New to the index. Changes worth knowing.

Vidpixo is an AI product video generator for e-commerce sellers. It turns product photos into shoppable videos, clones viral video styles, and creates AI product photos in one workspace.

GenPix is an AI image generator that turns text prompts into high-quality images, with Nano Banana Pro, GPT Image 2 and more high-fidelity models.

An AI dance generator that turns a single full-body photo into a smooth, shareable dance video. Pick a dance style from the library, upload a front-facing photo, and the AI animates a performance - clips run up to 30 seconds in HD MP4 without watermark, made for TikTok and Reels. One-time credit packs, no subscription.

A camera-controllable streaming video world model that grows a 360° scene prior from a single perspective image.

A world model that reasons through motion and geometry with an explicit chain of thought before predicting future video.

Long-horizon video world model rollouts that stay geometrically consistent through a fixed-size geometry-aware implicit memory.

Two released research systems in one repository: a long-horizon multi-shot audio-video generator and an interactive omnimodal world model.

Real-time instruction-guided editing of open-ended video streams with an autoregressive diffusion transformer.

An interactive world model that streams explorable 704 × 1280 video while you drive the camera with keyboard and mouse.

A project page for a block-causal LTX-2.3 rebuild that generates joint audio and video in real time with mid-stream text instructions.

An omni world model for spatial intelligence with pixel-perfect camera-controlled image and video generation.

Run an action-conditioned interactive world model with open-ended rollout on a single desktop GPU.

An experimental interface for steering objects and camera motion while AI video is being generated.

Generate continuing interactive worlds with bounded external state, mid-rollout prompts and camera control.

Build long-horizon playable video worlds with camera control, prompt switching and explicit spatial memory.

Train few-step autoregressive video generators with frame-wise and chunk-wise Causal Forcing variants.

Generate video progressively with a distilled causal diffusion model supporting streaming and dynamic prompts.

Diffusion-powered visual agents for continuous LLM-connected conversations and long-form avatar video.

A hosted real-time video-to-video editing model with live prompts, references and SDK sessions.

A general-purpose action-controlled video world model with open-ended event response and long-rollout training.

Train playable action-conditioned video world models with an open progressive causal recipe.

Generate egocentric video worlds controlled by tracked hand poses and camera motion from VR equipment.

Create and navigate generated environments in real time through the experimental Project Genie experience.

Run a released 14B long-video model with training code, inference tools and distilled checkpoints.