Hugging Face's logo

TencentARC
/
GeometryCrafter

GeometryCrafter
Diffusers
Safetensors
English
video-to-3d
point-cloud
Model card Files
xet
Community
2
wbhu-tc commited on
Commit
c52bee1
·
verified ·
1 Parent(s): 658d54b

Upload 6 files

Browse files
Files changed (6) hide show
  1. point_map_vae/config.json +29 -0
  2. point_map_vae/diffusion_pytorch_model.safetensors +3 -0
  3. unet_determ/config.json +38 -0
  4. unet_determ/diffusion_pytorch_model.safetensors +3 -0
  5. unet_diff/config.json +38 -0
  6. unet_diff/diffusion_pytorch_model.safetensors +3 -0
point_map_vae/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PMapAutoencoderKLTemporalDecoder",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "/dockerdata/workspace/pmap_vae_hybrid_synthetic_image_320_640_train_fp32_l_patch/checkpoint-40000/",
5
+ "dec_block_out_channels": [
6
+ 128,
7
+ 256,
8
+ 512,
9
+ 512
10
+ ],
11
+ "dec_layers_per_block": 2,
12
+ "enc_block_out_channels": [
13
+ 128,
14
+ 256,
15
+ 512,
16
+ 512
17
+ ],
18
+ "enc_down_block_types": [
19
+ "DownEncoderBlock2D",
20
+ "DownEncoderBlock2D",
21
+ "DownEncoderBlock2D",
22
+ "DownEncoderBlock2D"
23
+ ],
24
+ "enc_layers_per_block": 2,
25
+ "in_channels": 4,
26
+ "latent_channels": 4,
27
+ "mid_block_add_attention": true,
28
+ "offset_scale_factor": 0.1
29
+ }
point_map_vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23071fc3a10cc8a3188b7874566eb07c571d645f658afdcaab229a39edb39329
3
+ size 393019424
unet_determ/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNetSpatioTemporalConditionModelVid2vid",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "/dockerdata/workspace/unet_determ_pmap_vae_320x640_1-25_seq_norm_hybrid_synthetic_video/checkpoint-40000",
5
+ "addition_time_embed_dim": 256,
6
+ "block_out_channels": [
7
+ 320,
8
+ 640,
9
+ 1280,
10
+ 1280
11
+ ],
12
+ "cross_attention_dim": 1024,
13
+ "down_block_types": [
14
+ "CrossAttnDownBlockSpatioTemporal",
15
+ "CrossAttnDownBlockSpatioTemporal",
16
+ "CrossAttnDownBlockSpatioTemporal",
17
+ "DownBlockSpatioTemporal"
18
+ ],
19
+ "in_channels": 8,
20
+ "layers_per_block": 2,
21
+ "num_attention_heads": [
22
+ 5,
23
+ 10,
24
+ 20,
25
+ 20
26
+ ],
27
+ "num_frames": 25,
28
+ "out_channels": 4,
29
+ "projection_class_embeddings_input_dim": 768,
30
+ "sample_size": 96,
31
+ "transformer_layers_per_block": 1,
32
+ "up_block_types": [
33
+ "UpBlockSpatioTemporal",
34
+ "CrossAttnUpBlockSpatioTemporal",
35
+ "CrossAttnUpBlockSpatioTemporal",
36
+ "CrossAttnUpBlockSpatioTemporal"
37
+ ]
38
+ }
unet_determ/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:964b2139ac933d2bc170aeebd8c10df1af52f24db236b08a6674b979af7b0d54
3
+ size 3049435868
unet_diff/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNetSpatioTemporalConditionModelVid2vid",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "/dockerdata/workspace/unet_diff_pmap_vae_320x640_1-25_seq_norm_hybrid_synthetic_video/checkpoint-40000",
5
+ "addition_time_embed_dim": 256,
6
+ "block_out_channels": [
7
+ 320,
8
+ 640,
9
+ 1280,
10
+ 1280
11
+ ],
12
+ "cross_attention_dim": 1024,
13
+ "down_block_types": [
14
+ "CrossAttnDownBlockSpatioTemporal",
15
+ "CrossAttnDownBlockSpatioTemporal",
16
+ "CrossAttnDownBlockSpatioTemporal",
17
+ "DownBlockSpatioTemporal"
18
+ ],
19
+ "in_channels": 12,
20
+ "layers_per_block": 2,
21
+ "num_attention_heads": [
22
+ 5,
23
+ 10,
24
+ 20,
25
+ 20
26
+ ],
27
+ "num_frames": 25,
28
+ "out_channels": 4,
29
+ "projection_class_embeddings_input_dim": 768,
30
+ "sample_size": 96,
31
+ "transformer_layers_per_block": 1,
32
+ "up_block_types": [
33
+ "UpBlockSpatioTemporal",
34
+ "CrossAttnUpBlockSpatioTemporal",
35
+ "CrossAttnUpBlockSpatioTemporal",
36
+ "CrossAttnUpBlockSpatioTemporal"
37
+ ]
38
+ }
unet_diff/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcd251cde74f53f1ee028c38979651ca138aa63ce7ce4aa77a03e29ad969f5e
3
+ size 3049458908