Stars
OmniGen2: Exploration to Advanced Multimodal Generation.
cjeen / LoRAEdit
Forked from tdrussell/diffusion-pipeWe achieves high-quality first-frame guided video editing given a reference image, while maintaining flexibility for incorporating additional reference conditions.
Official implementation of "Text-Aware Image Restoration with Diffusion Models"
MidJourney client. Unofficial Node.js client
Pre-assembled gizmos for ComfyUI within Nuke
Hackable and optimized Transformers building blocks, supporting a composable construction.
Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)
[SIGGRAGH'25] Official repository of LayerFlow: A Unified Model for Layer-aware Video Generation
Any-to-Bokeh is a novel one-step video bokeh framework that converts arbitrary input videos into temporally coherent, depth-aware bokeh effects.
SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
Wan: Open and Advanced Large-Scale Video Generative Models
Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
Official repository for "Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment"
Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS …
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
A Modular Framework for 3D Generation and Beyond [WIP]
Official project page of MTVCrafter, a new paradigm for animating arbitrary characters with 4D motion tokens.
Open-source video compositing software. Node-graph based. Similar in functionalities to Adobe After Effects and Nuke by The Foundry.
Wrapper for X-Portrait for running in ComfyUI
KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment
DreamO: A Unified Framework for Image Customization
[CVPR 2025] RollingDepth: Video Depth without Video Models