Steerable Motion

Pricing model
GitHub
Upvote 0
Steerable Motion is a node in ComfyUI that facilitates batch creative interpolation. It incorporates optimal techniques for directing motion with images as video models advance. The node includes features like key frame position, influence duration, influence strength, and relative IPA strength & influence. It serves as an artistic tool that benefits from experimentation to maximize its potential. The node is greatly influenced by Kosinkadink's ComfyUI-Advanced-ControlNet and Cubiq's IPAdapter_plus, while the workflows utilize Kosinkadink’s Animatediff Evolved, Fizzledorf's Fizznodes, Fannovel16's Frame Interpolation, and other tools.

Similar neural networks:

Paid
Upvote 0
Transform your videos in a whole new way. Expand your audience and increase your impact by converting lengthy videos into compelling shorts, providing viewers with an enticing preview of your channel's offerings. Dedicate less time to editing and more to creating as our AI efficiently scans your content, pinpointing the most engaging sections. Test it for free or apply the coupon code HEY10 to receive a 10% lifetime discount.
Free
Upvote 1
Omniverse Audio2Face is a reference application that facilitates the animation of a 3D character to align with any voice-over track. It comes equipped with a 3D character model that can be animated using a voice-over track, where the audio input is processed by a pre-trained Deep Neural Network. The output then manipulates the 3D vertices of the character mesh to generate real-time facial animation. Additionally, it includes a character transfer feature, enabling users to retarget any 3D human or human-like face and scale the output with multiple characters in the scene, while controlling the character's emotion through an AI network. It also offers data conversion features for blendshape conversion and blendweight export options, and it supports export-import with Blendshapes for Blender and Epic Games Unreal Engine to produce character motion.
Price Unknown / Product Not Launched Yet
Upvote 0
Dumme is an AI-driven tool for generating short videos, capable of processing any video or podcast regardless of length or content type. It automatically identifies moments worth clipping while maintaining context and structure. The result is ready-to-upload short videos complete with captions, titles, and descriptions optimized for algorithmic performance across platforms, with no need for a YouTube account. Dumme is compatible with most languages and caters to content creators with existing long-form material.