by Viggle
Geometry-guided video-to-video model from Viggle that re-renders existing footage along a new camera path and timing.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Meridian is a video-to-video model from Viggle AI, built as an adapter on MiniMax-H3. It takes a recorded video and re-renders the event from a new viewpoint along a user-chosen camera path. It can also generate a camera move from a single image.
Geometry comes from VGGT-Omega, which reconstructs a rough 3D point cloud of the scene that guides the re-rendering. Space and time can be controlled independently: the action can play, be slowed, or be held still while the camera moves, then resumed. The model card shows examples including compound camera paths (orbit, sideways move, distance change) in one continuous shot.
Weights are published on Hugging Face (diffusers/safetensors format) under the MiniMax-H3 community license, a custom "other" license. A YouTube reviewer reported a base model size of about 62 GB. Users should check the license terms for usage restrictions.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Open-source model built on MiniMax H3 that changes the camera angle and timing of an existing video. It reconstructs a rough 3D point cloud with VGGT Omega, then re-renders the scene along a new camera path. The base model is about 62 GB.
Closest neighbours by meaning, not just by category.
Model · Viggle
Open-weights video model that replaces a character in a clip using one repainted frame, fine-tuned from MiniMax-H3.
Model
Research model for video relighting that jointly generates relit video and per-frame environment maps, no camera poses needed.
Model
3D-aware 360° video diffusion model that generates panoramic videos along user-defined camera paths from sparse panoramas.
Model · Netflix (Eyeline Labs)
Netflix Eyeline research model that restyles video from an edited keyframe while preserving face identity and performance.
Library · Tencent
Positional encoding method that gives video diffusion transformers precise camera control from an image and camera path.
Research
Research system that turns a single image into a 360° Gaussian scaffold and renders interactive video at 8 FPS.
