Merge and run without saving to drive. Sequential XY merge generations; extract and merge loras, bind loras to ckpt, merge block weights, and more.
Updated
LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.
Updated
Applies LoRA strength; block by block on the fly. Includes presets, weight analysis, randomization, XY plot.
Updated
Adds model, LoRA and embedding previews to the UI including preview images, descriptions and LoRA prompt lists.
Updated
Segment Anything for Stable Diffusion WebUI. Automatically generate high-quality segmentations/masks for images by clicking or text prompting. Aim for connecting WebUI and ControlNet with Segment Anything and GroundingDINO to enhance Stable Diffusion/ControlNet inpainting (both single image and batch process), enhance ControlNet semantic segmentation, automate image matting and create LoRA/LyCORIS training set.
Updated
Dynamically control the weights of LoRAs during image generation
Updated
Enables using AND keyword(composable diffusion) to limit LoRAs to subprompts. Useful when paired with Latent Couple extension.
Updated
Allows the Web UI to use LoRAs (1.X and 2.X) to generate images. Also allows editing .safetensors networks prompt metadata.
Updated