stable-diffusion-webui-directml AMD专用版2023/6/17

fudyou

venv "D:\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
fatal: No names found, cannot describe anything.
4 J- V+ K  V# E7 b4 V8 tPython 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
- i) N! [7 m9 g) g: KVersion: <none>
Commit hash: ebf229bd1727a0f8f0d149829ce82e2012ba7318
Installing requirements
Launching Web UI with arguments: --autolaunch
No module 'xformers'. Proceeding without it.
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
Loading weights [fc2511737a] from D:\stable-diffusion-webui-directml\models\Stable-diffusion\chilloutmix_NiPrunedFp32Fix.safetensors
; v5 j1 h) z# j* s. }Creating model from config: D:\stable-diffusion-webui-directml\configs\v1-inference.yaml
# \& Z2 }8 C% {- P) kLatentDiffusion: Running in eps-prediction mode
) d$ j4 v. Z: R8 Z1 X" TRunning on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
DiffusionWrapper has 859.52 M params.
Startup time: 15.1s (import torch: 3.6s, import gradio: 2.8s, import ldm: 1.0s, other imports: 4.4s, setup codeformer: 0.1s, load scripts: 1.7s, create ui: 0.7s, gradio launch: 0.7s).
Loading VAE weights found near the checkpoint: D:\stable-diffusion-webui-directml\models\VAE\chilloutmix_NiPrunedFp32Fix.vae.ckpt
/ ~  m6 d& d5 M' s8 c% gApplying optimization: InvokeAI... done.
. v& W  l' S: W1 tTextual inversion embeddings loaded(0):
% i: @2 W1 ^5 A" r  x3 bModel loaded in 5.6s (load weights from disk: 1.1s, create model: 0.8s, apply weights to model: 0.9s, apply half(): 0.5s, load VAE: 0.6s, move model to device: 1.5s).

version:  •  python: 3.10.6  •  torch: 2.0.0+cpu  •  xformers: N/A  •  gradio: 3.31.0  •  checkpoint: fc2511737a
* K% i& r5 q9 N7 ]" }

Git-2.41.0-64-bit
0 n; U% h6 C0 Q8 A2 m4 Q, v7 H$ U

python-3.10.6-amd64

### Installation on Windows 10/11 with NVidia-GPUs using release package

0 x) Q: w' D. ?" K& ?# f1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111 ... ases/tag/v1.0.0-pre) and extract it's contents.
* U, g5 D# L% }; |2 R2. Run `update.bat`.
3. Run `run.bat`.
6 {$ c4 b/ U6 p( M   > For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111 ... -Run-on-NVidia-GPUs)
# |, `- t% }0 Q' a5 P$ F* s5 d
9 i4 `7 k2 L# H/ f/ m* ~7 l; Z& N: B### Automatic Installation on Windows

" B5 c. d# d6 N1 E% ]! J1. Install [Python 3.10.6](https://www.python.org/downloads/release/python-3106/) (Newer version of Python does not support torch), checking "Add Python to PATH".
2. Install [git](https://git-scm.com/download/win).
3. Download the stable-diffusion-webui-directml repository, for example by running `git clone https://github.com/lshqqytiger/s ... ebui-directml.git`.
* x1 I0 a. L& }9 v4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
4 [* B2 t3 F/ E+ p( E. H
' }% J) V/ N7 s- z6 W### Automatic Installation on Linux

# r! A, ?5 T6 Z3 f5 p2 F- f5 n1. Install the dependencies:

$ t( X" M( a7 H7 e4 [! {& N0 l```bash
( c1 r; A, G0 [" M- ^, X7 k1 u# Debian-based:
sudo apt install wget git python3 python3-venv
: R8 c9 x2 `( }) g9 `9 u$ |  D6 J+ j# Red Hat-based:
; d4 E4 Y1 t( Bsudo dnf install wget git python3
# Arch-based:
sudo pacman -S wget git python3
2 T8 b* Z( l/ N! n. D```
% j, L* K/ c5 w, d* M- g& ]
3 f9 b8 w8 f9 [2. Navigate to the directory you would like the webui to be installed and execute the following command:

```bash
' h9 h8 d9 ]% Nbash <(wget -qO- https://raw.githubusercontent.co ... bui/master/webui.sh)
```

0 |1 j3 }! \$ @) g/ k3 P# G0 O7 _( a3. Run `webui.sh`.
4. Check `webui-user.sh` for options.

### Installation on Apple Silicon
/ E1 \; U* G6 Y6 _1 W, T
+ X: o. `; t! K, q1 S! bFind the instructions [here](https://github.com/AUTOMATIC1111 ... on-on-Apple-Silicon).
; J: A4 Z/ r$ ]. ?3 R9 Y
9 c2 A! f7 l/ L## Contributing
! O) j& |! F% O  v8 a$ \
Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111 ... i/wiki/Contributing)
5 A! J  E9 t. M7 k2 Y
## Documentation

+ |9 N$ a6 s+ u* O* m: c: `7 \The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
5 `: f" j" N! N
6 o# `$ g: I$ k& H- l8 ~- b9 Z## Credits

+ D0 ~, x2 ]  D: [/ \3 LLicenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.

4 A" ^/ T8 @- J* \0 D- Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
- k-diffusion - https://github.com/crowsonkb/k-diffusion.git
  N+ s  k8 n+ }1 [- GFPGAN - https://github.com/TencentARC/GFPGAN.git
4 A+ S! C: I" b3 M$ Z+ r- CodeFormer - https://github.com/sczhou/CodeFormer
- ESRGAN - https://github.com/xinntao/ESRGAN
8 O6 f  w: K9 d- c- SwinIR - https://github.com/JingyunLiang/SwinIR
- Swin2SR - https://github.com/mv-lab/swin2sr
- LDSR - https://github.com/Hafiidz/latent-diffusion
- MiDaS - https://github.com/isl-org/MiDaS
  P! m! A% c4 v- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
3 ~! [4 \$ ?; H- Cross Attention layer optimization - Doggettx - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
- Cross Attention layer optimization - InvokeAI, lstein - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)
- Sub-quadratic Cross Attention layer optimization - Alex Birch (https://github.com/Birch-san/diffusers/pull/1), Amin Rezaei (https://github.com/AminRezaei0x443/memory-efficient-attention)
+ q5 h: ~3 g6 Z9 Z  {+ v9 z3 r+ `- Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
6 P0 G  X/ B# F; W- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
" u$ q, {! i7 q7 Z1 r- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
9 H- I+ [7 X. e8 [: N: Y- CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator
- Idea for Composable Diffusion - https://github.com/energy-based- ... sion-Models-PyTorch
) P( \4 k* q! P/ e! Y& t- xformers - https://github.com/facebookresearch/xformers
- DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
; g/ T" w+ U, }, H9 V- C- Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (https://github.com/Birch-san/diffusers-play/tree/92feee6)
- Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - https://github.com/timothybrooks/instruct-pix2pix
- Security advice - RyotaK
- UniPC sampler - Wenliang Zhao - https://github.com/wl-zhao/UniPC
* D. {+ Y& f$ q5 T# `! p& _* M2 e: _- TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
3 i* ^* ?; y& O& T; X- Olive - https://github.com/microsoft/Olive
- (You)
- B0 y' Z4 t: p9 k; n) I

( m$ u, j+ d% y, X; lhttps://cloud.189.cn/t/FvqQbeZfYrui （访问码：9ur0）

必先安装运行环境：（安装包在网盘根目录下）

1.Git-2.41.0-64-bit

2.python-3.10.6-amd64，注意安装时选中安装"Add Python to PATH"

3.启动器运行依赖。net-dotnet-6.0.11

以上运行环境安装完毕后，打开根目录"webui-user.bat"等待数秒即可打开stable-diffusion-webui，若然是系统自带IE浏览器打开的话，需要手动指定版本更高的Edge进入地址：http://127.0.0.1:7860

gn01127083

下載.看好不好用