Automatic1111 stable-diffusion-webui SD SDXL 1.9更新内容

https://pan.quark.cn/s/8e66ada8a434

SD启动器2024最新版本下载
链接:https://pan.quark.cn/s/eea6375642fd
百度网盘复制到vx打开:
#小程序://百度网盘/QLGKUjisbuziV4B

1.9.0
特征:
根据模型时间步长而不是采样步骤进行精简程序切换 (#14978)
添加一个选项,使其具有旧样式的目录视图而不是树视图;额外网络排序/搜索控件的样式更改
添加用于重新排序回调的 UI,支持在扩展元数据中指定回调顺序 (#15205)
适用于 SDXL-Lightning 型号的 Sgm 统一调度程序 (#15325)
主 UI 中的调度程序选择(#15333、#15361、#15394)
次要:
“打开映像目录”按钮现在打开实际目录 (#14947)
支持使用 LyCORIS BOFT 网络进行推理(#14871、#14973)
默认情况下,将额外的网卡描述设置为纯文本,并可选择按原样重新启用 HTML
调整额外网络的大小句柄 (#15041)
cmd args: 和 (#15031–unix-filenames-sanitization–filenames-max-length)
在 HTML 表中显示额外的网络参数,而不是原始 JSON (#15131)
添加对 LoRA/LoHa/LoKr 的 DoRA(权重分解)支持(#15160、#15283)
添加 ‘–no-prompt-history’ cmd args 以禁用上一代提示历史记录 (#15189)
替换预览时更新预览 (#15201)
仅获取扩展的活动 Git 分支的更新 (#15233)
将高档后处理 UI 放入折叠式琴中 (#15223)
支持拖拽 URL 读取信息文本 (#15262)
使用 Diskcache 库进行缓存 (#15287, #15299)
允许 PNG-RGBA 用于附加选项卡 (#15334)
支持嵌入 safetensors 元数据的封面图像 (#15319)
使用 NN upscale 时中断速度更快 (#15380)
Extras upscaler:用于限制输出图像最大边长的输入字段(#15293、#15415、#15417、#15425)
添加一个选项以隐藏“附加”选项卡中的后处理选项
扩展和 API:
ResizeHandleRow - 允许覆盖列刻度参数 (#15004)
提前调用 script_callbacks.ui_settings_callback;修复了 extra-options-section 内置扩展在使用不存在的设置时会杀死 UI 的问题
可以在 WebUI 上下文之外使用zoom.js (#15286, #15288)
允许在 metadata.ini 中更改扩展名 (#15290)
在执行重新加载 UI 时,使重新加载 UI 脚本成为可选,默认情况下关闭
放请求:gr。在类似于 txt2img 的 img2img 函数开始时发出请求
open_folder 作为 util (#15442)
可以将扩展的脚本文件导入为 (#15423import scripts.)
性能:
额外网络 HTML 页面的性能优化
优化额外网络过滤
优化额外网络排序
Bug修复:
防止逃生按钮在尚未生成时造成中断
[bug] 避免 Inpaint 中的 doble 升级 (#14966)
在某些情况下,对于额外的网络,重新加载按钮不出现的可能修复。
修复:运行拆分超大图像时该参数不起作用 (#15006split_threshold)
修复垂直布局(移动)的调整大小手柄可见性 (#15010)
register_tmp_file也适用于 mtime (#15012)
在精简程序切换期间保护alphas_cumprod (#14979)
修复 API 镜像加载中的 EXIF 方向问题 (#15062)
仅在提示中实际使用时覆盖强调 (#15141)
修复了 (#15142 中缺少的强调信息文本params.txt)
修复extract_style_text_from_prompt #15132 (#15135)
修复 AnimateDiff 的软画图 (#15148)
编辑注意:取消选择周围的空格 (#15178)
杂务:修复字体未加载的问题 (#15183)
按路径排序时,在额外网络中使用自然排序
修复 torch.nn.MultiheadAttention 导致的内置 lora 系统 bug (#15190)
避免 get_learned_conditioning 中“无”出错 (#15191)
写入元数据后向 MassFileLister 添加条目 (#15199)
修复了使用“雇用”提示符时样式的问题(#15269、#15276)
从招聘修复提示中删除评论 (#15263)
使 imageviewer 事件侦听器浏览器保持一致 (#15261)
修复了尝试获取 MultiheadAttention 权重时 OFT 中的 AttributeError (#15260)
将缺少的 .mean() 添加回去 (#15239)
修复“恢复进度”按钮 (#15221)
修复 InputAccordion [custom_script_source] 的 ui-config (#15231)
手柄 0 轮 deltaY (#15268)
阻止 Firefox 的替代菜单 (#15267)
修复:修复语法错误 (#15179)
还原输出路径 (#15307)
转义btn_copy_path文件名 (#15316)
修复文件名包含撇号时的额外网络按钮 (#15331)
LoRa 随机提示生成器中的转义括号 (#15343)
修复:Python 版本检查 PyTorch 安装兼容性 (#15390)
修复 call_queue.py 中的拼写错误 (#15386)
修复:找到already_loaded模型时,删除由数组索引加载 (#15382)
修复了 SD 模型内存管理的小错误 (#15350)
修复 CodeFormer 权重 (#15414)
修复:删除 ordered_callbacks_map 中的脚本回调 (#15428)
修复有限的文件写入(谢谢,Sylwia)
修复超单镜像 API 无法执行升级失败的问题 (#15465)
处理可调用对象paste_field出错 (#15470)
硬件:
为 Ascend NPU 添加训练支持并更改 lspci (#14981)
ROCm5.7 和 PyTorch 更新 (#14820)
针对 Navi1 的更好解决方法,删除 Navi3 的 --pre (#15224)
Ascend NPU wiki 页面 (#15228)
其他:
更新 Pad 提示符/否定提示符 v0 的注释以添加有关截断的警告,使其覆盖 v1 实现
支持 Touch (平板电脑) 的可调整大小列 (#15002)
修复 #14591 使用翻译内容进行类别映射 (#14995)
使用规范化文件路径的路径 (#15035absolute)
resizeHandle 手柄双击 (#15065)
–dat-models-path cmd 标志 (#15039)
添加指向二进制版本的直接链接 (#15059)
upscaler_utils:减少日志记录 (#15084)
使用 crate-ci/typos 修复各种拼写错误 (#15116)
fix_jpeg_live_preview (#15102)
[替代修复] 如果在 UI 中选择了错误的额外选项,则无法加载 WebUI (#15121)
对不支持的透明度进行错误处理 (#14958)
将模型描述添加到搜索词 (#15198)
凹凸动作版本 (#15272)
PEP 604 注释 (#15259)
当用户选择升级模型时,自动设置比例值 (#15244)
将训练后处理移动到内置扩展中 (#15222)
键入提示 shared.py (#15211)
将 ruff 更新到 0.3.3
更新 pytorch 闪电实用程序 (#15310)
将大小添加为 XYZ 网格选项 (#15354)
将 HF_ENDPOINT 变量用于 HuggingFace 域,默认 (#15443)
重新添加update_file_entry (#15446)
create_infotext允许索引和可调用的返工雇用提示信息文本 (#15460)
更新restricted_opts以包含 --hide-ui-dir-config 的更多选项 (#15492)

1.9.0
Features:
Make refiner switchover based on model timesteps instead of sampling steps (#14978)
add an option to have old-style directory view instead of tree view; stylistic changes for extra network sorting/search controls
add UI for reordering callbacks, support for specifying callback order in extension metadata (#15205)
Sgm uniform scheduler for SDXL-Lightning models (#15325)
Scheduler selection in main UI (#15333, #15361, #15394)
Minor:
“open images directory” button now opens the actual dir (#14947)
Support inference with LyCORIS BOFT networks (#14871, #14973)
make extra network card description plaintext by default, with an option to re-enable HTML as it was
resize handle for extra networks (#15041)
cmd args: --unix-filenames-sanitization and --filenames-max-length (#15031)
show extra networks parameters in HTML table rather than raw JSON (#15131)
Add DoRA (weight-decompose) support for LoRA/LoHa/LoKr (#15160, #15283)
Add ‘–no-prompt-history’ cmd args for disable last generation prompt history (#15189)
update preview on Replace Preview (#15201)
only fetch updates for extensions’ active git branches (#15233)
put upscale postprocessing UI into an accordion (#15223)
Support dragdrop for URLs to read infotext (#15262)
use diskcache library for caching (#15287, #15299)
Allow PNG-RGBA for Extras Tab (#15334)
Support cover images embedded in safetensors metadata (#15319)
faster interrupt when using NN upscale (#15380)
Extras upscaler: an input field to limit maximul side length for the output image (#15293, #15415, #15417, #15425)
add an option to hide postprocessing options in Extras tab
Extensions and API:
ResizeHandleRow - allow overriden column scale parametr (#15004)
call script_callbacks.ui_settings_callback earlier; fix extra-options-section built-in extension killing the ui if using a setting that doesn’t exist
make it possible to use zoom.js outside webui context (#15286, #15288)
allow variants for extension name in metadata.ini (#15290)
make reloading UI scripts optional when doing Reload UI, and off by default
put request: gr.Request at start of img2img function similar to txt2img
open_folder as util (#15442)
make it possible to import extensions’ script files as import scripts. (#15423)
Performance:
performance optimization for extra networks HTML pages
optimization for extra networks filtering
optimization for extra networks sorting
Bug Fixes:
prevent escape button causing an interrupt when no generation has been made yet
[bug] avoid doble upscaling in inpaint (#14966)
possible fix for reload button not appearing in some cases for extra networks.
fix: the split_threshold parameter does not work when running Split oversized images (#15006)
Fix resize-handle visability for vertical layout (mobile) (#15010)
register_tmp_file also for mtime (#15012)
Protect alphas_cumprod during refiner switchover (#14979)
Fix EXIF orientation in API image loading (#15062)
Only override emphasis if actually used in prompt (#15141)
Fix emphasis infotext missing from params.txt (#15142)
fix extract_style_text_from_prompt #15132 (#15135)
Fix Soft Inpaint for AnimateDiff (#15148)
edit-attention: deselect surrounding whitespace (#15178)
chore: fix font not loaded (#15183)
use natural sort in extra networks when ordering by path
Fix built-in lora system bugs caused by torch.nn.MultiheadAttention (#15190)
Avoid error from None in get_learned_conditioning (#15191)
Add entry to MassFileLister after writing metadata (#15199)
fix issue with Styles when Hires prompt is used (#15269, #15276)
Strip comments from hires fix prompt (#15263)
Make imageviewer event listeners browser consistent (#15261)
Fix AttributeError in OFT when trying to get MultiheadAttention weight (#15260)
Add missing .mean() back (#15239)
fix “Restore progress” button (#15221)
fix ui-config for InputAccordion [custom_script_source] (#15231)
handle 0 wheel deltaY (#15268)
prevent alt menu for firefox (#15267)
fix: fix syntax errors (#15179)
restore outputs path (#15307)
Escape btn_copy_path filename (#15316)
Fix extra networks buttons when filename contains an apostrophe (#15331)
escape brackets in lora random prompt generator (#15343)
fix: Python version check for PyTorch installation compatibility (#15390)
fix typo in call_queue.py (#15386)
fix: when find already_loaded model, remove loaded by array index (#15382)
minor bug fix of sd model memory management (#15350)
Fix CodeFormer weight (#15414)
Fix: Remove script callbacks in ordered_callbacks_map (#15428)
fix limited file write (thanks, Sylwia)
Fix extra-single-image API not doing upscale failed (#15465)
error handling paste_field callables (#15470)
Hardware:
Add training support and change lspci for Ascend NPU (#14981)
Update to ROCm5.7 and PyTorch (#14820)
Better workaround for Navi1, removing --pre for Navi3 (#15224)
Ascend NPU wiki page (#15228)
Other:
Update comment for Pad prompt/negative prompt v0 to add a warning about truncation, make it override the v1 implementation
support resizable columns for touch (tablets) (#15002)
Fix #14591 using translated content to do categories mapping (#14995)
Use absolute path for normalized filepath (#15035)
resizeHandle handle double tap (#15065)
–dat-models-path cmd flag (#15039)
Add a direct link to the binary release (#15059)
upscaler_utils: Reduce logging (#15084)
Fix various typos with crate-ci/typos (#15116)
fix_jpeg_live_preview (#15102)
[alternative fix] can’t load webui if selected wrong extra option in ui (#15121)
Error handling for unsupported transparency (#14958)
Add model description to searched terms (#15198)
bump action version (#15272)
PEP 604 annotations (#15259)
Automatically Set the Scale by value when user selects an Upscale Model (#15244)
move postprocessing-for-training into builtin extensions (#15222)
type hinting in shared.py (#15211)
update ruff to 0.3.3
Update pytorch lightning utilities (#15310)
Add Size as an XYZ Grid option (#15354)
Use HF_ENDPOINT variable for HuggingFace domain with default (#15443)
re-add update_file_entry (#15446)
create_infotext allow index and callable, re-work Hires prompt infotext (#15460)
update restricted_opts to include more options for --hide-ui-dir-config (#15492)

  • 34
    点赞
  • 13
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
您好,以下是根据您的要求编写的Windows10自动部署StableDiffusion的Bat脚本: ```bat @echo off set home=%cd% set python=%home%\python set git=%home%\git set stable_diffusion=%home%\stable-diffusion echo 正在检查Python安装情况... if not exist %python%\python.exe ( echo 未检测到Python,正在安装Python 3.10.9... mkdir %python% cd %python% curl -o python.msi https://www.python.org/ftp/python/3.10.9/python-3.10.9-amd64.exe start /wait python.msi /quiet InstallAllUsers=1 PrependPath=1 Include_test=0 del python.msi echo Python安装完成! ) else ( echo 已检测到Python,正在检查更新... cd %python% curl -o current_version.txt https://www.python.org/ftp/python/3.10.9/python-3.10.9-amd64.exe for /f "delims=" %%a in (current_version.txt) do set current_version=%%a del current_version.txt for /f "tokens=2 delims=." %%a in ('python --version 2^>^&1') do set installed_version=%%a if %installed_version% LSS %current_version% ( echo 发现新版本Python,正在更新... curl -o python.msi https://www.python.org/ftp/python/3.10.9/python-3.10.9-amd64.exe start /wait python.msi /quiet InstallAllUsers=1 PrependPath=1 Include_test=0 del python.msi echo Python更新完成! ) else ( echo Python已是最新版本! ) ) echo. echo 正在检查Git安装情况... if not exist %git%\bin\git.exe ( echo 未检测到Git,正在安装Git 2.40.1... mkdir %git% cd %git% curl -o git.exe https://github.com/git-for-windows/git/releases/download/v2.40.1.windows.1/Git-2.40.1-64-bit.exe start /wait git.exe /VERYSILENT /NORESTART /SUPPRESSMSGBOXES /CLOSEAPPLICATIONS /SP- /RESTARTAPPLICATIONS /COMPONENTS="icons,ext\reg\shellhere,assoc,assoc_sh" del git.exe echo Git安装完成! ) else ( echo 已检测到Git,正在检查更新... cd %git% curl -o current_version.txt https://github.com/git-for-windows/git/releases/download/v2.40.1.windows.1/Git-2.40.1-64-bit.exe for /f "delims=" %%a in (current_version.txt) do set current_version=%%a del current_version.txt for /f "tokens=3 delims= " %%a in ('git --version') do set installed_version=%%a if %installed_version% LSS %current_version% ( echo 发现新版本Git,正在更新... curl -o git.exe https://github.com/git-for-windows/git/releases/download/v2.40.1.windows.1/Git-2.40.1-64-bit.exe start /wait git.exe /VERYSILENT /NORESTART /SUPPRESSMSGBOXES /CLOSEAPPLICATIONS /SP- /RESTARTAPPLICATIONS /COMPONENTS="icons,ext\reg\shellhere,assoc,assoc_sh" del git.exe echo Git更新完成! ) else ( echo Git已是最新版本! ) ) echo. echo 正在克隆StableDiffusion... if not exist %stable_diffusion% ( echo 未检测到StableDiffusion,正在克隆https://github.com/AUTOMATIC1111/stable-diffusion-webui... cd %home% git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui %stable_diffusion% echo StableDiffusion克隆完成! ) else ( cd %stable_diffusion% git remote get-url origin | findstr /C:"https://github.com/AUTOMATIC1111/stable-diffusion-webui" >nul if %errorlevel% equ 0 ( echo 已检测到StableDiffusion,正在更新... git pull echo StableDiffusion更新完成! ) else ( echo StableDiffusion非指定版本,正在清空文件夹并重新克隆https://github.com/AUTOMATIC1111/stable-diffusion-webui... rd /s /q %stable_diffusion% git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui %stable_diffusion% echo StableDiffusion克隆完成! ) ) pause ``` 脚本执行完毕后会自动暂停,您可以手动关闭窗口。如果需要自动关闭窗口,可以将最后一行的 `pause` 改为 `timeout /t 5 >nul`,表示等待5秒后自动关闭窗口。

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值