Update README.md

README.md

@@ -1,5 +1,111 @@
 ---
+pipeline_tag: text-to-video
+tags:
+  - text-to-video
+  - video-generation
+  - audio-video-generation
+  - api
+  - closed-weights
+  - proprietary
 license: other
 license_name: yoroll-terms-of-use
 license_link: https://docs.yoroll.ai/yoroll-terms-of-use/en
+language:
+  - en
+  - zh
 ---
+
+# Superfast Video
+
+Superfast Video is a proprietary, closed-weight text-to-video model developed
+by **LINEARGAME PTE. LTD.** and made available under the **YorollAI** brand.
+It generates 1344×768, 24 fps videos with audio through a hosted API.
+
+> **API-only availability:** model weights, training code, inference code, and
+downloadable checkpoints are not distributed through this repository.
+
+## Try the model
+
+- [Interactive Hugging Face Space](https://yorollai-superfast-video.hf.space/)
+- [Yoroll Terms of Use](https://docs.yoroll.ai/yoroll-terms-of-use/en)
+- Contact: [yoroll@support.ai](mailto:yoroll@support.ai)
+
+The Hugging Face Space is a hosted evaluation interface. It sends requests to
+the official Superfast API; inference does not run from model files stored in
+this repository.
+
+## Capabilities
+
+| Property | Current hosted preview |
+| --- | --- |
+| Task | Text-to-video |
+| Output resolution | 1344×768 |
+| Frame rate | 24 fps |
+| Audio | Included |
+| Durations | 5, 10, or 15 seconds |
+| Controls | Text prompt and seed |
+| Access | Hosted API only |
+
+## Intended use
+
+Superfast Video is intended for creative video generation, concept
+visualization, prototyping, marketing creatives, social video, entertainment,
+and other lawful uses permitted by the applicable service plan and the Yoroll
+Terms of Use.
+
+### Commercial use
+
+- The public Hugging Face Space is provided for evaluation, demonstration,
+  and non-commercial testing.
+- General commercial use is available to eligible paid API customers, subject
+  to the applicable service plan and the Yoroll Terms of Use.
+- High-volume use, white-label or resale use, regulated or high-risk use cases,
+  and uses requiring custom service levels or contractual assurances require a
+  separate enterprise agreement.
+- No access or license to the model weights, inference implementation, or
+  other proprietary model technology is granted.
+
+Subject to applicable law and the governing service terms, YorollAI does not
+claim ownership of a user's eligible output solely because it was generated
+using the service. Copyrightability varies by jurisdiction and by the degree
+of human contribution. Outputs are not guaranteed to be unique, copyrightable,
+or free of third-party rights.
+
+## Restrictions and responsible use
+
+Users must have all rights and permissions required for their prompts and
+other inputs. The service must not be used for illegal content, fraud,
+deceptive impersonation, privacy or publicity-rights violations, infringement
+of intellectual property, sexual exploitation, or other uses prohibited by
+the Yoroll Terms of Use or applicable law.
+
+Users are responsible for reviewing generated content before publication or
+commercial deployment. Extra review and safeguards are necessary when content
+depicts real people, brands, protected characters, sensitive events, or other
+third-party rights.
+
+## Limitations
+
+- Generated video may contain visual, temporal, physical, textual, or audio
+  inconsistencies.
+- The service does not guarantee factual accuracy, identity consistency,
+  uniqueness, fitness for a particular purpose, or non-infringement.
+- Generation is asynchronous and may include queueing time.
+- Result links returned by the current hosted preview are temporary.
+- Capabilities, limits, and output characteristics may change as the hosted
+  service is updated.
+
+## Model and training information
+
+The architecture, parameter count, model weights, training code, detailed
+training data composition, and production inference implementation are
+proprietary and are not published in this repository. Evaluation results will
+be added when a public, reproducible evaluation methodology is available.
+
+## License and terms
+
+Superfast Video is closed-weight and proprietary. This repository is an
+informational model card and does not distribute or license model artifacts.
+Access to the hosted service and use of generated outputs are governed by the
+[Yoroll Terms of Use](https://docs.yoroll.ai/yoroll-terms-of-use/en), the
+applicable service plan, and any separately executed agreement.