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.
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
, v2 O( ~2 r; e8 u/ }3 ^* O9 AVersion: <none>
Commit hash: ebf229bd1727a0f8f0d149829ce82e2012ba7318
0 Z, H/ {" c$ ^+ s, {Installing requirements
4 l, G" D" x: Y* @- m5 h) BLaunching Web UI with arguments: --autolaunch
No module 'xformers'. Proceeding without it.
8 a+ d- u# U$ E! ?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
Creating model from config: D:\stable-diffusion-webui-directml\configs\v1-inference.yaml
( |8 X7 e% {% Q' a( }LatentDiffusion: Running in eps-prediction mode
/ n; \( k6 V: S9 i8 a) {( ~Running on local URL:  http://127.0.0.1:7860

3 k* a+ k- m$ F# ~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).
4 }0 I# |* b8 n; D; R: m% \Loading VAE weights found near the checkpoint: D:\stable-diffusion-webui-directml\models\VAE\chilloutmix_NiPrunedFp32Fix.vae.ckpt
Applying optimization: InvokeAI... done.
0 t7 P3 V; c0 N6 J5 X4 B& F: FTextual inversion embeddings loaded(0):
3 @* }4 a; Y4 i' NModel 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

python-3.10.6-amd64
9 Z* R8 e$ \6 ^& n6 q8 W) W3 e

% P( f/ h7 M( E### Installation on Windows 10/11 with NVidia-GPUs using release package
  M- K3 B# g; T  H+ v; s1 X
8 N6 R3 b& l9 h" E1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111 ... ases/tag/v1.0.0-pre) and extract it's contents.
2. Run `update.bat`.
: E  S% S8 {4 X$ m3. Run `run.bat`.
   > For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111 ... -Run-on-NVidia-GPUs)
; I0 b- j  T+ g+ P( P
### Automatic Installation on Windows
$ }: k7 `7 S- c/ F& m: V# C# H
8 q3 }' A. n9 G: I1. 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 c- {# T( k' w  f% N% Y2 q2. 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`.
9 l) K0 ]. \, q- U4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.

### Automatic Installation on Linux

1. Install the dependencies:

" T* z' q, E5 R- u: I5 W1 d```bash
# Debian-based:
sudo apt install wget git python3 python3-venv
; ], g' b7 R; t# Red Hat-based:
  f3 d1 R# O& Y2 \sudo dnf install wget git python3
5 J& m9 _2 ?) k' Z! m1 q# Arch-based:
  A  r- P+ i9 G$ [sudo pacman -S wget git python3
) v0 L. f$ j% Z1 Q```

5 j3 G+ g" X% V9 C( ]: T; Y2. Navigate to the directory you would like the webui to be installed and execute the following command:
7 ?% M4 D3 Z$ W: `$ M& d5 o5 D6 R) p
```bash
* ~2 z9 O0 h* T2 M& }bash <(wget -qO- https://raw.githubusercontent.co ... bui/master/webui.sh)
" j2 w$ o" l3 M0 D```

  Z. `+ j+ d4 h6 t8 W3. Run `webui.sh`.
$ t$ u# u' s# R& L' d4. Check `webui-user.sh` for options.

### Installation on Apple Silicon

Find the instructions [here](https://github.com/AUTOMATIC1111 ... on-on-Apple-Silicon).
1 }% h8 B3 u7 O4 A& U
4 Y: R1 p9 L4 e, l1 x3 @## Contributing
, h7 Z- W- Q8 x- z4 ]7 g
9 C: z  c; I5 S7 [. fHere's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111 ... i/wiki/Contributing)

: o8 y$ C/ b* |! p* ?* I( o## Documentation
# F; T$ w9 c1 }$ |3 d, a* \
The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).

## Credits

Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.

- Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
4 S$ y& S$ @, ^/ z9 K% o- k-diffusion - https://github.com/crowsonkb/k-diffusion.git
4 K6 V3 L! H0 h: c; }1 N4 u- GFPGAN - https://github.com/TencentARC/GFPGAN.git
- CodeFormer - https://github.com/sczhou/CodeFormer
0 c% H# e! k2 @- ESRGAN - https://github.com/xinntao/ESRGAN
6 s* N$ c5 y$ b) s7 p; R- SwinIR - https://github.com/JingyunLiang/SwinIR
0 @/ P; v$ P- h" L) J! ^/ v- Swin2SR - https://github.com/mv-lab/swin2sr
$ U8 j9 p* f) M9 a* `' T5 `- LDSR - https://github.com/Hafiidz/latent-diffusion
- MiDaS - https://github.com/isl-org/MiDaS
" A1 f2 m7 F$ g, q- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
- 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)
' {3 m, }( e8 b+ ?1 |3 u+ m- 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)
- Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
$ L) J8 P/ Q) r+ |5 k  I/ M- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
7 S3 c; U7 E2 ]: u) P6 m' E+ }- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
- {: E8 `/ P. a7 v0 _4 {6 M- CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator
7 z3 T5 \# s7 R: p' L' u  m- Idea for Composable Diffusion - https://github.com/energy-based- ... sion-Models-PyTorch
- xformers - https://github.com/facebookresearch/xformers
6 k* n) P6 X# k- l% j/ f- DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
: Z5 z, N: T9 [4 `% e- 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
- TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
/ n: T+ x" Q# S3 ]6 A3 n0 S, z- Olive - https://github.com/microsoft/Olive
- (You)
( l3 w7 V0 s: p9 l3 M

% g- l3 W, D  h# ?4 j0 ^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