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

fudyou

venv "D:\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
+ C: }4 s$ ~6 u/ U4 u0 i. Ufatal: 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>
( U! O: V! y; J4 `7 tCommit hash: ebf229bd1727a0f8f0d149829ce82e2012ba7318
0 u2 o1 M: z6 W6 UInstalling requirements
Launching Web UI with arguments: --autolaunch
/ g' J4 Q! p: Q: gNo module 'xformers'. Proceeding without it.
+ s! Y% v0 I  S: A; c; j; ]! r: PWarning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
2 b1 b! b& w* Q# |, H3 `$ }9 MLoading weights [fc2511737a] from D:\stable-diffusion-webui-directml\models\Stable-diffusion\chilloutmix_NiPrunedFp32Fix.safetensors
2 \6 o2 D  ]/ {. `Creating model from config: D:\stable-diffusion-webui-directml\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
; _; H1 t+ _& L8 P8 \: L* GRunning on local URL:  http://127.0.0.1:7860

9 q* z4 Z. L7 H+ R( T, x! @To create a public link, set `share=True` in `launch()`.
4 d5 q3 y, ?/ s" ~- k+ m4 o$ {4 o$ _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).
) a9 z' h5 T& V" H. r- R; t9 ]Loading VAE weights found near the checkpoint: D:\stable-diffusion-webui-directml\models\VAE\chilloutmix_NiPrunedFp32Fix.vae.ckpt
/ i% Z: O* ?3 Q4 N! s  w+ O0 _Applying optimization: InvokeAI... done.
Textual inversion embeddings loaded(0):
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
# Q. D( c) U# H+ U: i. z

python-3.10.6-amd64
$ |* }) M+ G3 }" o! W: y

### Installation on Windows 10/11 with NVidia-GPUs using release package
& @" u5 c$ M) W
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.
2. Run `update.bat`.
3. Run `run.bat`.
1 U4 P; B1 T# T6 S4 ^" y  E# S# G   > For more details see [Install-and-Run-on-NVidia-GPUs](https://github.com/AUTOMATIC1111 ... -Run-on-NVidia-GPUs)

) y) b) I( D7 M: b" J- D### Automatic Installation on Windows
" r* d3 N4 B! v( S& v* r7 y
1. 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`.
4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.

/ V7 @4 J2 q- g7 ^2 o3 Q- l9 l+ L3 R### Automatic Installation on Linux

1. Install the dependencies:
; g! A. ]: S9 p+ k3 k# E
```bash
# Debian-based:
! s& [. w- Y9 }; p5 C" `sudo apt install wget git python3 python3-venv
0 F, ~0 q) I" o* L# Red Hat-based:
2 n1 _7 L7 M: A  Nsudo dnf install wget git python3
# Arch-based:
- x# J& U( T* u  Q" j% `sudo pacman -S wget git python3
8 @: l% c1 c+ f2 [```
9 v  l0 l& J: {1 T) T8 @
2. Navigate to the directory you would like the webui to be installed and execute the following command:
6 c* q! F- Z$ a- _
```bash
bash <(wget -qO- https://raw.githubusercontent.co ... bui/master/webui.sh)
```

3. Run `webui.sh`.
4. Check `webui-user.sh` for options.

### Installation on Apple Silicon

Find the instructions [here](https://github.com/AUTOMATIC1111 ... on-on-Apple-Silicon).

# c8 J. }* y/ p* ]4 B9 y1 U## Contributing

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

7 @! X# n6 w6 S$ n1 c* a/ e# h5 a## Documentation
, P( o/ e& e1 N- T, m) C* k5 C7 D
9 Y7 E, D* @) U$ @) e  R* vThe documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
* ?( c! N4 U5 O4 k
7 V" d# `- }) e- o$ r. k4 }3 h## 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
  Y: u6 H8 L# v7 @- k-diffusion - https://github.com/crowsonkb/k-diffusion.git
) F- W2 I2 F; }! P" V2 I! Z- GFPGAN - https://github.com/TencentARC/GFPGAN.git
- CodeFormer - https://github.com/sczhou/CodeFormer
8 x& ~+ u$ j" F$ `' K1 ~1 z2 ~3 G- ESRGAN - https://github.com/xinntao/ESRGAN
1 X; ^1 N  R' I8 `& P/ w- SwinIR - https://github.com/JingyunLiang/SwinIR
0 Y  g# ]. }5 J- k- Swin2SR - https://github.com/mv-lab/swin2sr
! z  V# E  T2 e+ h6 w0 V- LDSR - https://github.com/Hafiidz/latent-diffusion
/ e5 Z8 z3 _" S" k/ g% J+ M- MiDaS - https://github.com/isl-org/MiDaS
$ r/ m7 m# q) a1 x& _( [5 e- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
( l# L; y# X9 a- 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).
- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
6 c+ ?: b1 ]: O' O+ ?& u- 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
% p3 Y7 |5 G' h8 N- 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)
# ~% B9 k. h, u# B& r& `- 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
& z! I) K4 c/ w, d) _8 K& A# }- TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
; ~6 g' e  f  Y- }1 n1 r# [# ^0 e" e. m- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
; ]8 U2 Y# ?. e6 f- Olive - https://github.com/microsoft/Olive
0 \+ u. K+ ?+ W8 o- (You)


3 {* u: k5 @- R3 ~8 |  f3 @! [3 ]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