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

fudyou

venv "D:\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
& o5 G, c3 q, s4 M2 t; A; i/ dfatal: No names found, cannot describe anything.
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: <none>
9 g7 F( z: H! E3 D5 N+ n9 v* J8 DCommit hash: ebf229bd1727a0f8f0d149829ce82e2012ba7318
) D$ k( t8 ]+ I0 XInstalling requirements
: C+ S, a6 t1 L" D3 F5 x& X0 U: BLaunching Web UI with arguments: --autolaunch
3 G4 g- k+ s7 @& g% C# LNo module 'xformers'. Proceeding without it.
- }8 r; A$ s1 }3 h7 TWarning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
/ \" |3 q" S. C+ \Loading weights [fc2511737a] from D:\stable-diffusion-webui-directml\models\Stable-diffusion\chilloutmix_NiPrunedFp32Fix.safetensors
Creating model from config: D:\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
3 B2 [' H3 _0 f5 v& Z/ a" g5 R* BRunning on local URL:  http://127.0.0.1:7860
/ H6 {" b1 {4 ~- `: g% Z( d* r
% Y0 g6 }& Y. F7 y2 X5 k1 D3 QTo create a public link, set `share=True` in `launch()`.
DiffusionWrapper has 859.52 M params.
* }1 y2 I4 K) A) _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
Applying optimization: InvokeAI... done.
: k* \6 ~& O: o- Q$ D# JTextual inversion embeddings loaded(0):
9 o. I7 Q, s& u3 O% aModel 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

Git-2.41.0-64-bit
5 B- ^1 X7 i8 U6 m  H

python-3.10.6-amd64
4 ?" v# c8 h& G" w+ C5 i# e

' [8 V( J+ n. Y: n5 I' r8 g### Installation on Windows 10/11 with NVidia-GPUs using release package

1 L8 b/ i; M: \3 M1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111 ... ases/tag/v1.0.0-pre) and extract it's contents.
- d7 B- _" o! `! U9 g7 {0 R3 k2. Run `update.bat`.
9 Z$ P6 `0 G* i7 I% {: t& {3. Run `run.bat`.
   > For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111 ... -Run-on-NVidia-GPUs)

/ L  ?7 Q- g5 f: g0 T4 r  K( R: ]### Automatic Installation on Windows
" N- g0 J8 o& |
1 d/ d, e6 d9 Q6 h  L: b! W2 k1. 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".
' Y8 j% B) P6 w. \$ Q7 F0 h# N/ z2. Install [git](https://git-scm.com/download/win).
2 Q7 Q! D/ |6 O/ h3. Download the stable-diffusion-webui-directml repository, for example by running `git clone https://github.com/lshqqytiger/s ... ebui-directml.git`.
4 }0 k; q  x% \. [8 J5 _4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
: \# |. h! A" d- e) O3 `0 ~& s: H
### Automatic Installation on Linux
5 e, K; M0 n' V4 x
1. Install the dependencies:

```bash
# Debian-based:
3 s& _4 `) ^# h2 @7 K' x5 {& Jsudo apt install wget git python3 python3-venv
7 v) Y; u6 Q6 p3 ~# Red Hat-based:
sudo dnf install wget git python3
% M5 a+ W- I7 r5 O& U5 W# Arch-based:
sudo pacman -S wget git python3
```

2. Navigate to the directory you would like the webui to be installed and execute the following command:

```bash
7 X, c. q) W1 I6 D1 Zbash <(wget -qO- https://raw.githubusercontent.co ... bui/master/webui.sh)
0 R1 B# d9 h  M0 m```

( E& n  @$ y  o3 o0 a9 L* w3. Run `webui.sh`.
4. Check `webui-user.sh` for options.
( `4 @- b9 K0 P) |
* q( @$ V/ N" b# r8 E# r### Installation on Apple Silicon

2 I. t- z+ ?$ g6 t7 t* D7 P1 cFind the instructions [here](https://github.com/AUTOMATIC1111 ... on-on-Apple-Silicon).

## Contributing

Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111 ... i/wiki/Contributing)

* Q& i6 P- P5 F5 E8 w## Documentation

The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
6 n# k6 d$ e  ?& X
## Credits
" b: p6 \2 m* R) V9 a0 s
% ~" l8 f. K( C. oLicenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.

- c9 }2 t- z& A; s5 @6 e+ I/ F- Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
5 I/ m8 w3 U1 k( L- \/ B- k-diffusion - https://github.com/crowsonkb/k-diffusion.git
- GFPGAN - https://github.com/TencentARC/GFPGAN.git
% M* t0 _( N& ~' l0 B% N- CodeFormer - https://github.com/sczhou/CodeFormer
; i/ Y) k2 I/ H' {& b) F: P- |- ESRGAN - https://github.com/xinntao/ESRGAN
- SwinIR - https://github.com/JingyunLiang/SwinIR
- Swin2SR - https://github.com/mv-lab/swin2sr
- LDSR - https://github.com/Hafiidz/latent-diffusion
2 @8 f, m/ v2 d6 r- MiDaS - https://github.com/isl-org/MiDaS
7 V7 ^" Z% G4 z& `. ^- p- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
4 r+ k5 `$ h% I9 d- 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)
' }! |8 z9 N$ {3 e) J- 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)
9 L+ J; r7 \3 E- Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
+ N% k; S' ^3 G# H+ F* \) Z- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
- 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
! x' P  s' g6 h/ {; a) e' R2 l- xformers - https://github.com/facebookresearch/xformers
- DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
- 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)
/ w0 l) i% M5 F- X2 {9 b% M. s- 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
; ^: i, E' s+ W! o- TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
- Olive - https://github.com/microsoft/Olive
- (You)
- S% J* M* O. h; _, l0 \# b

: y( |2 B& m/ l" P& f! n1 B: ^https://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