Tag
Stable Diffusion XL (SDXL) can now run locally in the browser using WebGPU, enabling high-quality AI image generation directly on-device with open-source code.
Cyclic denoising is introduced as a novel extraction attack that reveals ultrastable memorized training images in diffusion models by repeatedly noising and denoising samples. The technique requires no gradients or weight inspection and has implications for privacy auditing.
Benchmark shows local Stable Diffusion 1.5 on iPhone can generate 512x512 images in as little as 3.1 seconds using optimized models like Realistic Vision V5.1 Hyper, making on-device AI image generation practical.
This paper introduces a post-training framework that leverages 3D priors from SAM3D to improve semantic correspondence in 2D foundation features, addressing issues like left-right confusion and repeated parts. The method uses instance-specific 3D reconstruction without pose annotations or spherical geometry shortcuts.
Visual Concept Fusion (VCF) enables dual conditioning on both an image and text prompt in diffusion models at inference time without retraining, using a lightweight aligner and fusion strategy.
Launching PhoneDiffusion, a local AI image generator for iPhone with sub-5 second generations, privacy, and no account needed.
This paper proposes a framework for conditional generative compressed sensing, proving stable recovery bounds for prompt-conditioned models and demonstrating how prompt matching influences sampling distributions in experiments with Stable Diffusion.
Flow-OPD is a research paper introducing a two-stage on-policy distillation framework for Flow Matching text-to-image models, significantly improving generation quality and alignment metrics using Stable Diffusion 3.5 Medium.
This open-source project provides a feature-rich web interface for Stable Diffusion, enabling users to easily generate, edit, and upscale images using various AI models and extensions. Built with Gradio, it supports txt2img, img2img, inpainting, and numerous community-driven tools for local AI image generation.