generative-model

[ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis

Official implementation of "MeshDiffusion: Score-based Generative 3D Mesh Modeling" (ICLR 2023 Spotlight)

CraftsMan: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage

[CVPR 2024] Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models, a no lighting baked texture generative model

[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.

[ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

[CVPR 2026🔥] 🧑‍🎨 OmniLottie, an open-sourced multi-modal instructed vector animation generator that produces Lottie JSONs.

[ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning

[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

Official release of the ProGen models

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.

Generation of protein sequences and evolutionary alignments via discrete diffusion models

A library for generating and evaluating synthetic tabular data for privacy, fairness and data augmentation.

[TPAMI 2023] SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections

A library to model multivariate data using copulas.

Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]

PyTorch Re-Implementation of "Generating Sentences from a Continuous Space" by Bowman et al 2015 https://arxiv.org/abs/1511.06349

Leverage hallucinations from Large Language Models (LLMs) for novelty-driven explorations.

SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.

A Euclidean diffusion model for structure-based drug design.

[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding