Stay up to date with the latest AI research, models, tools and behind-the-scenes stories at the intersection of AI and VFX.
Four practical techniques for faster, better video generation: MagCache accelerates diffusion 2-3x, NAG brings back negative prompting to distilled models, DLoRAL upscales in one step, and MIT shows how AI helps preserve paintings.
Read more →Four groundbreaking papers democratizing AI development - from training competitive video models with 256 NPUs to tracking through occlusions, streaming video generation, and climate modeling.
Read more →Transform a single LEGO photo into a complete animated shot using WAN 2.1 with ATI trajectory animation, CoTracker motion tracking, SAM2 segmentation, and VACE inpainting in ComfyUI.
Read more →Master four game-changing video generation techniques with complete ComfyUI workflows: NormalCrafter for relighting, Any-to-Bokeh for depth control, Uni3C for camera motion, and ATI for trajectory-based animation.
Read more →Celebrating ILM's 50th anniversary from warehouse to AI, Jafar Panahi's Cannes Palme d'Or win despite Iranian ban, Cinesite's ethical AI unit TechX, SpatialScore's 28k-sample 3D benchmark for LLMs, Jenga's 4-10x speedup for video diffusion, and AgenticSeek's local AI assistant.
Read more →