SH - Use torch 2.1.0 release candidate for Navi 3 (#12929)
• add Fallback at images.read_info_from_image if exif data was invalid (#13028)
• update cmd arg description (#12986)
• fix: update shared.opts.data when add_option (#12957, #13213)
• restore missing tooltips (#12976)
• use default dropdown padding on mobile (#12880)
• put enable console prompts option into settings from commandline args (#13119)
• fix some deprecated types (#12846)
• bump to torchsde==0.2.6 (#13418)
• update dragdrop.js (#13372)
• use orderdict as lru cache:opt/bug (#13313)
• XYZ if not include sub grids do not save sub grid (#13282)
• initialize state.time_start befroe state.job_count (#13229)
• fix fieldname regex (#13458)
• change denoising_strength default to None. (#13466)
• fix regression (#13475)
• fix IndexError (#13630)
• fix: checkpoints_loaded:{checkpoint:state_dict}, model.load_state_dict issue in dict value empty (#13535)
• update bug_report.yml (#12991)
• requirements_versions httpx==0.24.1 (#13839)
• fix parenthesis auto selection (#13829)
• fix [Bug]: Prompt Scheduling Code Comment is Wrong #13796 (#13797)
• corrected a typo in modules/cmd_args.py (#13855)
• feat: fix randn found element of type float at pos 2 (#14004)
• adds tqdm handler to logging_config.py for progress bar integration (#13996)
• hotfix: call shared.state.end() after postprocessing done (#13977)
• fix dependency address patch 1 (#13929)
• save sysinfo as .json (#14035)
• move exception_records related methods to errors.py (#14084)
• compatibility (#13936)
• json.dump(ensure_ascii=False) (#14108)
• dir buttons start with / so only the correct dir will be shown and no… (#13957)
• alternate implementation for unet forward replacement that does not depend on hijack being applied
• re-add keyedit_delimiters_whitespace setting lost as part of commit e294e46 (#14178)
• fix save_samples being checked early when saving masked composite (#14177)
• slight optimization for mask and mask_composite (#14181)
• add import_hook hack to work around basicsr/torchvision incompatibility (#14186)

---

This discussion was created from the release v1.7.0-RC.

[andzejsp]

how do you use this release? Are these changes the same changes that are in dev branch?

[illtellyoulater]

https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/How-to-switch-to-different-versions-of-WebUI

[mikehdt]

Fantastic work! I've only noticed one thing trying this version: newlines are being stripped from the prompts when the image is saved, meaning if you read the image back in the prompts become one big blob of text. Not sure if that's intentional. Happy to raise a separate issue if need be, but it's not a biggie.

[w-e-w]

no actually it's a very big deal, anyway it's already fixed #14203

[ArxFusion]

Just want to check the UI issue on mobile phones regarding dropdown menus won't be fix until Automatic1111 uses another version of Gradio, its even worse in this release (yeah I know double posting).

[ArxFusion]

Cheers thanks for the update!

[w-e-w]

if you want to try you can switch to gradio4 fork to test
to see if the drop down menu "and they drop the menu only" is less glitchy (don't expect other things to work)

[ArxFusion]

I am trying to switch to the gradio4 fork, am I missing something? git switch did not work and I couldnt clone it either.

[ArxFusion]

Just tried it today, yeah issue is still there, its slightly better, but the line spacing is there and part of the other issue is when you select the drop down the keyboard becomes visible, this though has been an ongoing issue.

[w-e-w]

well the spacing is intentional
see #14052 (comment)
and I didn't see any other people complaining about that so I don't think it's going to be reverted

however if you don't like it you can customize it yourself by creating a user.css in webui root which overrides the default

.gradio-dropdown ul.options li.item {
    padding: 0.05em 0;
}

using user.css you can customize the padding and many other aspects of web UI however you like
it has the ability to override the default css

[RayHell]

There's an issue with Prompts from file or textbox . It's taking another prompt from the list for the hires fix pass.

[w-e-w]

can you explain in detail what you're saying

[huhyunjinscarseat]

I cant modify or save new styles. It will not modify the style.csv file.

[w-e-w]

this is a known issue
see report #14263
I fixed PR has already been made #14276

[HyunJae5463]

Hi, according to the creator of Reactor (Face Swap Extension), 1.7.0 seems to break "facexlib" and therefor face swapping gives weird results.
Gourieff/sd-webui-reactor#245 (comment)
Might also be an ipex related issue?

Can anyone look into it?

[tusharbhutt]

I'm attempting to use an ARC 770 16 GB card and am running into issues. My webui.bat looks like this:

set COMMANDLINE_ARGS= --use-ipex --autolaunch --skip-torch-cuda-test

I deleted the old venv folder and let it create a new one, and using Python 3.10 and dev version v1.7.0-RC-75-gaeaf1c51. The errors show up before an image is even generated and seem to be related to it being unable to load an SDXL model. Does ARC not use SDXL yet?

loading stable diffusion model: RuntimeError
Traceback (most recent call last):
  File "C:\Applications\Python310\lib\threading.py", line 973, in _bootstrap
    self._bootstrap_inner()
  File "C:\Applications\Python310\lib\threading.py", line 1016, in _bootstrap_inner
    self.run()
  File "C:\Applications\Python310\lib\threading.py", line 953, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\initialize.py", line 147, in load_model
    shared.sd_model  # noqa: B018
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\shared_items.py", line 128, in sd_model
    return modules.sd_models.model_data.get_sd_model()
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\sd_models.py", line 531, in get_sd_model
    load_model()
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\sd_models.py", line 681, in load_model
    sd_model.cond_stage_model_empty_prompt = get_empty_cond(sd_model)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\sd_models.py", line 566, in get_empty_cond
    d = sd_model.get_learned_conditioning([""])
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\sd_models_xl.py", line 31, in get_learned_conditioning
    c = self.conditioner(sdxl_conds, force_zero_embeddings=['txt'] if force_zero_negative_prompt else [])
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\repositories\generative-models\sgm\modules\encoders\modules.py", line 141, in forward
    emb_out = embedder(batch[embedder.input_key])
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\sd_hijack_clip.py", line 234, in forward
    z = self.process_tokens(tokens, multipliers)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\sd_hijack_clip.py", line 273, in process_tokens
    z = self.encode_with_transformers(tokens)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\sd_hijack_clip.py", line 349, in encode_with_transformers
    outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=self.wrapped.layer == "hidden")
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 822, in forward
    return self.text_model(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 740, in forward
    encoder_outputs = self.encoder(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 654, in forward
    layer_outputs = encoder_layer(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 382, in forward
    hidden_states = self.layer_norm1(hidden_states)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\extensions-builtin\Lora\networks.py", line 531, in network_LayerNorm_forward
    return originals.LayerNorm_forward(self, input)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\torch\nn\modules\normalization.py", line 190, in forward
    return F.layer_norm(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\torch\nn\functional.py", line 2515, in layer_norm
    return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled)
RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'


Stable diffusion model failed to load
Exception in thread Thread-16 (load_model):
Traceback (most recent call last):
  File "C:\Applications\Python310\lib\threading.py", line 1016, in _bootstrap_inner
    self.run()
  File "C:\Applications\Python310\lib\threading.py", line 953, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\initialize.py", line 153, in load_model
    devices.first_time_calculation()
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\devices.py", line 162, in first_time_calculation
    linear(x)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\extensions-builtin\Lora\networks.py", line 486, in network_Linear_forward
    return originals.Linear_forward(self, input)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\torch\nn\modules\linear.py", line 114, in forward
    return F.linear(input, self.weight, self.bias)
RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'
Startup time: 24.0s (prepare environment: 0.8s, import torch: 5.1s, import gradio: 1.6s, setup paths: 6.2s, initialize shared: 0.7s, other imports: 1.0s, setup codeformer: 0.2s, load scripts: 2.3s, create ui: 1.0s, gradio launch: 5.0s).
Traceback (most recent call last):
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\gradio\routes.py", line 488, in run_predict
    output = await app.get_blocks().process_api(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\gradio\blocks.py", line 1431, in process_api
    result = await self.call_function(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\gradio\blocks.py", line 1103, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
    return await future
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
    result = context.run(func, *args)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\gradio\utils.py", line 707, in wrapper
    response = f(*args, **kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\ui_extra_networks.py", line 419, in pages_html
    return refresh()
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\ui_extra_networks.py", line 425, in refresh
    pg.refresh()
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\ui_extra_networks_textual_inversion.py", line 13, in refresh
    sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings(force_reload=True)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\textual_inversion\textual_inversion.py", line 222, in load_textual_inversion_embeddings
    self.expected_shape = self.get_expected_shape()
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\textual_inversion\textual_inversion.py", line 154, in get_expected_shape
    vec = shared.sd_model.cond_stage_model.encode_embedding_init_text(",", 1)
AttributeError: 'NoneType' object has no attribute 'cond_stage_model'
Traceback (most recent call last):
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\gradio\routes.py", line 488, in run_predict
    output = await app.get_blocks().process_api(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\gradio\blocks.py", line 1431, in process_api
    result = await self.call_function(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\gradio\blocks.py", line 1103, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
    return await future
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
    result = context.run(func, *args)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\venv\lib\site-packages\gradio\utils.py", line 707, in wrapper
    response = f(*args, **kwargs)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\ui_extra_networks.py", line 419, in pages_html
    return refresh()
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\ui_extra_networks.py", line 425, in refresh
    pg.refresh()
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\ui_extra_networks_textual_inversion.py", line 13, in refresh
    sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings(force_reload=True)
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\textual_inversion\textual_inversion.py", line 222, in load_textual_inversion_embeddings
    self.expected_shape = self.get_expected_shape()
  File "C:\Applications\StableDiffusion\Automatic1111\webui\modules\textual_inversion\textual_inversion.py", line 154, in get_expected_shape
    vec = shared.sd_model.cond_stage_model.encode_embedding_init_text(",", 1)
AttributeError: 'NoneType' object has no attribute 'cond_stage_model'

[tusharbhutt]

Follow up: re-did the drive, added the "no-half" and "no-half-vae" and it is working... at 133 sec/it for 1024x1024 and 31 sec/it for 512x512 :(

[HyunJae5463]

Everything works fine for me and i only use --use-ipex on A770. Must be something on your end. SDXL Models also work fine and i generate 512x512 in 5 seconds. Try to reinstall 1.7 and only use --use-ipex before your first launch.

Can also try the SDXL VAE Fix first https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/tree/main

[Nuullll]

"LayerNormKernelImpl" not implemented for 'Half' is an indication that you're running with CPU backend somehow.

[tusharbhutt]

Thank you both @Nuullll and @HyunJae5463

I am pretty sure it's running off of the CPU too. I'm going to blow the whole thing away and start fresh.

UPDATE It works now, kind of. Getting 512x512x20 in 30-50 seconds on an SDXL model. Further investigation needed by me :)

If there are some optimization settings noted somewhere that I could copy to test please let me know