ActAnywhere is a research video generation model that automatically creates temporally consistent, motion-aware backgrounds for foreground subjects—enabling seamless background replacement and visual effects without manual keyframing or green screens.
Follow Your Pose is an open research framework that generates highly controllable, temporally coherent videos from text prompts and user-specified human pose sequences.
OLMo is a fully open, high-performance language model framework offering transparent training data, reproducible code, and standardized evaluation tools for researchers and developers.
SafeEar is an open-source AI framework that detects audio deepfakes by analyzing acoustic features while preserving speaker privacy across multiple languages.
Make-A-Character is an open-source AI framework that generates highly realistic, customizable 3D digital humans from text descriptions, supporting full-body modeling, animation-ready rigging, and production-grade rendering.
MotionCtrl is an open-source motion controller for video generation models that enables independent, precise control of camera movement and object motion in AI-generated videos.
Llama 3.2 is Meta's open-weight multimodal model family optimized for edge devices, supporting vision-language understanding, on-device text generation, and customizable local deployment.
AnimateDiff is an open-source framework that transforms existing text-to-image models into animation generators without retraining, enabling high-fidelity, style-consistent video sequences from text prompts.
PortraitGen is an open-source AI video editing tool that enables high-fidelity, temporally consistent editing of human portrait videos using 3D Gaussian splatting and neural texture modeling.
GOT-OCR2.0 is an open-source, multimodal OCR model that converts complex documents—including math, charts, music scores, and multilingual text—into editable Markdown or LaTeX with interactive region control and long-context understanding.
V-JEPA is an open-source, self-supervised video foundation model that learns visual representations by predicting masked frame features—enabling robust video understanding without labels.
Boximator is an open-source video synthesis tool that enables precise object motion control in videos using hardhttps://www.aitopic.com/soft bounding box constraints and self-tracking techniques.
DiT is an open-source image generation model that replaces convolutional U-Nets with Transformers in diffusion models to produce high-fidelity, scalable, and controllable synthetic images.
VideoPoet is a multimodal AI video generator developed by Google Research that creates high-fidelity videos from text, images, or video inputs—and synthesizes matching audio.
ScreenAgent is an open-source AI agent that observes real computer screens and autonomously performs complex desktop tasks using vision-language understanding and reinforcement learning.
ChatMusician is an open-source large language model that understands and generates music using text-based notation—enabling composition, theory Q&A, and stylistic imitation without external multimodal components.
Snap Video is a research-grade text-to-video generator developed by Snap Inc. that produces high-fidelity, motion-rich videos using a video-first transformer architecture and extended EDM framework.
TextDiffuser-2 is an open-source text-to-image diffusion model that generates high-fidelity, resolution-flexible images from natural language descriptions.
OmniGen is an open-source unified diffusion model that handles text-to-image generation, image editing, subject-driven synthesis, visual conditioning, and even classic CV tasks—all within a single streamlined architecture.
Loopy is an open-source audio-driven digital human generator that creates realistic, expressive portrait avatars from speech or singing audio—no motion templates required.