Tag
RefineEdit is a training-free prompt-to-prompt image editing method that uses a generative refinement network to enhance edit localization and background preservation, achieving top benchmark scores.
Tangerine is an offline Mac application for converting and editing files using gestures, supporting images, videos, audio, PDFs, and archives without uploading files.
Marigold V2 transforms an image-editing Diffusion Transformer into a single-step model for sharp dense prediction, achieving best zero-shot results in depth estimation and related tasks with Apache 2.0 license.
Qwen-Image-2.1 is an open-source unified text-to-image and image editing model with 7B parameters, featuring efficient architecture, transparency support, and versatile editing capabilities.
A tweet from @calicastle praises the perfection of GPT image 2.5 sunburst for creating app store screenshots.
This paper introduces a framework using common-witness certificates and sharp feature bounds to audit counterfactual images, addressing the global-witness gap in structured image editors through theoretical and experimental validation.
The Artificial Analysis Image Editing Arena has been updated to expand editing tasks and use cases, providing a comprehensive leaderboard that ranks AI models on human preference for various image editing scenarios.
Paint.net version 5.2 alpha now supports Linux, expanding its availability beyond Windows.
Google has launched Google Pics, an AI-powered image creation and editing tool integrated into Google Workspace, offering features like object segmentation and in-image text editing for subscribers and business customers.
Adobe is introducing a new AI-heavy update for Photoshop in beta, including an AI Assisted Editor view and enhancements to its Firefly Image 5 model for more intuitive image editing.
A lab has open-sourced SenseNova U1.5-Lite, an 8B parameter model for image AI that allows making specific changes to images without destroying other elements, as demonstrated on infographics and posters.
Aphanta is an automated diagnostic framework that evaluates the utility of image-edited intermediates in multimodal reasoning pipelines, showing task-dependent benefits and improving performance on specific tasks.
This introduces an open-source image editing skill called xxg-portrait-rebuild-light, which relights existing portrait photos using professional lighting techniques to avoid common AI retouching flaws while retaining authentic details.
Google has released a free AI-powered image editor that allows users to edit photos using simple text commands, making complex photo editing accessible without Photoshop skills.
DARS is a reinforcement learning framework for dual-level credit assignment in instruction-based image editing, improving performance by routing updates between planner and renderer modules through structured reasoning and adaptive curriculum.
This is a comprehensive AI image generation tutorial covering everything from basic principles to practical applications, including prompt structure, style control, and composition techniques.
Wuli-Art introduces Gemma-4-for-Qwen-Image-Edit-2511-Prompt-Extend, a prompt optimizer that enhances image editing prompts for improved precision and clarity.
EditBridge is a diffusion bridge framework that enables efficient ultra-high-resolution image editing up to 4K by translating low-resolution edits to high-resolution outputs with sparse attention, achieving significant speed improvements and preserving source details.
GIMP announces a development update for August 2026, previewing new features for GIMP 3.4 such as a new project file format, spectral blending in MyPaint brushes, and non-destructive editing.
This paper introduces a hierarchical taxonomy and dense supervision training strategy for diffusion-based image editing, leveraging a large dataset of 12 million editing pairs and a granular evaluation benchmark to enhance model performance.