| | --- |
| | license: other |
| | license_name: sv3d-nc-community |
| | license_link: LICENSE |
| | datasets: |
| | - allenai/objaverse |
| | pipeline_tag: image-to-3d |
| | extra_gated_prompt: >- |
| | By clicking here, you accept the License agreement, and will use the Software |
| | Products and Derivative Works for non-commercial or research purposes only. A |
| | commercial license is required to self-host the Software Products for |
| | commercial purposes. [Please learn more about our self-hosted Membership |
| | options here](https://stability.ai/membership). |
| | |
| | By clicking below, you agree to sharing with Stability AI the information |
| | contained within this form and that Stability AI can contact you for the |
| | purposes of marketing our products and services. |
| | extra_gated_fields: |
| | I agree: checkbox |
| | Yes, I consent to receiving Stability AI marketing communications: checkbox |
| | --- |
| | # Stable Video 3D |
| |  |
| | **Stable Video 3D (SV3D)** is a generative model based on [Stable Video Diffusion](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt) that takes in a still image of an object as a conditioning frame, and generates an orbital video of that object. |
| |
|
| | ## Model Details |
| |
|
| | This model was trained to generate 21 frames at resolution 576x576 given a context frame of the same size, finetuned from SVD Image-to-Video. Please check our [tech report](https://stability.ai/s/SV3D_report.pdf) and [video summary](https://youtu.be/Zqw4-1LcfWg) for details. |
| |
|
| | We release two variants of the model: |
| | 1. **SV3D_u**: This variant generates orbital videos based on single image inputs without camera conditioning. |
| | 2. **SV3D_p**: Extending the capability of SVD3_u, this variant accommodates both single images and orbital views allowing for the creation of 3D video along specified camera paths. |
| | |
| | |
| | ### Model Description |
| | |
| | * **Developed by**: [Stability AI](https://stability.ai/) |
| | * **Model type**: Generative image-to-video model |
| | * **License**: [StabilityAI Non-Commercial Research Community License](https://huggingface.co/stabilityai/sv3d/raw/main/LICENSE). If you want to use this model for your commercial products or purposes, please contact us [here](https://stability.ai/contact) to learn more. |
| | |
| | ### Model Sources |
| | |
| | * **Repository**: https://github.com/Stability-AI/generative-models |
| | * **Tech report**: https://stability.ai/s/SV3D_report.pdf |
| | * **Video summary**: https://youtu.be/Zqw4-1LcfWg |
| | * **Project page**: https://sv3d.github.io |
| | * **arXiv page**: https://arxiv.org/abs/2403.12008 |
| |
|
| | ### Training Dataset |
| |
|
| | We use renders from the [Objaverse](https://objaverse.allenai.org/objaverse-1.0) dataset, utilizing our enhanced rendering method that more closely replicate the distribution of images found in the real world, significantly improving our model’s ability to generalize. We selected a carefully curated subset of the Objaverse dataset for the training data, which is available under the CC-BY license. |
| |
|
| |
|
| | ## Usage |
| |
|
| | For usage instructions, please refer to our [generative models GitHub repository](https://github.com/Stability-AI/generative-models) |
| |
|
| |
|
| | ### Out-of-Scope Use |
| |
|
| | The model was not trained to be factual or true representations of people or events, |
| | and therefore using the model to generate such content is out-of-scope for the abilities of this model. |
| | The model should not be used in any way that violates Stability AI's [Acceptable Use Policy](https://stability.ai/use-policy). |
