note

On the Stable Diffusion WebUI Specification Where the Same Image is Occasionally Generated Twice

Everyone, are you enjoying generating images (gacha) with Stable Diffusion? To my comrades who spend their days kneading prompts, chasing after ideal beautiful girls and stunning backgrounds: have you ...
note

The story of how I was recommended 'stable-diffusion.cpp' instead of ComfyUI when trying to test the buzzworthy Krea 2 on my MacBook (32GB RAM)

For the past few days (well, it's been a little while now), the open-sourcing of 'Krea 2', a professional-grade AI image generator, has been causing quite a stir in the local AI community. Hearing ...
GitHub

FlowWM stochastic world modeling via flow matching in DINOv3 feature space, with the FuturePerception (Waymo) benchmark.

FlowWM stochastic world modeling via flow matching in DINOv3 feature space, with the FuturePerception (Waymo) benchmark. - ...
GitHub

ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

ARDY is an autoregressive diffusion model designed for interactive motion generation, supporting online text prompting and flexible long-horizon kinematic constraints (root paths/waypoints, full-body ...