Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ FastHunyuan is an accelerated [HunyuanVideo](https://huggingface.co/tencent/Huny
|
|
| 25 |
|
| 26 |
- Clone [Fastvideo](https://github.com/hao-ai-lab/FastVideo) repository and follow the inference instructions in the README.
|
| 27 |
- Alternatively, you can inference FastHunyuan using the official [Hunyuan Video repository](https://github.com/Tencent/HunyuanVideo) by **setting the shift to 17, steps to 6, resolution to 720X1280X125, and cfg bigger than 6**.
|
| 28 |
-
|
| 29 |
## Training details
|
| 30 |
|
| 31 |
FastHunyuan is consistency distillated on the [MixKit](https://huggingface.co/datasets/LanguageBind/Open-Sora-Plan-v1.1.0/tree/main) dataset with the following hyperparamters:
|
|
|
|
| 25 |
|
| 26 |
- Clone [Fastvideo](https://github.com/hao-ai-lab/FastVideo) repository and follow the inference instructions in the README.
|
| 27 |
- Alternatively, you can inference FastHunyuan using the official [Hunyuan Video repository](https://github.com/Tencent/HunyuanVideo) by **setting the shift to 17, steps to 6, resolution to 720X1280X125, and cfg bigger than 6**.
|
| 28 |
+
We find that a large CFG scale generally leads to faster videos.
|
| 29 |
## Training details
|
| 30 |
|
| 31 |
FastHunyuan is consistency distillated on the [MixKit](https://huggingface.co/datasets/LanguageBind/Open-Sora-Plan-v1.1.0/tree/main) dataset with the following hyperparamters:
|