eyaler/chronoedit

<p align="center"> <img src="https://cdn-uploads.huggingface.co/production/uploads/658529d61c461dfe88afe8e8/tto-qt1BmKdhObReEKBq2.png" width="400"/> <p>

<p align="center"> 💚 <a href="https://research.nvidia.com/labs/toronto-ai/chronoedit/"><b>ChronoEdit</b></a> &nbsp&nbsp ｜ &nbsp&nbsp 🖥️ <a href="https://github.com/nv-tlabs/ChronoEdit">GitHub</a> &nbsp&nbsp | &nbsp&nbsp🤗 <a href="https://huggingface.co/collections/nvidia/chronoedit">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://huggingface.co/spaces/nvidia/ChronoEdit">Gradio Demo</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://arxiv.org/abs/2510.04290">Paper</a> &nbsp&nbsp <br>

ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

Description:

ChronoEdit-14B enables physics-aware image editing and action-conditioned world simulation through temporal reasoning. It distills priors from a 14B-parameter pretrained video generative model and separates inference into (i) a video reasoning stage for latent trajectory denoising, and (ii) an in-context editing stage for pruning trajectory tokens. ChronoEdit-14B was developed by NVIDIA as part of the ChronoEdit family of multimodal foundation models. This model is ready for commercial use.

License/Terms of Use

Governing Terms: Use of this model is governed by the NVIDIA Open Model License Agreement. Additional Information: Apache License Version 2.0.

Deployment Geography

Global

Use Case

Researchers and developers for:

• —Physics-aware in-context image editing
• —Action-conditioned world simulation (PhysicalAI)
• —Benchmarking multimodal foundation models

Release Date

• —Hugging Face: 10/29/2025 via ChronoEdit.

• —GitHub: 29/10/2025 via GitHub Repo Link

References(s)

• —ChronoEdit: Temporal Reasoning for In-Context Image Editing (Preprint, 2025)
• —Related NVIDIA works: Cosmos,Gen3C,DiffusionRenderer,Difix3D

Model Architecture

Architecture Type: Diffusion Transformer Network Architecture: Custom temporal denoising transformer Base Model: Pretrained video generative model (14B parameters) Number of Parameters: ~1.4 × 10^10

Input

Input Type(s): Image + Text (instruction) Input Format:

• —Text: UTF-8 string
• —Image: RGB (.png, .jpg) Input Parameters:
• —Image: Two-Dimensional (2D) Red, Green, Blue (RGB), variable resolution (recommended ≤1024×1024)
• —Text: One-Dimensional (1D), up to ~300 tokens Other Properties Related to Input:
• —Image Resolution: 1280 x 720 or 720 x 1280 or 960 x 960 or 1024×1024

Output

Output Type(s): Image Output Format: RGB (.png) Output Parameters: Two-Dimensional (2D) Red, Green, Blue (RGB), resolution configurable Other Properties Related to Output:

• —Image Resolution: 1280 x 720 or 720 x 1280 or 960 x 960 or 1024×1024

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

Software Integration

Runtime Engine(s):

• —PyTorch / Diffusers
• —Triton Inference Server (optional)

Supported Hardware Microarchitecture Compatibility:

• —NVIDIA Ampere
• —NVIDIA Blackwell
• —NVIDIA Hopper
• —NVIDIA Lovelace

Preferred Operating Systems:

• —Linux

The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.

Model Version(s)

• —ChronoEdit-14B v1.0 (initial public release, 03/2025)

Training, Testing and Evaluation Datasets

Training Dataset:

• —Synthetic world interaction data (robot arm manipulation, object picking, temporal consistency)
• —Open-domain video-text corpora (research use only)

Data Modality: Image, Text, Video

Image Training Data Size: 1 Million to 1 Billion Images

Text Training Data Size: Less than 10,000 Hours

Data Collection Method: Hybrid: Synthetic, Automated, Human

Labeling Method: Hybrid: Synthetic, Automated, Human

Properties:

• —Modalities: 10 million image and text pair
• —Nature of the content: Synthetic world interaction data (robot arm manipulation, object picking, temporal consistency)
• —Linguistic characteristics: Natural Language

Testing Dataset

• —Held-out portion of training dataset for action-conditioned tasks.

Data Collection Method: Automated

Labeling Method by dataset: Automated

Properties:

• —Modalities: 500 million image and text pair
• —Nature of the content: Robot world interaction data (robot arm manipulation, object picking, temporal consistency)
• —Linguistic characteristics: Natural Language

Evaluation Dataset

• —Held-out portion of training dataset for action-conditioned tasks.

Data Collection Method: Automated

Labeling Method by dataset: Automated

Properties:

• —Modalities: 500 million image and text pair
• —Nature of the content: Robot world interaction data (robot arm manipulation, object picking, temporal consistency)
• —Linguistic characteristics: Natural Language

Inference

Acceleration Engine: TensorRT, Triton Test Hardware: NVIDIA H100, NVIDIA B200

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ Bias, Explainability, Safety & Security, and Privacy Subcards.

Users are responsible for model inputs and outputs. Users are responsible for ensuring safe integration of this model, including implementing guardrails as well as other safety mechanisms, prior to deployment.

Please make sure you have proper rights and permissions for all input image and video content; if image or video includes people, personal health information, or intellectual property, the image or video generated will not blur or maintain proportions of image subjects included.

Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.

Plus Plus (++) Promise

We value you, the datasets, the diversity they represent, and what we have been entrusted with. This model and its associated data have been:

• —Verified to comply with current applicable disclosure laws, regulations, and industry standards.
• —Verified to comply with applicable privacy labeling requirements.
• —Annotated to describe the collector/source (NVIDIA or a third-party).
• —Characterized for technical limitations.
• —Reviewed to ensure proper disclosure is accessible to, maintained for, and in compliance with NVIDIA data subjects and their requests.
• —Reviewed before release.
• —Tagged for known restrictions and potential safety implications.

Bias

Explainability

Privacy

Safety

Citation

@article{wu2025chronoedit,
    title={ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation},
    author={Wu, Jay Zhangjie and Ren, Xuanchi and Shen, Tianchang and Cao, Tianshi and He, Kai and Lu, Yifan and Gao, Ruiyuan and Xie, Enze and Lan, Shiyi and Alvarez, Jose M. and Gao, Jun and Fidler, Sanja and Wang, Zian and Ling, Huan},
    journal={arXiv preprint arXiv:2510.04290},
    year={2025}
}