Recent Articles

Advertisement

InstantID maintains high facial fidelity while maintaining compatibility with other models.

InstantID maintains high facial fidelity while maintaining compatibility with other models.

InstantID: Zero-shot Identity-Preserving Generation in Seconds

Tencent's PhotoMaker - Faster, More Realistic, and More Controllable AI Avatars

Tencent's PhotoMaker - Faster, More Realistic, and More Controllable AI Avatars

Satisfy the requirements of high efficiency, promising identity fidelity, and flexible text controllability.

Adherence to principles vs flexibility; effective communication & mass media

Adherence to principles vs flexibility; effective communication & mass media

What really matters? First, character. Second, dedication. Third, ability. Fourth, and most important of all, the guts to explain to the people and win their support. - Lee Kuan Yew

Singapore's corporate model of governance

Singapore's corporate model of governance

"Although Singapore faces many problems, 70% can refer to and draw lessons from other countries that have encountered similar issues, and then adapt them according to our national conditions; however, we must not overlook the innovative capacity displayed by Singapore in addressing some issues." - Lee Kuan Yew

Two papers from UC Berkeley: Exploring LLM-enhanced diffusion models for text-to-image translation

Two papers from UC Berkeley: Exploring LLM-enhanced diffusion models for text-to-image translation

Text Prompt -> LLM -> Intermediate Representation (such as an image layout) -> Stable Diffusion -> Image.

Alibaba's DreaMoving: A character video generation framework based on diffusion models.

Alibaba's DreaMoving: A character video generation framework based on diffusion models.

DreaMoving is a diffusion-based controllable video generation framework to produce high-quality customized human videos.

Meta's Audio2Photoreal - From sound to virtual humans in motion.

Meta's Audio2Photoreal - From sound to virtual humans in motion.

From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations

"AutoStory: Minimal Input for High-Quality, Diverse Storytelling Images"

"AutoStory: Minimal Input for High-Quality, Diverse Storytelling Images"

Generating Diverse Storytelling Images with Minimal Human Effort