Stories by Hard_Space

Multitask Video Synthesis Without Fine-Tuning

A Unified System for Facial Analysis

The Continuing Struggle to Create Significant Motion in Text-to-Video Output

Better Stable Diffusion Deepfakes with an Object-Oriented Programming Approach

Will GPT-4 Run Doom?

Getting Real Transparency into Stable Diffusion

Face-Swapping Directly in the Latent Space

Plausible Stable Diffusion Video from a Single Image

Better Neural Avatars from Just Five Face Images

The Challenge of Preventing 'Identity Bleed' in Face Swaps

Combating Stable Diffusion Face Forgery Through Frequency Analysis

Multiple Cropping of Images May Improve AI Model Performance

A Text-to-Video Method That Generates Some Action

Reshaping the Human Body with CGI and Stable Diffusion

An Old Algorithm May Be Holding Back New Generative AI Systems

What's the Difference Between CGI and AI?

Solving the 'Profile View' Crisis in Facial Image Synthesis

Using Traditional CGI to Re-Sculpt Generative AI

The Emergence of Full-Body Gaussian Splat Deepfake Humans

Colorization Is an Obstacle to Recreating Actors of the Past

1
2
3
4
5
6
7
8
9
10