generating images from the command line and web UI
recording.mp4
pip install sd-toolssdxl 'locomotive'If the model can't be downloaded, try using a huggingface mirror:
export HF_MIRROR=https://hf-mirror.comTo get better result, use more steps and higher resolutions:
sdxl 'locomotive' --size 720 --steps 4Generate more with --count:
sdxl 'locomotive' --size 1024x576 --steps 4 --count 3By default, images are save to output/{seed}-{time}.webp, which can be customized via -o:
sdxl 'locomotive' -o 'output/{seed}-{size}-{cfg}-{time}.webp'The loading of the model can task some time, use -i to enter interactive mode, keeping the model loaded:
sdxl 'locomotive' --size 1024x576 --steps 4 -iEdited prompt and press enter:
> locomotive
size, count, steps and cfg can also be set on the fly:
> locomotive size=1024 cfg=1.9
sdxl 'A green frog' \
--model 'Lykon/dreamshaper-xl-lightning' \
--scheduler 'DPM++ SDE Karras' \
--listen 8888To use a specific model:
sdxl 'locomotive' \
--model Lykon/dreamshaper-xl-lightning \
--steps 6 \
--size 1024x576 \
--scheduler 'DPM++ SDE Karras' \
--cfg 2 \More models can be found on huggingface and civitai, models with Lightning or Turbo can generate image in less than 8 steps.
For models without fp16 variant or safetensor format, add --no-fp16 or --no-safetensor
sdxl 'locomotive' \
--model RunDiffusion/Juggernaut-XL-Lightning \
--cfg 1.5 \
--steps 6 \
--size 832x1216 \
--scheduler 'DPM++ SDE' \
--no-fp16 --no-safetensorTo use models downloaded from civitai:
sdxl 'locomotive' --model ./model.safetensorsLoras are like plugins for the base model, multiple loras can be used:
sdxl 'locomotive' \
--model SG161222/RealVisXL_V4.0_Lightning \
--steps 8 \
--size 1024x576 \
--loras ./lora1.safetensors ./lora2.safetensors:0.8 \Using --lcm, --tcd, --hyper or --lightning to speed up generation, not necessary for turbo/lightning models:
sdxl 'locomotive' \
--model SG161222/RealVisXL_V4.0 \
--steps 4 \
--size 1024x576 \
--tcd 1 \sdxl 'protrait of a man' --canny photo.jpg --canny-low 100 --canny-high 200sdxl 'protrait of a man' --depth photo.jpgsdxl 'protrait of a man' --pose photo.jpgsdxl 'helmet' \
--inpaint test/tesla.webp \
--inpaint-mask mask.png \
--steps 40 \
-i \
-o output/preview.pngOpen mask.png, paint the area to be modified, close image editor, then press Enter to start inpainting.
pip install 'sd-tools[photomaker]'use img to indicate the reference target
sdxl 'man img holding a toy car' \
--model Lykon/dreamshaper-xl-lightning \
--steps 6 \
--cfg 2 \
--photo-maker test/tesla.webp \
--scheduler 'DPM++ SDE Karras'multiple reference images can be provided:
--photo-maker 1.png 2.png
style reference, multiple images can be used:
sdxl 'portrait of a man' \
--model Lykon/dreamshaper-xl-lightning \
--scheduler 'DPM++ SDE Karras' \
--steps 8 --size 1024x576 \
--ipa-plus test/ghibli \
--ipa-plus-scale 0.7 \
--seed 0face reference, multiple images can be used:
sdxl 'portrait of a man' \
--model Lykon/dreamshaper-xl-lightning \
--scheduler 'DPM++ SDE Karras' \
--steps 8 --size 1024x576 \
--ipa-plus-face test/tesla-s.webp \
--ipa-plus-scale 0.4 \
--seed 0combined
sdxl 'portrait of a man' \
--model Lykon/dreamshaper-xl-lightning \
--scheduler 'DPM++ SDE Karras' \
--steps 8 --size 1024x576 \
--ipa-plus test/ghibli \
--ipa-plus-face test/tesla-s.webp \
--ipa-plus-scale 0.7 0.4 \
--cfg 2 \
--seed 0pip install 'sd-tools[faceid]'sdxl 'man walking on the moon' \
--model Lykon/dreamshaper-xl-lightning \
--scheduler 'DPM++ SDE Karras' \
--steps 6 \
--cfg 2 \
--ipa-faceid-plus test/tesla.webppip install 'sd-tools[faceid]'sdxl 'man walking on the moon' \
--model Lykon/dreamshaper-xl-lightning \
--scheduler 'DPM++ SDE Karras' \
--steps 6 \
--cfg 2 \
--instantid test/tesla.webpsdxl 'Arnold Schwarzenegger' \
--model Lykon/dreamshaper-xl-lightning \
--scheduler 'DPM++ SDE Karras' \
--steps 6 \
--cfg 1.2 \
--ip-composition test/tesla.webpsdxl 'man walking on the moon' --listen 127.0.0.1:8800Invoking using curl:
curl '127.0.0.1:8800?prompt=shell&seed=1' > image.webpsdxl 'locomotive' --size 512 -i -o output/preview.pngOpen output folder in Finder, switch to gallery mode, once generated, image preview will be updated.
You can even set a count to generate more images:
> locomotive count=3To keep the generated images, pass an additional ouput path:
sdxl 'locomotive' --size 512 -i -o output/preview.png 'output/{seed}.webp'sdxl 'portrait of a woman img, chinese paint style' \
--model SG161222/RealVisXL_V4.0_Lightning \
--steps 6 --size 768x1024 \
--scheduler 'DPM++ SDE Karras' \
--cfg 2sdxl 'locomotive comming' \
--model Lykon/dreamshaper-xl-lightning \
--steps 6 --size 1024x576 \
--scheduler 'DPM++ SDE Karras' \
--cfg 2sdxl 'portrait of a woman, chinese painting style, Full Body Shot' \
--model RunDiffusion/Juggernaut-XL-Lightning \
--cfg 1.9 \
--steps 6 \
--size 832x1216 \
--scheduler 'DPM++ SDE' \
--no-fp16 --no-safetensorsd -hsd 'portrait of man, masterpiece' \
--model Lykon/dreamshaper-8 \
--steps 8 \
--lcm 1 \
--ipa-portrait photo1.png photo2.png \
-isd 'man walking down the street' \
--model Lykon/dreamshaper-8 \
--steps 10 \
--size 760 \
--ipa-plus-scale 0.8 \
--ipa-plus-face test/tesla-s.webp \
--lcm 1sd 'man in nature' \
--model Lykon/dreamshaper-8 \
--steps 10 \
--size 760 \
--ipa-plus-scale 0.8 \
--ipa-plus test/ghibli \
--lcm 1sd 'Arnold Schwarzenegger' \
--model Lykon/dreamshaper-8 \
--steps 10 \
--lcm 1 \
--seed 4 \
--ip-composition test/tesla.webpsd 'ethereal fantasy concept art of cat, magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy' \
--sketch sketch.png -i -o output/preview.webpSDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions
sd --model zweifisch/sdxs-512-0.9-fp16 'chihuahua' --steps 1 --count 10sd --model 'SG161222/Realistic_Vision_V6.0_B1_noVAE' 'chihuahua' --steps 2 --no-fp16 --no-safetensor --yoso 1 --count 10 --cfg 1
