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

fudyou

venv "D:\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
& z/ O* L/ `& u$ j" i- Lfatal: 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)]
) k" R/ s& |1 ~$ rVersion: <none>
Commit hash: ebf229bd1727a0f8f0d149829ce82e2012ba7318
Installing requirements
3 f  u1 {; h, q& ^7 n! a8 i7 [Launching Web UI with arguments: --autolaunch
No module 'xformers'. Proceeding without it.
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
) ]; X3 X, Q9 j, a6 u# TLoading 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
Running 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.
# O* G* e, W2 D9 _! }7 fStartup 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).
. W, |1 F# P" v; g- a6 e" gLoading VAE weights found near the checkpoint: D:\stable-diffusion-webui-directml\models\VAE\chilloutmix_NiPrunedFp32Fix.vae.ckpt
1 X) e! A- Q" Z- {0 @Applying optimization: InvokeAI... done.
0 O& f0 w7 N- H* PTextual inversion embeddings loaded(0):
5 i2 r+ O9 R6 ?Model 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

### Installation on Windows 10/11 with NVidia-GPUs using release package
3 S3 }3 Z" W$ }- z
1. Download `sd.webui.zip` from [v1.0.0-pre](https://github.com/AUTOMATIC1111 ... ases/tag/v1.0.0-pre) and extract it's contents.
9 X- z- g6 o; ?+ I/ w2. Run `update.bat`.
, i$ T, W. t! s& i/ S* b! B7 ?3. Run `run.bat`.
   > For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111 ... -Run-on-NVidia-GPUs)
4 t. Y1 A& f) P7 C
### Automatic Installation on Windows

! |2 R$ H' }: G  ]' G1. 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".
9 r/ o0 P/ h$ c/ f7 W2. Install [git](https://git-scm.com/download/win).
3 O2 n/ [8 G) z+ F6 A9 B/ t3. Download the stable-diffusion-webui-directml repository, for example by running `git clone https://github.com/lshqqytiger/s ... ebui-directml.git`.
/ e! p0 w" A$ M1 }6 X/ A4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
. V5 w& F5 v' F3 y! \7 w
! P/ p$ v5 D4 r# _9 v' P  L; L$ ~### Automatic Installation on Linux
% j* `6 a- s. O$ K' M' L5 t
9 I+ m& {  T. v& N2 g  q& u1 f7 @1. Install the dependencies:

```bash
# Debian-based:
sudo apt install wget git python3 python3-venv
4 U' D5 [6 I" q) F# O) E. e1 h# Red Hat-based:
+ a" i2 O# F5 W9 t6 {sudo dnf install wget git python3
# H4 g; ~8 G6 a9 p! z6 W7 B- Y# Arch-based:
sudo pacman -S wget git python3
  F% b. F0 W6 M```
: B% X% M. |" t' N% c
2 p+ C! T4 l. x0 w  a2. Navigate to the directory you would like the webui to be installed and execute the following command:
4 `2 p. g! {& u4 n- z9 Z# G  G
```bash
) M# C1 d, b/ z8 y5 j" lbash <(wget -qO- https://raw.githubusercontent.co ... bui/master/webui.sh)
```
* F7 y& ?/ }2 W$ o3 u+ H6 ^# U4 i
3. Run `webui.sh`.
4. Check `webui-user.sh` for options.

2 h3 \" ]# F7 b: `* h### Installation on Apple Silicon
- w& r: n. U/ m( }/ \
# g& L- o- P) K* ?; t4 O2 {Find the instructions [here](https://github.com/AUTOMATIC1111 ... on-on-Apple-Silicon).
$ o# b; `8 [$ E6 B; ]: u7 P
; I: G" Y6 |4 W1 z  d1 c## Contributing

+ |3 T5 ~% K! A) E+ X1 r7 T. u/ QHere's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111 ... i/wiki/Contributing)

2 n  [% z+ p# k/ K! R' T## Documentation

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

+ N- k: e2 l( q1 n# B4 S8 z- Y+ w## Credits
% [7 {( S) e. }4 t0 t" k/ l
" X9 C4 T( W* |, ]: S. Z' OLicenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.

  d; ^0 S' B' J. f" C( ^$ t- Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
- k-diffusion - https://github.com/crowsonkb/k-diffusion.git
- GFPGAN - https://github.com/TencentARC/GFPGAN.git
# p2 B3 s; d* _. `5 d' F- CodeFormer - https://github.com/sczhou/CodeFormer
7 @6 ~. q, ~( z8 M+ K8 k- ESRGAN - https://github.com/xinntao/ESRGAN
% |: g* k* y' ?9 B' H& P- 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
- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
$ B$ |) S" e# L* A9 V/ E4 u- 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)
- Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
! M! e3 ?- g2 Y6 |- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
' r: X+ k4 a( T  v6 b( ^9 |- 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
- 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)
- 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
: m+ U8 Q) G0 |- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
- Olive - https://github.com/microsoft/Olive
+ ?+ O9 W6 w8 M. k2 T: J- (You)
, `0 O! x5 Y1 g$ S  J+ R2 i+ M
9 ~5 k% _+ K, Q: l1 z
0 M% U' b2 P1 V4 W! w! `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