Search Results for "stable diffusion 1.5"

...Inpaint to fix up images and convert existing textures into seamless ones automatically. Outpaint to increase the size of an image by extending it in any direction. Perform style transfer and create novel animations with Stable Diffusion as a post processing step. Dream Textures has been tested with CUDA and Apple Silicon GPUs. Over 4GB of VRAM is recommended.

This project is an extension for the Stable Diffusion Web UI that removes backgrounds from images directly inside the interface. It wraps popular background-removal models so creators can take a generated or uploaded image and isolate the subject with a single click. The workflow is designed to be non-destructive: you can preview, tweak thresholds, and export either a transparent PNG or a masked layer for further editing.

...PersonaLive’s architecture balances visual quality and efficiency by combining motion encoding, temporal modules, and hybrid implicit control signals to preserve identity and stable expression through long sequences.

IOPaint is a powerful open-source image editing tool focused on inpainting, outpainting, object removal, and general image manipulation driven by state-of-the-art AI models, delivering these capabilities through both local and hosted workflows. Designed to be fully self-hosted and flexible, IOPaint supports a variety of underlying generators and inpaint models — from LaMa erase networks to Stable Diffusion-based replace/object generation — giving users multiple ways to refine or reconstruct images by removing unwanted elements or expanding artwork beyond its original boundaries. Its feature set includes erasing people, watermarks, or defects, adding or replacing objects, applying text-aware edits, and extending images outward (outpainting) to fill contours or expand compositions.

AnimateDiff is an open-source project designed to enhance text-to-image diffusion models by adding animation capabilities. It allows users to turn static images generated by popular text-to-image models into animated sequences without requiring additional model training. This plug-and-play tool is compatible with a wide range of community models and facilitates the generation of animation directly from pre-existing text-to-image models. It supports various configurations to create animations...

A powerful tool for reading, extracting, and removing AI generation metadata from image files. Specifically designed to handle metadata from AI image generation tools like ComfyUI, Stable Diffusion, SwarmUI, InvokeAI, and more. Core Functionality Read EXIF/Metadata: Extract and display comprehensive metadata from images AI Metadata Detection: Automatically identify and highlight AI generation metadata Metadata Removal: Strip AI generation metadata while preserving image quality Batch Processing: Handle multiple files with wildcard patterns Cross-Platform: Works on Windows, macOS, and Linux AI Tool Support ComfyUI: Detects and extracts workflow JSON data Stable Diffusion: Identifies prompts, parameters, and generation settings SwarmUI/StableSwarmUI: Handles JSON-formatted metadata Midjourney, DALL-E, NovelAI: Recognizes generation signatures Automatic1111, InvokeAI: Extracts generation parameters

Lightweight Stable Diffusion v 2.1 web UI: txt2img, img2img, depth2img, in paint and upscale4x. Gradio app for Stable Diffusion 2 by Stability AI. It uses Hugging Face Diffusers implementation. Currently supported pipelines are text-to-image, image-to-image, inpainting, upscaling and depth-to-image.

Atari FontMaker is a tool for creating Atari fonts both in mono and color graphics mode. Atari FontMaker is written in Delphi up to version 1.5.x, since version 1.6.x the project has been converted to C# and moved to another repository: https://github.com/matosimi/atari-fontmaker

Snoise is a command line tool for scaling and denoising images. Usage: snoise -i <input image> -o <output image> -s <scale amount> -d <denoise amount> -t Usage example: snoise -i in.jpg -o out.png -s 1.5 -d 10 Type "snoise -h" to display the help message.

Matplotlib is a python library for making publication quality plots using a syntax familiar to MATLAB users. Matplotlib uses numpy for numerics. Output formats include PDF, Postscript, SVG, and PNG, as well as screen display. As of matplotlib version 1.5, we are no longer making file releases available on SourceForge. Please visit http://matplotlib.org/users/installing.html for help obtaining matplotlib.

Purple Koala is a free and open source cross-platform simple drawing and painting software. Part of Purple Animation Tools by O. Bahri Gordebak (purplehuman). See Wiki for details. Note that Sourceforge project page doesn't always show the latest download. Please click Files above and browse files before download. Latest version is 1.5 right now.

FCOLLADA based COLLADA plugins for Maya and 3DSMax. Newer plugins with 1.5 support and support the files mentioned in "Papervision3D Essentials" by Paul Tondeur are available at http://opencollada.org . Please use this project for FCOLLADA related topi

Ekspos is a cross platform Image Viewer program and licensed under revised BSD License. It support plugin for additional image type. Make sure you have J2SE or Java VM (JRE) 1.5 or higher

Platform independend, multithreaded fractal generator. Fine control over thread/CPU usage; unlimited precision; smooth/random/function coloring; supports color map files (over 1600 available); many image file formats. For any Java 1.5+ (32/64 Bit) VM.