Research framework for controllable video generation from sketches, pose or line art, a reference image and a text prompt.
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.
CogOmniControl is a research project on reasoning-driven controllable video generation, described as working via "Creative Intent Cognition". It is authored by Hongji Yang, Songlian Li, Yucheng Zhou, Xiaotong Zhao, Alan Zhao, Chengzhong Xu and Jianbing Shen, and hosted as a project page under the um-lab GitHub organization.\n\nAccording to a YouTube creator summary, it works like a ControlNet-style system for video: the user supplies control signals such as sketches, pose skeletons or line art, plus a reference image and a text prompt, and the model generates a video that follows them. The project page shows example outputs with long, detailed text prompts.\n\nAs of the available material, only a paper and project page are reported; no code, weights, demo or pricing have been found. It is not usable by the public yet, and details such as the base model, license and release date are not confirmed.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
ControlNet-like system for video generation using sketches, pose skeletons or line art plus a reference image and text prompt. Only a paper is released so far.
Closest neighbours by meaning, not just by category.
Research
Diffusion framework that learns text-to-3D human motion generation from 2D poses extracted from monocular videos.
Model · ByteDance
ByteDance unified video generation and editing framework pairing an MLLM semantic planner with a DiT renderer.
Model
Research method for multi-shot text-to-video with frame-accurate cuts, fades and camera moves, built on Wan2.1-T2V-14B.
Model · ByteDance
ByteDance research model unifying image and video understanding, generation and editing in a 3B active-parameter network.
Library · Tencent
Positional encoding method that gives video diffusion transformers precise camera control from an image and camera path.
Model · OpenMOSS
Open-weights 5B text-to-image model family from OpenMOSS with native JSON bounding-box layout control and text rendering.
