Image, video and 3D creation, creative tools and practical workflows.
One workspaceSiber Sörfçü presents Lotzy’s evolving canvas and a Claude MCP connection. The alpha app is free to access, while generation uses a connected Higgsfield account.
Mario in the roomA prototype lets the player reach into the game, offer a hand as a platform and move Mario into the room.
Small model, big editsDigitale Profis introduces Black Forest Labs’ compact image model, with ten reference images, region-based editing and an INT8 option for 8 GB NVIDIA cards.
Your creative appDigitale Profis shows how Runway App Studio builds task-focused tools from plain-language descriptions and shares established creative workflows with a team.
Less waitingDigitale Profis explores fal’s faster video model, with text and image inputs and a provider-measured 12.45-second generation time for a ten-second clip.
Code to filmSenseNova 6.8 Code2Video uses code generation to create animation and video scenes.
Train virtuallyNVIDIA SimReady assets provide objects intended for robotics and physical AI simulations.
Cleaner edgesMatAnyone-E aims to make high-resolution video foreground separation more efficient.
Image to 3DSperid Labs Idol creates viewable 3D Gaussian splat objects from a single image.
Motion flowsNVIDIA Research presents a unified motion framework for navigation and object interaction.
Find your workSebastian Kamph tests Numonic with a 317-file ComfyUI folder. Search, metadata, exports and automatic capture help—but important limits remain.
Worlds respondMatt Wolfe tests a rainy cyberpunk city and a cartoon world. The demonstrations reveal both live scene changes and problems with continuity.
