Stable Video 4D 2.0 (SV4D 2.0)
is a generative model based on
Stable Video 4D (SV4D)
, which takes in a single-view video of an object and generates multiple novel-view videos (4D image matrix) of that object.
Please note: For individuals or organizations generating annual revenue of US $1,000,000 (or local currency equivalent) or more, regardless of the source of that revenue, you must obtain an enterprise commercial license directly from Stability AI before commercially using SV4D 2.0, or any derivative work of SV4D 2.0 or its outputs, such as “fine tune” or “low-rank adaption” models. You may submit a request for an Enterprise License at
https://stability.ai/enterprise
. Please refer to Stability AI’s Community License, available at
https://stability.ai/license
, for more information.
Model details
: This model is trained to generate 48 images (12 video frames x 4 camera views) at 576x576 resolution, given a reference video of 12 frames of the same size.
The generated 12x4 image matrix can be viewed as 4 videos (12 frames each), showing how the dynamic object looks from 4 different camera angles specified by the user.
We also release an 8-view model that generates 5 frames x 8 views at a time (same as SV4D). To generate longer novel-view videos, we use the first generated frames as reference, and then sample the remaining frames in an auto-regressive manner.
Please check our
arxiv paper
and
video summary
for details.
License
Community License:
Free for research, non-commercial, and commercial use by organizations and individuals generating annual revenue of US $1,000,000 (or local currency equivalent) or less, regardless of the source of that revenue. If your annual revenue exceeds US $1M, any commercial use of this model or derivative works thereof requires obtaining an Enterprise License directly from Stability AI. You may submit a request for an Enterprise License at
https://stability.ai/enterprise
. Please refer to Stability AI’s Community License, available at
https://stability.ai/license
, for more information.
We use renders from the
Objaverse-XL
dataset, available under the Open Data Commons Attribution License, utilizing our enhanced rendering method that more closely replicates the distribution of images found in the real world, significantly improving our model's ability to generalize. We filter objects based on the review of licenses and curated a subset suitable for our training needs.
The model was not trained to be factual or true representations of people or events. As such, using the model to generate such content is out-of-scope of the abilities of this model.
Safety
As part of our safety-by-design and responsible AI deployment approach, we implement safety measures throughout the development of our models, from the time we begin pre-training a model to the ongoing development, fine-tuning, and deployment of each model. We have implemented a number of safety mitigations that are intended to reduce the risk of severe harms. However, we recommend that developers conduct their own testing and apply additional mitigations based on their specific use cases.
For more about our approach to Safety, please visit our
Safety page
.
Contact
Please report any issues with the model or contact us:
sv4d2.0 huggingface.co is an AI model on huggingface.co that provides sv4d2.0's model effect (), which can be used instantly with this stabilityai sv4d2.0 model. huggingface.co supports a free trial of the sv4d2.0 model, and also provides paid use of the sv4d2.0. Support call sv4d2.0 model through api, including Node.js, Python, http.
sv4d2.0 huggingface.co is an online trial and call api platform, which integrates sv4d2.0's modeling effects, including api services, and provides a free online trial of sv4d2.0, you can try sv4d2.0 online for free by clicking the link below.
stabilityai sv4d2.0 online free url in huggingface.co:
sv4d2.0 is an open source model from GitHub that offers a free installation service, and any user can find sv4d2.0 on GitHub to install. At the same time, huggingface.co provides the effect of sv4d2.0 install, users can directly use sv4d2.0 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.