Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation"

[NeurIPS 2025 D&B🔥] OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

VideoCoF: Unified Video Editing with Temporal Reasoner

EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling

📖 This is a repository for organizing papers, codes, and other resources related to unified multimodal models.

[NeurIPS 2025] The official repository of "Sekai: A Video Dataset towards World Exploration"

Vision Bridge Transformer at Scale

[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"

[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

"MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation"

A curated list of recent diffusion models for video generation, editing, and various other applications.

[ICLR 2026] LongLive: Real-time Interactive Long Video Generation

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

Kandinsky 5.0: A family of diffusion models for Video & Image generation

HunyuanVideo-1.5: A leading lightweight video generation model

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

我的 nano-banana 创意玩法大合集！ 持续更新中！

Official Repo for Self-Forcing++ High Quality Long Video Generation

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

[ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

[Unofficial] RF Inversion implemented for SD3 / SD3.5

Reference PyTorch implementation and models for DINOv3

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

A unified inference and post-training framework for accelerated video generation.

4-steps distilled version of Wan2.2-TI2V-5B