Text-to-Video
Wan2.2
English
Chinese
custom
ti2v
text-to-audio-video
audio-video-generation
mmdit
flow-matching
Instructions to use robingg1/NAVA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Wan2.2
How to use robingg1/NAVA with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Upload config.json with huggingface_hub
Browse files- config.json +21 -0
config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"patch_size": [1, 2, 2],
|
| 3 |
+
"model_type": "ti2v",
|
| 4 |
+
"dim": 3072,
|
| 5 |
+
"ffn_dim": 14336,
|
| 6 |
+
"freq_dim": 256,
|
| 7 |
+
"num_heads": 24,
|
| 8 |
+
"num_layers": 30,
|
| 9 |
+
"num_double_layers": 10,
|
| 10 |
+
"num_single_layers": 20,
|
| 11 |
+
"vid_in_dim": 48,
|
| 12 |
+
"vid_out_dim": 48,
|
| 13 |
+
"audio_in_dim": 128,
|
| 14 |
+
"audio_out_dim": 128,
|
| 15 |
+
"text_len": 512,
|
| 16 |
+
"window_size": [-1, -1],
|
| 17 |
+
"qk_norm": true,
|
| 18 |
+
"cross_attn_norm": true,
|
| 19 |
+
"eps": 1e-6,
|
| 20 |
+
"temporal_rope_scaling_factor": 0.24
|
| 21 |
+
}
|