Stable Diffusion and other AI Art Notes

https://github.com/Haoming02/sd-webui-mosaic-outpaint for outpainting

Lots of stable diffusion model checkpoints have recommended settings. Here are some of them.

• Default SD 1.5: Use the “DPM++ SDE Karras” or “DPM++ 2M Karras” sampler with only 20 steps for better quality. “DPM++ SDE Karras” has better quality but is slow.
• Default SD 1.5: Use the CFG scale between 5 and 9. CFG scale at 5 is recommended. Stable Diffusion default value is 7. For the cartoon model, CFG in 8-9 has had better results.
• SD 1.5 LCM: Use the “Euler a” or “LCM” sampler with only 8 steps for better quality.
• SD 1.5 LCM: Use the CFG scale between 1 and 2. CFG scale at 2 is recommended.
• LCM with DPM++ SDE Karras: Sampling steps 8, Hires. Fix enabled, upscaler nearest, Hires steps 2, hires. denoise 0.45, upscale by 1.05, cfg scale 1.5.
• LCM with DPM++ 2M Karras: Sampling steps 8, Hires. Fix enabled, upscaler nearest, Hires steps 2, hires. denoise 0.55, upscale by 1.05, cfg scale 1.5.
• Resolution between 512 and 768 using “Hires. Fix” or other form of upscaling.
• If you use “Hires. Fix”, use “Upscale by” with the value 1.5 with denoising at 0.6.
• Tips for a better prompt:
  • Use (word) for larger weight and [word] for smaller weight and word:0.5 to set the weight manually.
• Recomendations for improvement on performance:
  • Use Token Merging Ratio 0.5 on optimization settings.
  • If you have a GPU with low VRAM, use –medvram on command line arguments (webui-user.bat on Windows).
• Recommended negative prompts to improve human images: amputee, deformed body, long neck, extra fingers, bad body proportions, mutated hands, mutilated, mutation, ugly, fused fingers, malformed limbs, extra heads, disfigured,

Recommended settings: DPM++ 3M SDE Karras or DPM++ 2M Karras, 20-30 steps, 2.5-5 CFG (or use Dynamic Thresholding), happiest at 640×960 with a hires fix on top, but if you are happy to hunt through seeds to avoid head duplicates, 768×1152 works quite well also.

Made a folder called ai. All models and interfaces will live here.

git clone https://github.com/lllyasviel/Omost omost
cd omost
~/.pyenv/versions/3.10.6/bin/python3 -m venv venv
source venv/bin/activate
pip install --upgrade pip
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu121
pip install -r requirements.txt
 
# Run
python gradio_app.py

git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui automatic
~/.pyenv/versions/3.10.6/bin/python3 -m venv venv
source venv/bin/activate
pip install --upgrade pip
 
# Run
./webui.sh --xformers
 
# Extensions
cd extensions
git clone https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 && git clone https://github.com/Mikubill/sd-webui-controlnet && git clone https://github.com/adieyal/sd-dynamic-prompts && git clone https://github.com/Bing-su/adetailer
 
# Model linking
ln -sr ../models/stable-diffusion models/Stable-diffusion/shared
ln -sr ../models/controlnet extensions/sd-webui-controlnet/models/shared

cd ~/ai
 
git clone https://github.com/comfyanonymous/ComfyUI comfyui
cd comfy
~/.pyenv/versions/3.10.6/bin/python3 -m venv venv
source venv/bin/activate
pip install --upgrade pip
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu124
pip install -r requirements.txt 
 
# Models
ln -sr ../models/stable-diffusion models/checkpoints/shared