Stable Diffusion UI v2.15

Advanced Settings

• Show a live preview of the image (consumes more VRAM, slightly slower image generation)
• Fix incorrect faces and eyes (uses GFPGAN)
• Upscale the image to 4x resolution using RealESRGAN_x4plus RealESRGAN_x4plus_anime_6B
• Show only the corrected/upscaled image


• Seed: Random Image
• Number of images to make: Generate in parallel: (images at once)
• Sampler: plms ddim heun euler euler_a dpm2 dpm2_a lms
• Width: 128 (*) 192 256 (*) 320 384 448 512 (*) 576 640 704 768 (*) 832 896 960 1024 (*) 1280 1536 1792 2048
• Height: 128 (*) 192 256 (*) 320 384 448 512 (*) 576 640 704 768 (*) 832 896 960 1024 (*) 1280 1536 1792 2048
• Number of inference steps:
• Guidance Scale:
• Prompt Strength:
  
•  
• Automatically save to
• Play sound on task completion
• Turbo mode (generates images faster, but uses an additional 1 GB of GPU memory)
• Use CPU instead of GPU (warning: this will be *very* slow)
• Use full precision (for GPU-only. warning: this will consume more VRAM)


• 🔥Beta channel. Get the latest features immediately (but could be less stable). Please restart the program after changing this.

Image Modifiers (art styles, tags etc)