Update README.md
Browse files
README.md
CHANGED
@@ -19,8 +19,8 @@ license: apache-2.0
|
|
19 |
|
20 |
## Model Overview
|
21 |
|
22 |
-
- 3-step inference is supported and achieves up to **
|
23 |
-
- Our model is trained on **
|
24 |
- Finetuning and inference scripts are available in the [FastVideo](https://github.com/hao-ai-lab/FastVideo) repository:
|
25 |
- [1 Node/GPU debugging finetuning script](https://github.com/hao-ai-lab/FastVideo/blob/main/scripts/distill/v1_distill_dmd_wan_VSA.sh)
|
26 |
- [Slurm training example script](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/distill/Wan2.1-T2V/Wan-Syn-Data-480P/distill_dmd_VSA_t2v_1.3B.slurm)
|
|
|
19 |
|
20 |
## Model Overview
|
21 |
|
22 |
+
- 3-step inference is supported and achieves up to **50x** speed up for denoising loop on a single **H100** GPU.
|
23 |
+
- Our model is trained on **121×704×1280** resolution, but it supports generating videos with **any resolution**.(quality may degrade)
|
24 |
- Finetuning and inference scripts are available in the [FastVideo](https://github.com/hao-ai-lab/FastVideo) repository:
|
25 |
- [1 Node/GPU debugging finetuning script](https://github.com/hao-ai-lab/FastVideo/blob/main/scripts/distill/v1_distill_dmd_wan_VSA.sh)
|
26 |
- [Slurm training example script](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/distill/Wan2.1-T2V/Wan-Syn-Data-480P/distill_dmd_VSA_t2v_1.3B.slurm)
|