stable-diffusion-webui/requirements.txt

GitPython
Pillow
accelerate
astunparse
basicsr
blendmodes
clean-fid
einops
gfpgan
gradio==3.32.0
inflection
jsonmerge
kornia
lark
numpy
omegaconf
opencv-contrib-python
piexif
psutil
pytorch_lightning==1.7.7
realesrgan
requests
resize-right
rich
safetensors
scikit-image>=0.19
timm==0.4.12
tomesd
torch
torchdiffeq
torchsde
transformers==4.25.1
Sort requirements files 2023-05-28 06:36:43 -06:00			`GitPython`
			`Pillow`
Optional Accelerate Launch 2022-11-09 10:15:17 -07:00			`accelerate`
Sort requirements files 2023-05-28 06:36:43 -06:00			`astunparse`
added detailed installation instructions fixed bug with missing same dir for a new install added ctrl+c hander to immediately stop the program instead of waiting 2022-08-31 02:04:19 -06:00			`basicsr`
Sort requirements files 2023-05-28 06:36:43 -06:00			`blendmodes`
			`clean-fid`
			`einops`
added detailed installation instructions fixed bug with missing same dir for a new install added ctrl+c hander to immediately stop the program instead of waiting 2022-08-31 02:04:19 -06:00			`gfpgan`
Upgrade Gradio, remove docs URL hack 2023-05-22 00:53:24 -06:00			`gradio==3.32.0`
Sort requirements files 2023-05-28 06:36:43 -06:00			`inflection`
			`jsonmerge`
			`kornia`
			`lark`
added detailed installation instructions fixed bug with missing same dir for a new install added ctrl+c hander to immediately stop the program instead of waiting 2022-08-31 02:04:19 -06:00			`numpy`
			`omegaconf`
update req.txt The old 'opencv-python' package is very limiting in terms of optical flow - so I propose a package change to 'opencv-contrib-python', which has more cv2.optflow methods. These are needed for optical flow trickery in auto1111 and its extensions, and it cannot be installed by an extension as only a single package of opencv needs to be installed for optical flow to work properly. Change of the main one is Inevitable. 2023-01-03 02:22:06 -07:00			`opencv-contrib-python`
removing duplicates removing duplicated requirements (transformers, diffusers) and reorganizing alphabetically to be able to spot duplicates in the future. 2022-09-24 21:37:27 -06:00			`piexif`
Sort requirements files 2023-05-28 06:36:43 -06:00			`psutil`
Update requirements.txt 2022-11-01 07:50:47 -06:00			`pytorch_lightning==1.7.7`
removing duplicates removing duplicated requirements (transformers, diffusers) and reorganizing alphabetically to be able to spot duplicates in the future. 2022-09-24 21:37:27 -06:00			`realesrgan`
Sort requirements files 2023-05-28 06:36:43 -06:00			`requests`
			`resize-right`
			`rich`
			`safetensors`
Update with definitely right requirements for skimage In my defense I was doing this on my phone. 2022-09-13 08:19:52 -06:00			`scikit-image>=0.19`
CLIP interrogator 2022-09-11 09:48:36 -06:00			`timm==0.4.12`
Sort requirements files 2023-05-28 06:36:43 -06:00			`tomesd`
removing duplicates removing duplicated requirements (transformers, diffusers) and reorganizing alphabetically to be able to spot duplicates in the future. 2022-09-24 21:37:27 -06:00			`torch`
clone k-diffusion instead of installing it via pip, and do not install its requirements.txt 2022-09-28 12:38:26 -06:00			`torchdiffeq`
Add support Stable Diffusion 2.0 2022-11-26 06:10:46 -07:00			`torchsde`
Sort requirements files 2023-05-28 06:36:43 -06:00			`transformers==4.25.1`