6 repositorios
Creating new images using another image as a structural or stylistic reference.
Distinct from Image Generation: Distinct from general generation by requiring an image as a primary prompt/reference.
Explore 6 awesome GitHub repositories matching artificial intelligence & ml · Image-Conditioned Generation. Refine with filters or upvote what's useful.
SD.Next is an all-in-one web interface and multi-backend inference engine for generating, editing, and processing images and videos using diffusion models. It functions as a comprehensive tool for diffusion model management and an automated image processing pipeline for bulk operations. The project is distinguished by its hardware-backend abstraction layer, which provides automatic detection and acceleration for NVIDIA CUDA, AMD ROCm, Intel OpenVINO, and DirectML. It features a headless generative API and a programmatic command interface, allowing users to trigger tasks via REST API or CLI wi
Generates or edits images using other images as starting points or visual references.
IP-Adapter is a framework for conditioning pretrained text-to-image diffusion models to use image prompts as visual guides. It serves as a text-to-image model extension that transforms a text-based diffusion model to accept and process image inputs as primary generation sources. The system implements identity preservation to maintain consistent facial features across multiple outputs using a reference photo. It also enables style transfer workflows to produce image variations that preserve the artistic characteristics of a source image. Capabilities cover multi-modal prompting, including the
Creates new visual content using an existing image as the primary structural or stylistic reference.
OOTDiffusion is an AI virtual try-on system designed for controllable image synthesis. It generates images of people wearing specific clothing items by superimposing garments onto human figures for both half-body and full-body compositions. The project facilitates digital fashion prototyping and virtual clothing fitting by creating garment-to-person overlays. It aims to maintain the original identity of the wearer and the specific details of the clothing during the synthesis process. The system utilizes a latent diffusion model and conditioning-based image generation to control the output. I
Implements generation guided by garment images and human poses as structural and stylistic references.
ComfyUIIPAdapterplus es una extensión basada en nodos para ComfyUI que implementa modelos IPAdapter para guiar la generación de imágenes utilizando imágenes de referencia. Funciona como una herramienta de prompting de imágenes y un adaptador de imágenes de Stable Diffusion, permitiendo que los archivos de referencia sirvan como prompts visuales para controlar el estilo, la composición y la identidad del sujeto. El proyecto proporciona capacidades especializadas para mantener la identidad facial y características de alta fidelidad en retratos generados. Permite la transferencia de características visuales y estilos artísticos desde imágenes de referencia, así como la extracción de diseños espaciales para guiar la disposición de objetos en nuevas generaciones. La extensión cubre áreas funcionales amplias, incluyendo condicionamiento de imágenes por IA, generación consistente de personajes y control de composición de imágenes.
Enables the generation of new images using reference files as structural or stylistic baselines.
SUPIR es un sistema de IA para el escalado y restauración de imágenes diseñado para eliminar artefactos y restaurar la calidad de fotografías del mundo real. Funciona como una herramienta de mejora y restauración de imágenes basada en difusión que utiliza escalado de modelos a gran escala para producir resultados de alta resolución con detalles fotorrealistas. El sistema equilibra la estética visual con la fidelidad de la entrada, permitiendo un compromiso entre la estricta adherencia a la imagen original y el atractivo visual general del resultado. Aprovecha la inferencia de modelos a gran escala para mejorar la claridad de la imagen y mantener detalles realistas durante el proceso de escalado.
Uses the original low-resolution image as a structural reference to guide the generation of high-resolution output.
Nunchaku is a 4-bit model quantization library and diffusion model inference engine designed to run large-scale neural networks on consumer GPUs. It functions as a GPU-accelerated optimizer that reduces VRAM usage and increases inference speed through weight compression and memory management. The project utilizes low-rank weight decomposition and SVD weight quantization to compress models to four-bit precision while maintaining visual fidelity. It employs kernel-level operator fusion to minimize data movement and hardware-aware precision mapping to adjust numerical precision based on the unde
Supports image-to-image generation by using existing images as structural or stylistic references alongside text prompts.