Upload folder using huggingface_hub
Browse files- config.json +58 -0
- diffusion_pytorch_model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"num_attention_heads": 48,
|
| 3 |
+
"attention_head_dim": 64,
|
| 4 |
+
"vae_channels": 16,
|
| 5 |
+
"in_channels": 6,
|
| 6 |
+
"downscale_coef": 8,
|
| 7 |
+
"flip_sin_to_cos": true,
|
| 8 |
+
"freq_shift": 0,
|
| 9 |
+
"time_embed_dim": 512,
|
| 10 |
+
"num_layers": 8,
|
| 11 |
+
"dropout": 0.0,
|
| 12 |
+
"attention_bias": true,
|
| 13 |
+
"sample_width": 90,
|
| 14 |
+
"sample_height": 60,
|
| 15 |
+
"sample_frames": 49,
|
| 16 |
+
"patch_size": 2,
|
| 17 |
+
"temporal_compression_ratio": 4,
|
| 18 |
+
"max_text_seq_length": 226,
|
| 19 |
+
"activation_fn": "gelu-approximate",
|
| 20 |
+
"timestep_activation_fn": "silu",
|
| 21 |
+
"norm_elementwise_affine": true,
|
| 22 |
+
"norm_eps": 1e-05,
|
| 23 |
+
"spatial_interpolation_scale": 1.875,
|
| 24 |
+
"temporal_interpolation_scale": 1.0,
|
| 25 |
+
"use_rotary_positional_embeddings": false,
|
| 26 |
+
"use_learned_positional_embeddings": false,
|
| 27 |
+
"out_proj_dim": 3072,
|
| 28 |
+
"out_proj_dim_zero_init": true,
|
| 29 |
+
"camera_scale_fourier_bands": 6,
|
| 30 |
+
"camera_scale_fourier_min_freq": 1.0,
|
| 31 |
+
"camera_scale_fourier_max_freq": 64.0,
|
| 32 |
+
"camera_scale_embed_dim": null,
|
| 33 |
+
"_use_default_values": [
|
| 34 |
+
"timestep_activation_fn",
|
| 35 |
+
"activation_fn",
|
| 36 |
+
"spatial_interpolation_scale",
|
| 37 |
+
"dropout",
|
| 38 |
+
"use_rotary_positional_embeddings",
|
| 39 |
+
"temporal_interpolation_scale",
|
| 40 |
+
"sample_width",
|
| 41 |
+
"max_text_seq_length",
|
| 42 |
+
"camera_scale_embed_dim",
|
| 43 |
+
"norm_elementwise_affine",
|
| 44 |
+
"flip_sin_to_cos",
|
| 45 |
+
"norm_eps",
|
| 46 |
+
"camera_scale_fourier_bands",
|
| 47 |
+
"temporal_compression_ratio",
|
| 48 |
+
"freq_shift",
|
| 49 |
+
"camera_scale_fourier_max_freq",
|
| 50 |
+
"patch_size",
|
| 51 |
+
"use_learned_positional_embeddings",
|
| 52 |
+
"sample_frames",
|
| 53 |
+
"attention_bias",
|
| 54 |
+
"time_embed_dim",
|
| 55 |
+
"camera_scale_fourier_min_freq",
|
| 56 |
+
"sample_height"
|
| 57 |
+
]
|
| 58 |
+
}
|
diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17f219ca8ef2fc16ed1984e240a7caa5612581e2846eaff41509c4296a60faca
|
| 3 |
+
size 4671709240
|