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

fudyou

venv "D:\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
; J* d7 z- {2 q3 C1 d" {7 J5 jfatal: 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)]
- a# c* p" u; r' PVersion: <none>
; r) ~* \2 |# i( ?5 I& l' d7 S9 Z2 ~Commit hash: ebf229bd1727a0f8f0d149829ce82e2012ba7318
8 Q# T3 k7 W8 N5 Z4 w1 }( Y3 p; DInstalling requirements
Launching Web UI with arguments: --autolaunch
No module 'xformers'. Proceeding without it.
( p6 W# B, M! Z5 }/ l" E: {Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
/ ]  G- A3 s$ A/ j! d" s( YLoading 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
. e6 E( @0 P1 O( F# ~0 _1 Z% zLatentDiffusion: Running in eps-prediction mode
Running on local URL:  http://127.0.0.1:7860
/ R# J7 v$ P7 U* V( P
2 i3 {* W9 R, C! t% U4 r' w9 Q% [$ xTo create a public link, set `share=True` in `launch()`.
9 s( y' @8 Z1 l1 ~. j" @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
) v: v% a) G( c1 y8 @Applying optimization: InvokeAI... done.
, [6 l7 V5 Q# T; dTextual inversion embeddings loaded(0):
1 E4 w2 M, X+ e0 O' yModel 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).

1 `) k5 G6 q) k# E2 n9 O

. `! h0 o0 A5 Q6 C! z

version:  •  python: 3.10.6  •  torch: 2.0.0+cpu  •  xformers: N/A  •  gradio: 3.31.0  •  checkpoint: fc2511737a
# i  h) o8 E+ Y. q- @5 D0 j

Git-2.41.0-64-bit

python-3.10.6-amd64
1 j# P  ?: Z: G

6 @+ I; c1 b! u& q### Installation on Windows 10/11 with NVidia-GPUs using release package
/ n, u7 ~+ `8 Q; X
# {9 Q3 P* O" y1. 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`.
0 z7 W5 Q/ g6 `' Y4 J( \% [3. Run `run.bat`.
, g6 o/ }1 B- |( u) z, R4 Q1 K   > For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111 ... -Run-on-NVidia-GPUs)

+ @5 W9 r8 m( j  Y. M5 w### Automatic Installation on Windows
* @7 j0 l0 [; q( J6 K1 y
! L/ K+ G. l6 k+ M0 u7 M1. 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".
6 u# I4 l! W- g, P! R% D6 n2. Install [git](https://git-scm.com/download/win).
: J9 L$ F* U0 z- A" V3. Download the stable-diffusion-webui-directml repository, for example by running `git clone https://github.com/lshqqytiger/s ... ebui-directml.git`.
4 k$ u% u/ ^$ s6 N; c4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.

### Automatic Installation on Linux
, s1 t& B0 E( i$ z
1. Install the dependencies:

```bash
# Debian-based:
sudo apt install wget git python3 python3-venv
* T6 w% E5 F& g  |7 x  e# Red Hat-based:
0 \9 B+ O( Y) h/ N: Usudo dnf install wget git python3
# Arch-based:
sudo pacman -S wget git python3
# z5 N! T. B. y% [- N; G0 a  M```

( t. t  \) q* x  @3 m+ B% T8 i; `: D2. Navigate to the directory you would like the webui to be installed and execute the following command:

( }7 k7 ~% `2 O+ |0 f```bash
bash <(wget -qO- https://raw.githubusercontent.co ... bui/master/webui.sh)
: }% Q' B9 A& p. }```
) N/ I1 Q4 S, l1 B- q1 o
; C. |. L0 i$ V; F3. Run `webui.sh`.
+ U8 Z1 N2 S- G4 c/ B% p& m4. Check `webui-user.sh` for options.

### Installation on Apple Silicon
8 u; i: D3 W2 O
# d2 f' R+ l& nFind the instructions [here](https://github.com/AUTOMATIC1111 ... on-on-Apple-Silicon).
& F# W& c* {9 \. O* I& t
## Contributing
# q* W9 O5 m3 g% K$ r; T: H/ [$ }
. v' k& u3 n& H) B+ F& e* M. d* FHere's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111 ... i/wiki/Contributing)

## Documentation

The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).

3 h/ W1 \/ I1 b  h0 V## Credits

# [- m8 X- k" [4 Z* |: xLicenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
8 W& F: m1 S( F
9 C$ c( J( U* q1 [- Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
. V; b' G( K- Q5 m# R% D' f  J- k-diffusion - https://github.com/crowsonkb/k-diffusion.git
1 k! k' m9 P4 ]: @# q; j- GFPGAN - https://github.com/TencentARC/GFPGAN.git
1 `: n2 P( b/ C- C- h: @- CodeFormer - https://github.com/sczhou/CodeFormer
$ I& \  V( R* B) _- ESRGAN - https://github.com/xinntao/ESRGAN
+ P7 z8 I% u& J- 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
: ?) ^# w7 {( a' q4 K6 k- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
+ P3 B" E4 q. t8 V9 d, O1 n4 ?3 M$ v( E- 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)
& k3 x  ]/ |0 `* g3 O- 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)
2 S+ d# e% ~4 }% `- Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
8 j: |  ]4 A6 d. r* F/ {4 l- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
$ W9 R, X: Z5 K- N! O) X7 \$ S/ v. _- 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
+ K, X3 J2 b7 V* U' n: l" g0 c- xformers - https://github.com/facebookresearch/xformers
- DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
7 ?) M; [# _3 ^- r  |) u8 q/ t# d) [- 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
. |% u1 ^- p9 H- H- UniPC sampler - Wenliang Zhao - https://github.com/wl-zhao/UniPC
- TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
; d  W5 y# S% ^- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
- Olive - https://github.com/microsoft/Olive
* L$ u7 F* Y4 R5 f( b8 C$ t5 z- (You)
2 M. U( U% i; T5 U1 n. X% R$ B
$ n1 J* D; X9 i
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