Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ tags:
|
|
| 9 |
**Hunyuan supports Lora fine-tuning of videos up to 720p. Detailed finetuning instructions are available in our GitHub repository.**
|
| 10 |
|
| 11 |
You can easily perform inference using the LoRA weights in our [FastVideo](https://github.com/hao-ai-lab/FastVideo) repository, supporting both single and multi-GPU configurations.
|
| 12 |
-
Our training dataset consists solely of Wukong videos and can be accessed [here](https://huggingface.co/datasets/FastVideo/Black-Myth-Wukong)
|
| 13 |
# Black-Myth-Wukong
|
| 14 |
|
| 15 |
<div style="display: flex; flex-direction: column; gap: 16px;">
|
|
@@ -68,7 +68,7 @@ Our training dataset consists solely of Wukong videos and can be accessed [here]
|
|
| 68 |
- rank: 32
|
| 69 |
- alpha: 32
|
| 70 |
- batch size: 1
|
| 71 |
-
- gradient accumulation steps:
|
| 72 |
|
| 73 |
## Acknowledgment:
|
| 74 |
|
|
|
|
| 9 |
**Hunyuan supports Lora fine-tuning of videos up to 720p. Detailed finetuning instructions are available in our GitHub repository.**
|
| 10 |
|
| 11 |
You can easily perform inference using the LoRA weights in our [FastVideo](https://github.com/hao-ai-lab/FastVideo) repository, supporting both single and multi-GPU configurations.
|
| 12 |
+
Our training dataset consists solely of Wukong videos and can be accessed [here](https://huggingface.co/datasets/FastVideo/Black-Myth-Wukong-720p)
|
| 13 |
# Black-Myth-Wukong
|
| 14 |
|
| 15 |
<div style="display: flex; flex-direction: column; gap: 16px;">
|
|
|
|
| 68 |
- rank: 32
|
| 69 |
- alpha: 32
|
| 70 |
- batch size: 1
|
| 71 |
+
- gradient accumulation steps: 2
|
| 72 |
|
| 73 |
## Acknowledgment:
|
| 74 |
|