With WEBSITE NOW

added a webui along with better faces, upscaling all on the cpu if i did this right

.gitignore

@@ -24,3 +24,5 @@ src/taming-transformers/
 *.ckpt
 *.png
 condaenv.fintae5p.requirements.txt
+GFPGAN/
+*.pth

README.md

@@ -43,6 +43,43 @@ conda install pytorch torchvision torchaudio cpuonly -c pytorch
 conda env create -f environment-cpuonly.yaml
 conda activate ldm
 ```
+Go here and download the correct mode from here. YOu'll have to agree to the license setup an account, I believe.
+This the bread and butter AI art generating learning model.
+...
+https://huggingface.co/CompVis/stable-diffusion-v-1-4-original
+...
+
+copy it to your stable-diffusion-cpuonly/models/ldm/stable-diffusion-v1 directory and rename it to model.ckpt
+
+Download the model - this is for better face generation or cleanup
+...
+https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth 
+...
+and copy it to your stable-diffusion-cpuonly/src/GFPGAN/experiments/pretrained_models directory
+
+Download the model - this is for upscaling your images
+...
+https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth
+...
+...
+https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth
+...
+and copy these to your stable-diffusion-cpuonly/src/realsrgan/experiments/pretrained_models directory
+
+
+Run the following command
+
+python .\webui.py --no-half
+
+
+...
+python inference_gfpgan.py -i inputs/whole_imgs -o results -v 1.3 -s 2
+...
+
+
+
+
+
 
 old readme info
 //You can also update an existing [latent diffusion](https://github.com/CompVis/latent-diffusion) environment by running

environment-cpuonly.yaml

@@ -7,9 +7,18 @@ dependencies:
   - pip=20.3
   - numpy=1.19.2
   - pip:
+    - basicsr
+    - facexlib
+    - lmdb
+    - pyyaml
+    - scipy
+    - tb-nightly
+    - tqdm
+    - yapf
     - albumentations==0.4.3
     - diffusers
     - opencv-python==4.1.2.30
+    - opencv-python-headless
     - pudb==2019.2
     - invisible-watermark
     - imageio==2.9.0
@@ -23,6 +32,13 @@ dependencies:
     - transformers==4.19.2
     - torchmetrics==0.6.0
     - kornia==0.6
+    - pynvml
+    - gradio
+    - keras-unet
+    - fairseq
     - -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
     - -e git+https://github.com/openai/CLIP.git@main#egg=clip
+    - -e git+https://github.com/TencentARC/GFPGAN#egg=GFPGAN
+    - -e git+https://github.com/xinntao/Real-ESRGAN#egg=realesrgan
+    - -e git+https://github.com/hlky/k-diffusion-sd#egg=k_diffusion
     - -e .

logs/txt2img_logs.csv

@@ -0,0 +1,2 @@
+prompt,outdir,skip_grid,skip_save,ddim_steps,fixed_code,ddim_eta,n_iter,H,W,C,f,n_samples,n_rows,scale,device,from_file,seed,unet_bs,turbo,precision,format
+a painting of a virus monster playing guitar,outputs/txt2img-samples,False,False,50,False,0.0,1,512,512,4,8,5,0,7.5,cuda,,99270,1,False,autocast,png