Instructions to use H-oliday/SwiftVR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use H-oliday/SwiftVR with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("H-oliday/SwiftVR", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
#3
by chxy95 - opened
README.md
CHANGED
|
@@ -1,7 +1,9 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
-
|
|
|
|
| 4 |
library_name: diffusers
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
<h1 align="center">SwiftVR: Real-Time One-Step Generative Video Restoration</h1>
|
|
@@ -182,18 +184,49 @@ Use `--png` to write a PNG sequence.
|
|
| 182 |
SwiftVR builds on [Wan2.2-TI2V-5B](https://github.com/Wan-Video), the lightweight autoencoder [TAEHV](https://github.com/madebyollin/taehv), and the [RealBasicVSR](https://github.com/ckkelvinchan/RealBasicVSR) degradation pipeline. We thank the authors of [DOVE](https://github.com/zhengchen1999/DOVE), [SeedVR2](https://github.com/ByteDance-Seed/SeedVR), and [FlashVSR](https://github.com/OpenImagingLab/FlashVSR) for releasing strong baselines, and the [UltraVideo](https://github.com/Tele-AI/UltraVideo) team for the training corpus.
|
| 183 |
|
| 184 |
|
| 185 |
-
|
| 186 |
## ๐ License
|
| 187 |
|
| 188 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 189 |
|
| 190 |
-
|
|
|
|
| 191 |
|
| 192 |
-
|
| 193 |
|
| 194 |
-
|
|
|
|
|
|
|
| 195 |
|
| 196 |
-
Unless required by applicable law or agreed to in writing, this project is distributed on an **"AS IS" BASIS**, without warranties or conditions of any kind, either express or implied. See the [LICENSE](./LICENSE) file for the full license text.
|
| 197 |
|
| 198 |
## ๐ Citation
|
| 199 |
|
|
@@ -211,4 +244,4 @@ Unless required by applicable law or agreed to in writing, this project is distr
|
|
| 211 |
|
| 212 |
If you have any questions, feel free to reach out:
|
| 213 |
|
| 214 |
-
* Email:
|
|
|
|
| 1 |
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: swiftvr-research-license
|
| 4 |
+
license_link: LICENSE
|
| 5 |
library_name: diffusers
|
| 6 |
+
pipeline_tag: video-to-video
|
| 7 |
---
|
| 8 |
|
| 9 |
<h1 align="center">SwiftVR: Real-Time One-Step Generative Video Restoration</h1>
|
|
|
|
| 184 |
SwiftVR builds on [Wan2.2-TI2V-5B](https://github.com/Wan-Video), the lightweight autoencoder [TAEHV](https://github.com/madebyollin/taehv), and the [RealBasicVSR](https://github.com/ckkelvinchan/RealBasicVSR) degradation pipeline. We thank the authors of [DOVE](https://github.com/zhengchen1999/DOVE), [SeedVR2](https://github.com/ByteDance-Seed/SeedVR), and [FlashVSR](https://github.com/OpenImagingLab/FlashVSR) for releasing strong baselines, and the [UltraVideo](https://github.com/Tele-AI/UltraVideo) team for the training corpus.
|
| 185 |
|
| 186 |
|
|
|
|
| 187 |
## ๐ License
|
| 188 |
|
| 189 |
+
The model weights in this repository are licensed under the
|
| 190 |
+
**SwiftVR Research License**. See the [LICENSE](./LICENSE) file.
|
| 191 |
+
|
| 192 |
+
### Permitted without separate authorization
|
| 193 |
+
|
| 194 |
+
- Non-commercial academic research;
|
| 195 |
+
- Personal non-commercial research;
|
| 196 |
+
- Teaching and education;
|
| 197 |
+
- Reproduction of academic results;
|
| 198 |
+
- Internal evaluation for determining whether to request a commercial
|
| 199 |
+
license.
|
| 200 |
+
|
| 201 |
+
### Prior written authorization required
|
| 202 |
+
|
| 203 |
+
- Use in a commercial product or service;
|
| 204 |
+
- Production deployment;
|
| 205 |
+
- Customer-facing use;
|
| 206 |
+
- Paid API, SaaS, cloud, or hosted services;
|
| 207 |
+
- Paid consulting or contract work;
|
| 208 |
+
- Processing videos on behalf of customers;
|
| 209 |
+
- Commercial redistribution of the model or modified versions;
|
| 210 |
+
- Use primarily intended to generate revenue or commercial advantage.
|
| 211 |
+
|
| 212 |
+
Repository access, model download, email acknowledgement, or informal
|
| 213 |
+
communication does not constitute commercial authorization.
|
| 214 |
+
|
| 215 |
+
For commercial licensing inquiries, contact:
|
| 216 |
+
|
| 217 |
+
- Email: kakibluee@gmail.com or chxy95@gmail.com
|
| 218 |
+
|
| 219 |
+
### Source code
|
| 220 |
|
| 221 |
+
The corresponding SwiftVR source code is separately licensed under
|
| 222 |
+
the Apache License 2.0 in the GitHub repository.
|
| 223 |
|
| 224 |
+
### Historical releases
|
| 225 |
|
| 226 |
+
Historical model versions previously released under the Apache License
|
| 227 |
+
2.0 remain subject to that license. This license does not retroactively
|
| 228 |
+
revoke rights validly granted for those historical versions.
|
| 229 |
|
|
|
|
| 230 |
|
| 231 |
## ๐ Citation
|
| 232 |
|
|
|
|
| 244 |
|
| 245 |
If you have any questions, feel free to reach out:
|
| 246 |
|
| 247 |
+
* Email: kakibluee@gmail.com or chxy95@gmail.com
|