Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos

Code for [CVPR 2025] ROICtrl: Boosting Instance Control for Visual Generation

[NeurIPS 2024] EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models.

High-resolution models for human tasks.

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

(ECCV 2024) Empowering Multimodal Large Language Model as a Powerful Data Generator

CosmicMan: A Text-to-Image Foundation Model for Humans (CVPR 2024)

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

Open-Sora: Democratizing Efficient Video Production for All

AvatarStudio: High-fidelity and Animatable 3D Avatar Creation from Text

[CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"

[NeurIPS 2023] XAGen: 3D Expressive Human Avatars Generation

[ICCV 2023] GETAvatar: Generative Textured Meshes for Animatable Human Avatars

[IJCV] Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation

FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)

MagicEdit: High-Fidelity Temporally Coherent Video Editing

MagicAvatar: Multimodal Avatar Generation and Animation

[CVPR 2024] ViT-Lens: Towards Omni-modal Representations

[NeurIPS2023] DatasetDM:Synthesizing Data with Perception Annotations Using Diffusion Models

[ICCV 2023] UniVTG: Towards Unified Video-Language Temporal Grounding

[CVPR2024, Highlight] Official code for DragDiffusion

The repository for paper Unsupervised Volumetric Animation

[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

[Image 2 Text Para] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.