Config path to config which constructs model default Value "[set_fullPath]v1-inference.yaml"

Ckpt path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded default Value "[set_fullPath]model.ckpt"

Ckpt Dir Path to directory with stable diffusion checkpoints

Gfpgan Dir GFPGAN directory default Value "./GFPGAN"

Gfpgan Model GFPGAN model file name

No Half do not switch the model to 16-bit floats default Value false

No Half Vae do not switch the VAE model to 16-bit floats default Value false

No Progressbar Hiding do not hide progressbar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser) default Value false

Max Batch Count maximum batch count value for the UI

Embeddings Dir embeddings directory for textual inversion (default: embeddings) default Value "[set_fullPath]embeddings"

Hypernetwork Dir hypernetwork directory default Value "[set_fullPath]models\hypernetworks"

Localizations Dir localizations directory default Value "[set_fullPath]localizations"

Allow Code allow custom script execution from webui default Value false

Medvram enable stable diffusion model optimizations for sacrificing a little speed for low VRM usage default Value false

Lowvram enable stable diffusion model optimizations for sacrificing a lot of speed for very low VRM usage default Value false

Lowram load stable diffusion checkpoint weights to VRAM instead of RAM default Value false

Always Batch Cond Uncond disables cond/uncond batching that is enabled to save memory with --medvram or --lowvram default Value false

Unload Gfpgan does not do anything. default Value false

Precision evaluate at this precision default Value "autocast"

Share use share=True for gradio and make the UI accessible through their site default Value false

Ngrok ngrok authtoken, alternative to gradio --share

Ngrok Region The region in which ngrok should start. default Value "us"

Enable Insecure Extension Access enable extensions tab regardless of other options default Value false

Codeformer Models Path Path to directory with codeformer model file(s). default Value "[set_fullPath]models\Codeformer"

Gfpgan Models Path Path to directory with GFPGAN model file(s). default Value "[set_fullPath]models\GFPGAN"

Esrgan Models Path Path to directory with ESRGAN model file(s). default Value "[set_fullPath]models\ESRGAN"

Bsrgan Models Path Path to directory with BSRGAN model file(s). default Value "[set_fullPath]models\BSRGAN"

Realesrgan Models Path Path to directory with RealESRGAN model file(s). default Value "[set_fullPath]models\RealESRGAN"

Clip Models Path Path to directory with CLIP model file(s).

Xformers enable xformers for cross attention layers default Value false

Force Enable Xformers enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work default Value false

Deepdanbooru does not do anything default Value false

Opt Split Attention force-enables Doggettx's cross-attention layer optimization. By default, it's on for torch cuda. default Value false

Opt Split Attention Invokeai force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable. default Value false

Opt Split Attention V1 enable older version of split attention optimization that does not consume all the VRAM it can find default Value false

Disable Opt Split Attention force-disables cross-attention layer optimization default Value false

Use Cpu use CPU as torch device for specified modules default Value []

Listen launch gradio with 0.0.0.0 as server name, allowing to respond to network requests default Value false

Port launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available

Show Negative Prompt does not do anything default Value false

Ui Config File filename to use for ui configuration default Value "[set_fullPath]ui-config.json"

Hide Ui Dir Config hide directory configuration from webui default Value false

Freeze Settings disable editing settings default Value false

Ui Settings File filename to use for ui settings default Value "[set_fullPath]config.json"

Gradio Debug launch gradio with --debug option default Value false

Gradio Auth set gradio authentication like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"

Gradio Img2Img Tool gradio image uploader tool: can be either editor for ctopping, or color-sketch for drawing default Value "editor"

Gradio Inpaint Tool gradio inpainting editor: can be either sketch to only blur/noise the input, or color-sketch to paint over it default Value "sketch"

Opt Channelslast change memory type for stable diffusion to channels last default Value false

Styles File filename to use for styles default Value "[set_fullPath]styles.csv"

Autolaunch open the webui URL in the system's default browser upon launch default Value false

Theme launches the UI with light or dark theme

Use Textbox Seed use textbox for seeds in UI (no up/down, but possible to input long seeds) default Value false

Disable Console Progressbars do not output progressbars to console default Value false

Enable Console Prompts print prompts to console when generating with txt2img and img2img default Value false

Vae Path Path to Variational Autoencoders model

Disable Safe Unpickle disable checking pytorch models for malicious code default Value false

Api use api=True to launch the API together with the webui (use --nowebui instead for only the API) default Value false

Api Auth Set authentication for API like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"

Nowebui use api=True to launch the API instead of the webui default Value false

Ui Debug Mode Don't load model to quickly launch UI default Value false

Device Id Select the default CUDA device to use (export CUDA_VISIBLE_DEVICES=0,1,etc might be needed before)

Administrator Administrator rights default Value false

Cors Allow Origins Allowed CORS origin(s) in the form of a comma-separated list (no spaces)

Cors Allow Origins Regex Allowed CORS origin(s) in the form of a single regular expression

Tls Keyfile Partially enables TLS, requires --tls-certfile to fully function

Tls Certfile Partially enables TLS, requires --tls-keyfile to fully function

Server Name Sets hostname of server

Dreambooth Models Path Path to directory to store Dreambooth model file(s).

Ckptfix (Dreambooth) Enable fix for OOM errors when extracting checkpoints. default Value false

Ldsr Models Path Path to directory with LDSR model file(s). default Value "[set_fullPath]models\LDSR"

Scunet Models Path Path to directory with ScuNET model file(s). default Value "[set_fullPath]models\ScuNET"

Swinir Models Path Path to directory with SwinIR model file(s). default Value "[set_fullPath]models\SwinIR"