Nunchaku v0.1.4 Unleashed SVDQuant To 3x Speed Up 12B FLUX On RTX 4090

The world of AI image generation is rapidly evolving, with diffusion models leading the charge. However, the computational demands of these powerful models can be a significant bottleneck. That’s where Nunchaku v0.1.4 comes in, offering a groundbreaking solution for accelerating diffusion model inference. This release introduces SVDQuant, a novel quantization technique that drastically reduces memory usage and […]
Say Hello to Goku: The Future of AI Video is Here From ByteDance

In the fast-evolving world of AI, creating realistic videos has always been a grand challenge. But what if we told you that a new model has emerged, setting unprecedented benchmarks in video generation quality? Enter Goku, a cutting-edge video generation model that’s changing the game. Developed as a state-of-the-art family of models, Goku is not just […]
Google DeepMind Goes Big in Video with Release of Veo, Setting Their Sights on Surpassing OpenAI’s Sora

Just today, in the Google I/O announcements, Google released a new model called Veo, a new text-to-video AI model. Veo creates videos at 1080p and is very realistic and able to create videos in a variety of styles. With Veo, Google DeepMind takes aim at surpassing OpenAI’s widely acclaimed Sora which currently leads in quality, […]
Omni-Zero Puts Power To Create Fine Art Portraits In Everyone’s Hands

With advances in AI, new possibilities are emerging for customized digital portrait generation. Omni-Zero is an innovative open-source pipeline that takes this technology to the next level by allowing the generation of realistic portraits of people in different art styles without any training data. So, let’s get into the details! What is Omni-Zero? Omni-Zero is […]
Forget Photoshop, Add Next-Level Relighting to Your Images for Free With IC-Light

Have you ever wanted to relight images with just a click? Now, you can with IC-Light, an open-source tool that lets you impose new lighting conditions on portraits and other images. In this article, we will explore the incredible capabilities of IC-Light and how you can use it in relighting your images. What is IC-Light? […]
Layered Diffusion Brushes: A Photoshop-Level Image Editor to Achieve Real-Time Results

Image editing is evolving at a rapid pace with advancements in AI and machine learning technologies. Diffusion models have emerged as powerful tools for various image generation and manipulation tasks. However, controlling and fine-tuning images remains a challenge with existing techniques. Researchers from the University of British Columbia introduced a new technique, Layered Diffusion Brushes, […]
InstantFamily: An AI Tool That Makes Multi-ID Image Creation a Reality

Personalized image generation aims to generate photorealistic images based on user-defined attributes and conditions. Over the years, models have significantly improved at preserving concepts from text prompts. However, creating images with multiple individuals while accurately representing each identity still poses unique challenges. A new model called InstantFamily is looking to change that by enabling zero-shot […]
DeepFaceLive Lets You Swap Faces in Real-Time During Video Calls or Live Streaming

Are you tired of looking at the same face during your video calls or PC streaming sessions? Do you wish you could swap faces in real-time and have some fun with your friends? Look no further! DeepFaceLive is here to fulfill your face-swapping desires. In this article, we will explore the features and capabilities of […]
NVIDIA Introduces “Align Your Steps” to Boost Output Quality of Diffusion Models

Generative AI models like diffusion models have achieved impressive results in generating images, videos, and other media. However, one limitation is that generating high-quality outputs requires many sequential steps through large neural networks, making the process slow. NVIDIA researchers have now introduced a new technique called Align Your Steps (AYS), which can help diffusion models […]
Adobe Introduces VideoGigaGAN: An AI Model Capable of 8x Video Upsampling With High-Quality Results

Video upscaling is a complex task that aims to recover high-resolution videos from low-resolution inputs while maintaining temporal consistency across frames. Previous models struggled to generate realistic textures and fine details. Adobe researchers have recently introduced VideoGigaGAN, a new generative model that significantly advances state-of-the-art video upscaling quality and consistency. It is known for 8x […]