![]() : 1 prompt with 1 iteration each = 1 images total. ![]() : Preparing to run Optimized Stable Diffusion - 1 Iterations, 30 Steps, Scale 8, 512x512, Starting Seed: 10 Only keep this option enabled if your GPU has less than 8 GB of memory. I'm using Windows 10 with Nvidia RTX 2080. ![]() But I'd like to try this GUI, since it has upscaling and IMG2IMG. Any idea why? I've used Stable Diffusion with GRisk GUI without issue. I keep getting "No images generated." I've tried switching most all the settings, but still no luck. Fixed full-precision option not actually enabling full-precision.Error messages are now shown for common errors.Improved installer, python files are now included and should no longer conflict with system conda.Slightly reduced VRAM usage across both implementations (fast/optimized).Added warnings if the program is running from a long or problematic (e.g.Added option to change image output folder.Added option to use the same seed for each prompt when running multiple prompts.User can now run multiple prompts at once (one prompt per line, not counting word wrap).Added option to disable prompt in filename.Added option to save images to a subfolder per prompt.Added fullscreen image preview (click on image to open), click into it for 2x2/3x3 tiling (if seamless mode is enabled).Added option to generate seamless (tileable) images.Added optional AI post-processing: RealESRGAN upscaling and GFPGAN face restoration.Added option to use low-VRAM code, only needs around 3.3 GB VRAM for 512x512 images.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |