Wan-Animate-2 pushes character animation beyond pose-driven pipelines: reference image + driving video in, cleaner character motion out. 🚀 🤖modelscope.ai/models/Wan-AI/… 🌐modelscope.ai/studios/Wan-AI… 🏆 Blind user study: preferred over Wan-Animate in 70%+ of overall-quality comparisons, with perceived quality comparable to Dreamina and Kling-MotionControl. 🎬 Cleaner animation: directly processes driving-video motion instead of relying on pose skeletons, reducing identity drift, artifacts, and shape distortion across different characters. 🎥 Text camera control: Viewpoint LoRA lets prompts steer the output perspective while keeping the original motion consistent. ⚡ Streaming path: Wan-Animate-2-Lite reports 24fps at 400x720, with stable long-sequence generation for live avatars and interactive virtual environments. Built with dual-branch DiT, Time-Align RoPE, Sparse-Ref Attention, 100K+ video pairs, and 50K Unreal Engine multi-view samples.

Thank you @nvidia for the hookup on this DGX Workstation. This will crunch a *lot* of high quality tokens here! This thing is a total beast.

DiffusionGemma, our experimental open model released under an Apache 2.0 license, explores text diffusion, an exceptionally fast approach to text generation. Here’s how DiffusionGemma accelerates development: + Faster token output: By shifting the bottleneck from memory bandwidth to raw compute, the model generates up to 4x faster token output on dedicated GPUs + Accessible hardware footprint: Activates just 3.8B parameters during inference, fitting comfortably within 24GB-VRAM high-end consumer GPUs when quantized + Novel workflows: Parallel token generation enables self-correction, making it ideal for code infilling, in-line editing, and non-linear structures DiffusionGemma prioritizes speed over raw quality and accelerates best on compute-bound hardware (like @NVIDIAAI GPUs). Standard @GoogleGemma 4 remains recommended for production quality and memory-bound devices.