--- title: Cosmos-Predict2-2B-Video2World canonical_url: "https://www.modelscope.cn/models/nv-community/Cosmos-Predict2-2B-Video2World" md_url: "https://www.modelscope.cn/models/nv-community/Cosmos-Predict2-2B-Video2World.md" repository: nv-community/Cosmos-Predict2-2B-Video2World last_updated: 2025-07-24 license: other pipeline_tag: image-to-video tasks: - image-to-video parameters: 6.9B tensor_type: - F32 - BF16 library_name: - pytorch - diffusers - safetensors frameworks: - pytorch downloads: 851 stars: 1 tags: - nvidia - cosmos - diffusers --- # Cosmos-Predict2-2B-Video2World > Cosmos-Predict2-2B-Video2World - nv-community 在 ModelScope 开源的模型。Cosmos-Predict2: A Suite of Diffusion-based World Foundation Models Available in 2B, and 14B nv-community/Cosmos-Predict2-2B-Video2World 是 ModelScope 魔搭社区上的 6.9B 参数image-to-video模型，采用 other 许可。 - **Repository**: nv-community/Cosmos-Predict2-2B-Video2World - **License**: other - **Tasks**: image-to-video - **Parameters**: 6.9B - **Tags**: nvidia, cosmos, diffusers - **Downloads**: 851 - **Stars**: 1 - **Last updated**: 2025-07-24 Source: https://www.modelscope.cn/models/nv-community/Cosmos-Predict2-2B-Video2World --- # **Cosmos-Predict2: A Suite of Diffusion-based World Foundation Models Available in 2B, and 14B** [**Cosmos**](https://huggingface.co/collections/nvidia/cosmos-predict2-68028efc052239369a0f2959) | [**Code**](https://github.com/nvidia-cosmos/cosmos-predict2) | [**Website**](https://research.nvidia.com/labs/dir/cosmos-predict2/) # Model Overview ## Description **Cosmos-Predict2**: A family of highly performant pre-trained world foundation models purpose-built for generating physics-aware images, videos and world states for physical AI development. Cosmos-Predict2 diffusion models are a collection of diffusion based world foundation models that generate dynamic, high quality images and videos from text, image, or video inputs. It can serve as the building block for various applications or research that are related to world generation. The models are ready for commercial use under NVIDIA Open Model license agreement. **Model Developer**: NVIDIA ## Model Versions The Cosmos-Predict2 diffusion-based model family includes the following models: - [Cosmos-Predict2-2B-Text2Image](https://huggingface.co/nvidia/Cosmos-Predict2-2B-Text2Image) - Given a text description, predict an output image. - [Cosmos-Predict2-14B-Text2Image](https://huggingface.co/nvidia/Cosmos-Predict2-14B-Text2Image) - Given a text description, predict an output image. - [Cosmos-Predict2-2B-Video2World](https://huggingface.co/nvidia/Cosmos-Predict2-2B-Video2World) - Given a text description and an image as the first frame, predict the future frames. - We have six variants for this model to support different use cases: - variant that produces 720P video with 16FPS (this is our default model) - variant that produces 720P video with 10FPS - variant that produces 480P video with 16FPS - variant that produces 480P video with 10FPS - variant that produces 720P video with 16FPS + NATTEN (Sparse Attention variant) - variant that produces 720P video with 10FPS + NATTEN (Sparse Attention variant) - [Cosmos-Predict2-14B-Video2World](https://huggingface.co/nvidia/Cosmos-Predict2-14B-Video2World) - Given a text description and an image as the first frame, predict the future frames. - We have six variants for this model to support different use cases: - variant that produces 720P video with 16FPS (this is our default model) - variant that produces 720P video with 10FPS - variant that produces 480P video with 16FPS - variant that produces 480P video with 10FPS - variant that produces 720P video with 16FPS + NATTEN (Sparse Attention variant) - variant that produces 720P video with 10FPS + NATTEN (Sparse Attention variant) - [Cosmos-Predict2-14B-Video2World-Sample-GR00T-Dreams-GR1](https://huggingface.co/nvidia/Cosmos-Predict2-14B-Video2World-Sample-GR00T-Dreams-GR1): - Video + Text based future visual world generation, post trained on GR00T GR1 data - [Cosmos-Predict2-14B-Video2World-Sample-GR00T-Dreams-DROID](https://huggingface.co/nvidia/Cosmos-Predict2-14B-Video2World-Sample-GR00T-Dreams-DROID): - Video + Text based future visual world generation, post trained on GR00T DROID data - [Cosmos-Predict2-2B-Action-Conditioned-Sample](https://huggingface.co/nvidia/Cosmos-Predict2-2B-Sample-Action-Conditioned) - Given an image as the first frame and next 12 actions, predict the future 12 frames. ### License This model is released under the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license). For a custom license, please contact [cosmos-license@nvidia.com](mailto:cosmos-license@nvidia.com). Under the NVIDIA Open Model License, NVIDIA confirms: * Models are commercially usable. * You are free to create and distribute Derivative Models. * NVIDIA does not claim ownership to any outputs generated using the Models or Derivative Models. **Important Note**: If you bypass, disable, reduce the efficacy of, or circumvent any technical limitation, **safety guardrail** or associated safety guardrail hyperparameter, encryption, security, digital rights management, or authentication mechanism contained in the Model, your rights under [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) will automatically terminate. ### Deployment Geography Global ## Model Architecture Cosmos-Predict2-2B-Video2World is a diffusion transformer model designed for video denoising in the latent space. The network is composed of interleaved self-attention, cross-attention and feedforward layers as its building blocks. The cross-attention layers allow the model to condition on input text throughout the denoising process. Before each layer, adaptive layer normalization is applied to embed the time information for denoising. When image or video is provided as input, their latent frames are concatenated with the generated frames along the temporal dimension. Augment noise is added to conditional latent frames to bridge the training and inference gap. ## Input/Output Specifications * **Input** * **Input Type(s)**: Text+Image, Text+Video * **Input Format(s)**: * Text: String * Image: jpg, png, jpeg, webp * Video: mp4 * **Input Parameters**: * Text: One-dimensional (1D) * Image: Two-dimensional (2D) * Video: Three-dimensional (3D) * **Other Properties Related to Input**: * The input string should contain fewer than 300 words and should provide descriptive content for world generation, such as a scene description, key objects or characters, background, and any specific actions or motions to be depicted within the 5-second duration. * For the 720P model, the input image should be 1280×704; for the 480P model, use 832×480. * The input video should consist of 5 frames, each with a resolution of 1280×704 for the 720P model, or 832×480 for the 480P model. * **Output** * **Output Type(s)**: Video * **Output Format(s)**: mp4 * **Output Parameters**: Three-dimensional (3D) * **Other Properties Related to Output**: The generated video is a 5-second clip, with resolution and frame rate determined by the model variant used. For example, the 720P 16FPS model produces a video with a resolution of 1280×704 and a frame rate of 16 FPS. The video content visualizes the input text description as a short animated scene, capturing key elements within the specified time constraints. 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):** * [Cosmos-Predict2](https://github.com/nvidia-cosmos/cosmos-predict2) * [Diffusers](https://github.com/huggingface/diffusers) ```python import torch from diffusers import Cosmos2VideoToWorldPipeline from diffusers.utils import export_to_video, load_image # Available checkpoints: nvidia/Cosmos-Predict2-2B-Video2World, nvidia/Cosmos-Predict2-14B-Video2World model_id = "nvidia/Cosmos-Predict2-2B-Video2World" pipe = Cosmos2VideoToWorldPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) pipe.to("cuda") prompt = "A close-up shot captures a vibrant yellow scrubber vigorously working on a grimy plate, its bristles moving in circular motions to lift stubborn grease and food residue. The dish, once covered in remnants of a hearty meal, gradually reveals its original glossy surface. Suds form and bubble around the scrubber, creating a satisfying visual of cleanliness in progress. The sound of scrubbing fills the air, accompanied by the gentle clinking of the dish against the sink. As the scrubber continues its task, the dish transforms, gleaming under the bright kitchen lights, symbolizing the triumph of cleanliness over mess." negative_prompt = "The video captures a series of frames showing ugly scenes, static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. Overall, the video is of poor quality." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/yellow-scrubber.png" ) video = pipe( image=image, prompt=prompt, negative_prompt=negative_prompt, generator=torch.Generator().manual_seed(1) ).frames[0] export_to_video(video, "output.mp4", fps=16) ``` **Supported Hardware Microarchitecture Compatibility:** * NVIDIA Ampere * NVIDIA Blackwell * NVIDIA Hopper **Note**: Only BF16 precision is tested. Other precisions like FP16 or FP32 are not officially supported. ## Inference **Acceleration Engine**: [PyTorch](https://pytorch.org/), [Transformer Engine](https://github.com/NVIDIA/TransformerEngine) **Operating System(s):** * Linux (We have not tested on other operating systems.) **System Requirements and Performance:** This model requires 32.54 GB of GPU VRAM. The following table shows inference time for a single generation across different NVIDIA GPU hardware: | GPU Hardware | 480p, 10 FPS | 480p, 16 FPS | 720p, 10 FPS | 720p, 16 FPS | 720p, 10 FPS + NATTEN | 720p, 16 FPS + NATTEN | |------------------------|--------------|--------------|--------------|--------------|-----------------------|-----------------------| | H100 SXM | 25.3 s | 45.5 s | 115.1 s | 228.8 s | 56 s | 94.2 s | | H200 SXM | 24 s | 43.7 s | 111.1 s | 221.7 s | 52.9 s | 89.4 s | | B200 | 14.3 s | 25.5 s | 62.4 s | 123.9 s | 32.6 s | 54 s | | H100 NVL | 34.1 s | 66.4 s | 175.5 s | 355.7 s | 79 s | 138.7 s | | H100 PCIe | 39.5 s | 73.7 s | 187.9 s | 378.5 s | 87.4 s | 149.6 s | | H200 NVL | 27.2 s | 51.4 s | 133.1 s | 267.2 s | 60.7 s | 104.3 s | | L40S | 256.2 s | 480.9 s | 1281.1 s | 2567.1 s | - | - | | RTX PRO 6000 Blackwell | 44.6 s | 84.7 s | 223.1 s | 452.2 s | - | - | **Quality Benchmarks:** For comparative evaluation, we present benchmark scores using the [PBench](https://research.nvidia.com/labs/dir/pbench/). | **Model** | **PBench Overall Score** | **PBench Domain Score** | **PBench Quality Score** | |---------------------------------|---------------------------|-------------------------|--------------------------| | LTX-Video | 74.0 | 77.2 | **70.8** | | HunyuanVideo-I2V | 74.0 | 77.4 | 70.6 | | CogVideoX-5B-I2V | 74.2 | 79.5 | 69.0 | | Wan2.1-I2V-14B-720P | 75.8 | 81.9 | 69.7 | | Cosmos-Predict1-7B-Video2World | 73.2 | 77.4 | 69.0 | | Cosmos-Predict1-14B-Video2World | 73.3 | 77.6 | 69.0 | | Cosmos-Predict2-2B-Video2World | 77.2 | 84.8 | 69.6 | | Cosmos-Predict2-14B-Video2World | **77.4** | **84.9** | 69.9 | NOTE: Cosmos-Predict2 numbers in the above table are both our default variants (720p, 16FPS, no sparsity). Please refer to the table below for PBench scores corresponding to all the Predict2 variants: | **Model** | **PBench Overall Score** | **PBench Domain Score** | **PBench Quality Score** | |--------------------------------------------|--------------------------|-------------------------|--------------------------| | Cosmos-Predict2-2B, 480p, 10 fps | 76.8 | 84.3 | 69.2 | | Cosmos-Predict2-2B, 480p, 16 fps | 76.5 | 83.6 | 69.5 | | Cosmos-Predict2-2B, 720p, 10 fps | 76.5 | 84.1 | 68.9 | | Cosmos-Predict2-2B, 720p, 16 fps | 77.2 | 84.8 | 69.6 | | Cosmos-Predict2-2B, 720p, 10 fps + NATTEN | 76.3 | 83.6 | 69.0 | | Cosmos-Predict2-2B, 720p, 16 fps + NATTEN | 77.0 | 84.5 | 69.5 | | Cosmos-Predict2-14B, 480p, 10 fps | 77.0 | 84.2 | 69.7 | | Cosmos-Predict2-14B, 480p, 16 fps | 77.0 | 84.0 | **70.0** | | Cosmos-Predict2-14B, 720p, 10 fps | 77.3 | **85.0** | 69.6 | | Cosmos-Predict2-14B, 720p, 16 fps | **77.4** | 84.9 | 69.9 | | Cosmos-Predict2-14B, 720p, 10 fps + NATTEN | 76.7 | 84.1 | 69.4 | | Cosmos-Predict2-14B, 720p, 16 fps + NATTEN | 77.0 | 84.2 | 69.9 | # Usage * See [Cosmos-Predict2](https://github.com/nvidia-cosmos/cosmos-predict2) for details. ## Limitations Despite various improvements in world generation for Physical AI, Cosmos-Predict2 video2world models still face technical and application limitations for world prediction. In particular, they struggle to generate long, high-resolution videos without artifacts. Common issues include temporal inconsistency, camera and object motion instability, and imprecise interactions. The models may inaccurately represent 3D space, 4D space-time, or physical laws in the generated videos, leading to artifacts such as disappearing or morphing objects, unrealistic interactions, and implausible motions. As a result, applying these models for applications that require simulating physical law-grounded environments or complex multi-agent dynamics remains challenging. ## 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. 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. For more detailed information on ethical considerations for this model, please see the subcards of Explainability, Bias, Safety & Security, and Privacy below. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). ### 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 Field | Response :---------------------------------------------------------------------------------------------------|:--------------- Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None Measures taken to mitigate against unwanted bias: | None ### Explainability Field | Response :------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------- Intended Application & Domain: | World Generation Model Type: | Transformer Intended Users: | Physical AI developers Output: | Videos Describe how the model works: | Generates videos based on video inputs Technical Limitations: | The model may not follow the video input accurately. Verified to have met prescribed NVIDIA quality standards: | Yes Performance Metrics: | Quantitative and Qualitative Evaluation Potential Known Risks: | The model's output can generate all forms of videos, including what may be considered toxic, offensive, or indecent. Licensing: | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) ### Privacy Field | Response :----------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------- Generatable or reverse engineerable personal information? | None Known Protected class data used to create this model? | None Known Was consent obtained for any personal data used? | None Known How often is dataset reviewed? | Before Release Is there provenance for all datasets used in training? | Yes Does data labeling (annotation, metadata) comply with privacy laws? | Yes Is data compliant with data subject requests for data correction or removal, if such a request was made? | Not Applicable Applicable Privacy Poicy | https://www.nvidia.com/en-us/about-nvidia/privacy-policy/ ### Safety Field | Response :---------------------------------------------------|:---------------------------------- Model Application(s): | World Generation Describe the life critical impact (if present). | None Known Use Case Restrictions: | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license) Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to. Model checkpoints are made available on Hugging Face, and may become available on cloud providers' model catalog.