model upload
Browse files- config.json +34 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"camera_head": true,
|
| 3 |
+
"decode_chunk_size": 128,
|
| 4 |
+
"decoder_depth": 2,
|
| 5 |
+
"decoder_embed_dim": 384,
|
| 6 |
+
"decoder_head_type": "linear",
|
| 7 |
+
"decoder_init_values": null,
|
| 8 |
+
"decoder_num_heads": 6,
|
| 9 |
+
"depth_decoder_depth": null,
|
| 10 |
+
"depth_decoder_embed_dim": null,
|
| 11 |
+
"depth_decoder_num_heads": null,
|
| 12 |
+
"depth_head_type": "conv",
|
| 13 |
+
"drop_path": 0.1,
|
| 14 |
+
"embed_dim": 768,
|
| 15 |
+
"gradient_checkpointing_config": null,
|
| 16 |
+
"img_size": 504,
|
| 17 |
+
"inference_steps": 12,
|
| 18 |
+
"k_sampler_beta_a": 2,
|
| 19 |
+
"k_sampler_beta_b": 1,
|
| 20 |
+
"k_sampling": "linspace",
|
| 21 |
+
"load_patch_embed_weights": false,
|
| 22 |
+
"min_steps": 8,
|
| 23 |
+
"mlp_ratio": 4.0,
|
| 24 |
+
"num_heads": 12,
|
| 25 |
+
"num_register_tokens": 4,
|
| 26 |
+
"num_steps": 16,
|
| 27 |
+
"patch_embed": "dinov2_vitb14_reg",
|
| 28 |
+
"patch_size": 14,
|
| 29 |
+
"recurrence_mode": "gated",
|
| 30 |
+
"stochastic_depth": 0.3,
|
| 31 |
+
"stochastic_depth_mode": "random",
|
| 32 |
+
"sync_stochastic_depth": true,
|
| 33 |
+
"time_conditioning": "interval"
|
| 34 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87aac651e77e381eea02c40c14985d196edfb0d4a1c2d4197acb50ef18776eb5
|
| 3 |
+
size 468367852
|