Stories by Hard_Space

Stable Diffusion and Imagen Can Reproduce Training Data Almost Perfectly

ComfyUI – A powerful and modular Stable Diffusion GUI

Image Synthesis Has an SEO Problem

Diffusion Models Already Have a Semantic Latent Space

Discovering the Traces of Disinformation on Instagram in the Internet Archive

Creating Better Avatars with a Dual-Domain Approach

The 'Cheap' Decisions That Can Affect Image Synthesis

NoAI Watermark Generator

Temporally Coherent Human Video Deepfakes via Diffusion

Google’s New Text-to-Image Model Abandons Latent Diffusion for Transformers

High-Quality Deepfake Puppetry in Thirty Seconds

Using Diffusion Models to Create Superior NeRF Avatars

Investigating Data Replication in Diffusion Models

Research Proposes 'Moral' Sanitization for Text-to-Image Systems

Creating State-of-the-Art NeRF Head Avatars in Minutes

InstructPix2Pix: AI-Based Image-Editing with GPT-3 and Stable Diffusion

Editing Out the Real World with 'Diminished Reality'

A New Social Image-Sharing System Deepfakes All People by Default

The Future of Using Public Images for AI Research

Class-action complaint against GitHub Co-Pilot, among others [pdf]

1
2
3
4
5
6
7
8
9
10