Add Nuva Lab acknowledgement and link
#1
by whatif-jd - opened
README.md
CHANGED
|
@@ -53,6 +53,10 @@ Run FastH3 Omni on **DGX Spark or RTX 5090 through FastVideo** using the [FastVi
|
|
| 53 |
|
| 54 |
[FP8 weights](https://huggingface.co/FastVideo/FastH3-OmniRef-FP8) are a separate FastVideo variant; the [FP8 recipe for RTX 4090](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_fasth3_omniref_rtx4090.yaml) illustrates the non-FP4 path with layerwise offload and compatible BF16 encoder components. Use each runtime's matching checkpoint format.
|
| 55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
## License
|
| 57 |
|
| 58 |
Use of these weights is governed by the [MiniMax-H3 Community License Agreement](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE).
|
|
|
|
| 53 |
|
| 54 |
[FP8 weights](https://huggingface.co/FastVideo/FastH3-OmniRef-FP8) are a separate FastVideo variant; the [FP8 recipe for RTX 4090](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_fasth3_omniref_rtx4090.yaml) illustrates the non-FP4 path with layerwise offload and compatible BF16 encoder components. Use each runtime's matching checkpoint format.
|
| 55 |
|
| 56 |
+
## Acknowledgements
|
| 57 |
+
|
| 58 |
+
FastH3 Omni was built in close collaboration with [Nuva Lab](https://nuvalab.ai/fasth3/), which co-developed the model with FastVideo, defined and curated the omni reference dataset, and brought production-grounded creative video workflows to FastH3. For dedicated production deployment, fine-tuning on your own data and a creative agent on top, see [Nuva Lab's FastH3-Omni page](https://nuvalab.ai/fasth3/).
|
| 59 |
+
|
| 60 |
## License
|
| 61 |
|
| 62 |
Use of these weights is governed by the [MiniMax-H3 Community License Agreement](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE).
|