GitHub

SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions

We present two models, SDXS-512 and SDXS-1024, achieving inference speeds of approximately 100 FPS (30x faster than SD v1.5) and 30 FPS (60x faster than SDXL) on a single GPU. Assuming the image ...
IEEE

TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting

Abstract: This paper introduces TurboFill, a fast image inpainting model that enhances a few-step text-to-image diffusion model with an inpainting adapter for high-quality and efficient inpainting.
IEEE

Two-Step Single-Slope ADC with Three-Stage Bandwidth-Limited Comparator for CMOS Image Sensors

Abstract: This paper proposes a low-power column parallel two-step single-slope Analog-to-Digital Converter (SS ADC) with three-stage Bandwidth-Limited preamplifier ...

A Story of Hip-Hop Rehabilitation With the Body as Battleground

Dahlak Brathwaite’s “Try/Step/Trip,” part of the Under the Radar festival, uses the language of step to express the liberating and restricting power of groups.
GitHub

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

This is the official repository of paper Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching. We propose Distilled Decoding (DD) to distill a pre-trained image ...
TechCrunch

OpenAI continues on its ‘code red’ warpath with new image generation model

OpenAI is rolling out a new version of ChatGPT Images that promises better instruction-following, more precise editing, and up to 4x faster image generation speeds. The new model, dubbed GPT Image 1.5 ...