![]() ![]() Make sure the required dependencies are met and follow the instructions available for: Reorder elements in the UI from settings screen.Eased resolution restriction: generated image's dimension must be a multiple of 8 rather than 64. ![]() Alt-Diffusion support - see wiki for instructions.Stable Diffusion 2.0 support - see wiki for instructions.via extension: Aesthetic Gradients, a way to generate images with a specific aesthetic by using clip images embeds (implementation of ).Support for dedicated inpainting model by RunwayML.Estimated completion time in progress bar.Can select to load a different VAE from settings screen.A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt.Loras (same as Hypernetworks but more pretty).Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime). ![]() via extension: History tab: view, direct and delete images conveniently within the UI.xformers, major speed increase for select cards: (add -xformers to commandline args).DeepDanbooru integration, creates danbooru style tags for anime prompts.No token limit for prompts (original stable diffusion lets you use up to 75 tokens).also supports weights for prompts: a cat :1.2 AND a dog AND a penguin :2.2.Composable-Diffusion, a way to use multiple prompts at once.Custom scripts with many extensions from community.Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one.Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions.Img2img Alternative, reverse Euler method of cross attention control.Batch Processing, process a group of files using img2img.Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway.CLIP interrogator, a button that tries to guess prompt from an image.Seed resizing, a way to generate same image but at slightly different resolution.Variations, a way to generate same image but with tiny differences.Styles, a way to save part of prompt and easily apply them via dropdown later.Negative prompt, an extra text field that allows you to list what you don't want to see in generated image.Can use a separate neural network to produce previews with almost none VRAM or compute requirement. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |