Spaces:
Build error
Build error
Upload 18 files
Browse files- MacLab-Era3D-512-6view/feature_extractor/preprocessor_config.json +27 -0
- MacLab-Era3D-512-6view/image_encoder/config.json +23 -0
- MacLab-Era3D-512-6view/image_encoder/model.safetensors +3 -0
- MacLab-Era3D-512-6view/image_noising_scheduler/scheduler_config.json +19 -0
- MacLab-Era3D-512-6view/image_normalizer/config.json +6 -0
- MacLab-Era3D-512-6view/image_normalizer/diffusion_pytorch_model.safetensors +3 -0
- MacLab-Era3D-512-6view/model_index.json +40 -0
- MacLab-Era3D-512-6view/scheduler/scheduler_config.json +20 -0
- MacLab-Era3D-512-6view/text_encoder/config.json +25 -0
- MacLab-Era3D-512-6view/text_encoder/model.safetensors +3 -0
- MacLab-Era3D-512-6view/tokenizer/merges.txt +0 -0
- MacLab-Era3D-512-6view/tokenizer/special_tokens_map.json +24 -0
- MacLab-Era3D-512-6view/tokenizer/tokenizer_config.json +38 -0
- MacLab-Era3D-512-6view/tokenizer/vocab.json +0 -0
- MacLab-Era3D-512-6view/unet/config.json +95 -0
- MacLab-Era3D-512-6view/unet/diffusion_pytorch_model.safetensors +3 -0
- MacLab-Era3D-512-6view/vae/config.json +32 -0
- MacLab-Era3D-512-6view/vae/diffusion_pytorch_model.safetensors +3 -0
MacLab-Era3D-512-6view/feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 224,
|
4 |
+
"width": 224
|
5 |
+
},
|
6 |
+
"do_center_crop": true,
|
7 |
+
"do_convert_rgb": true,
|
8 |
+
"do_normalize": true,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"image_mean": [
|
12 |
+
0.48145466,
|
13 |
+
0.4578275,
|
14 |
+
0.40821073
|
15 |
+
],
|
16 |
+
"image_processor_type": "CLIPImageProcessor",
|
17 |
+
"image_std": [
|
18 |
+
0.26862954,
|
19 |
+
0.26130258,
|
20 |
+
0.27577711
|
21 |
+
],
|
22 |
+
"resample": 3,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"shortest_edge": 224
|
26 |
+
}
|
27 |
+
}
|
MacLab-Era3D-512-6view/image_encoder/config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-unclip",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPVisionModelWithProjection"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"dropout": 0.0,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_size": 1280,
|
10 |
+
"image_size": 224,
|
11 |
+
"initializer_factor": 1.0,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5120,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"model_type": "clip_vision_model",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_channels": 3,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"patch_size": 14,
|
20 |
+
"projection_dim": 1024,
|
21 |
+
"torch_dtype": "float16",
|
22 |
+
"transformers_version": "4.37.2"
|
23 |
+
}
|
MacLab-Era3D-512-6view/image_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae616c24393dd1854372b0639e5541666f7521cbe219669255e865cb7f89466a
|
3 |
+
size 1264217240
|
MacLab-Era3D-512-6view/image_noising_scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDPMScheduler",
|
3 |
+
"_diffusers_version": "0.26.0.dev0",
|
4 |
+
"beta_end": 0.02,
|
5 |
+
"beta_schedule": "squaredcos_cap_v2",
|
6 |
+
"beta_start": 0.0001,
|
7 |
+
"clip_sample": true,
|
8 |
+
"clip_sample_range": 1.0,
|
9 |
+
"dynamic_thresholding_ratio": 0.995,
|
10 |
+
"num_train_timesteps": 1000,
|
11 |
+
"prediction_type": "epsilon",
|
12 |
+
"rescale_betas_zero_snr": false,
|
13 |
+
"sample_max_value": 1.0,
|
14 |
+
"steps_offset": 0,
|
15 |
+
"thresholding": false,
|
16 |
+
"timestep_spacing": "leading",
|
17 |
+
"trained_betas": null,
|
18 |
+
"variance_type": "fixed_small"
|
19 |
+
}
|
MacLab-Era3D-512-6view/image_normalizer/config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableUnCLIPImageNormalizer",
|
3 |
+
"_diffusers_version": "0.26.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-unclip",
|
5 |
+
"embedding_dim": 1024
|
6 |
+
}
|
MacLab-Era3D-512-6view/image_normalizer/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7772cf09639cea0c65639a3bfc88004a66d42259090d03fa8e15efdc255f240a
|
3 |
+
size 4272
|
MacLab-Era3D-512-6view/model_index.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableUnCLIPImg2ImgPipeline",
|
3 |
+
"_diffusers_version": "0.26.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
"transformers",
|
6 |
+
"CLIPImageProcessor"
|
7 |
+
],
|
8 |
+
"image_encoder": [
|
9 |
+
"transformers",
|
10 |
+
"CLIPVisionModelWithProjection"
|
11 |
+
],
|
12 |
+
"image_noising_scheduler": [
|
13 |
+
"diffusers",
|
14 |
+
"DDPMScheduler"
|
15 |
+
],
|
16 |
+
"image_normalizer": [
|
17 |
+
"stable_diffusion",
|
18 |
+
"StableUnCLIPImageNormalizer"
|
19 |
+
],
|
20 |
+
"scheduler": [
|
21 |
+
"diffusers",
|
22 |
+
"DDIMScheduler"
|
23 |
+
],
|
24 |
+
"text_encoder": [
|
25 |
+
"transformers",
|
26 |
+
"CLIPTextModel"
|
27 |
+
],
|
28 |
+
"tokenizer": [
|
29 |
+
"transformers",
|
30 |
+
"CLIPTokenizer"
|
31 |
+
],
|
32 |
+
"unet": [
|
33 |
+
"mvdiffusion.models.unet_mv2d_condition",
|
34 |
+
"UNetMV2DConditionModel"
|
35 |
+
],
|
36 |
+
"vae": [
|
37 |
+
"diffusers",
|
38 |
+
"AutoencoderKL"
|
39 |
+
]
|
40 |
+
}
|
MacLab-Era3D-512-6view/scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDIMScheduler",
|
3 |
+
"_diffusers_version": "0.26.0.dev0",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"clip_sample": false,
|
8 |
+
"clip_sample_range": 1.0,
|
9 |
+
"dynamic_thresholding_ratio": 0.995,
|
10 |
+
"num_train_timesteps": 1000,
|
11 |
+
"prediction_type": "v_prediction",
|
12 |
+
"rescale_betas_zero_snr": false,
|
13 |
+
"sample_max_value": 1.0,
|
14 |
+
"set_alpha_to_one": false,
|
15 |
+
"skip_prk_steps": true,
|
16 |
+
"steps_offset": 1,
|
17 |
+
"thresholding": false,
|
18 |
+
"timestep_spacing": "leading",
|
19 |
+
"trained_betas": null
|
20 |
+
}
|
MacLab-Era3D-512-6view/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-unclip",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModel"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 23,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.37.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
MacLab-Era3D-512-6view/text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc1827c465450322616f06dea41596eac7d493f4e95904dcb51f0fc745c4e13f
|
3 |
+
size 680820392
|
MacLab-Era3D-512-6view/tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
MacLab-Era3D-512-6view/tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "!",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
MacLab-Era3D-512-6view/tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "!",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"49406": {
|
13 |
+
"content": "<|startoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"49407": {
|
21 |
+
"content": "<|endoftext|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"bos_token": "<|startoftext|>",
|
30 |
+
"clean_up_tokenization_spaces": true,
|
31 |
+
"do_lower_case": true,
|
32 |
+
"eos_token": "<|endoftext|>",
|
33 |
+
"errors": "replace",
|
34 |
+
"model_max_length": 77,
|
35 |
+
"pad_token": "!",
|
36 |
+
"tokenizer_class": "CLIPTokenizer",
|
37 |
+
"unk_token": "<|endoftext|>"
|
38 |
+
}
|
MacLab-Era3D-512-6view/tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
MacLab-Era3D-512-6view/unet/config.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNetMV2DConditionModel",
|
3 |
+
"_diffusers_version": "0.26.0.dev0",
|
4 |
+
"_name_or_path": "../checkpoint_backup/output/unit-unclip-512-6view-randomele-self+row-8w-selfcd-rowmv-2block-linear-depthfilter-step-removewh-bs256-three/checkpoint-40000/unet_ema",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_channels": [
|
7 |
+
1280,
|
8 |
+
1280,
|
9 |
+
1280
|
10 |
+
],
|
11 |
+
"addition_downsample": false,
|
12 |
+
"addition_embed_type": null,
|
13 |
+
"addition_embed_type_num_heads": 64,
|
14 |
+
"addition_time_embed_dim": null,
|
15 |
+
"attention_head_dim": [
|
16 |
+
5,
|
17 |
+
10,
|
18 |
+
20,
|
19 |
+
20
|
20 |
+
],
|
21 |
+
"block_out_channels": [
|
22 |
+
320,
|
23 |
+
640,
|
24 |
+
1280,
|
25 |
+
1280
|
26 |
+
],
|
27 |
+
"cd_attention_last": false,
|
28 |
+
"cd_attention_mid": false,
|
29 |
+
"center_input_sample": false,
|
30 |
+
"class_embed_type": "projection",
|
31 |
+
"class_embeddings_concat": false,
|
32 |
+
"conv_in_kernel": 3,
|
33 |
+
"conv_out_kernel": 3,
|
34 |
+
"cross_attention_dim": 1024,
|
35 |
+
"cross_attention_norm": null,
|
36 |
+
"decay": 0.9999,
|
37 |
+
"down_block_types": [
|
38 |
+
"CrossAttnDownBlockMV2D",
|
39 |
+
"CrossAttnDownBlockMV2D",
|
40 |
+
"CrossAttnDownBlockMV2D",
|
41 |
+
"DownBlock2D"
|
42 |
+
],
|
43 |
+
"downsample_padding": 1,
|
44 |
+
"dual_cross_attention": false,
|
45 |
+
"encoder_hid_dim": null,
|
46 |
+
"encoder_hid_dim_type": null,
|
47 |
+
"flip_sin_to_cos": true,
|
48 |
+
"freq_shift": 0,
|
49 |
+
"in_channels": 8,
|
50 |
+
"inv_gamma": 1.0,
|
51 |
+
"layers_per_block": 2,
|
52 |
+
"mid_block_only_cross_attention": null,
|
53 |
+
"mid_block_scale_factor": 1,
|
54 |
+
"mid_block_type": "UNetMidBlockMV2DCrossAttn",
|
55 |
+
"min_decay": 0.0,
|
56 |
+
"multiview_attention": true,
|
57 |
+
"mvcd_attention": true,
|
58 |
+
"norm_eps": 1e-05,
|
59 |
+
"norm_num_groups": 32,
|
60 |
+
"num_attention_heads": null,
|
61 |
+
"num_class_embeds": null,
|
62 |
+
"num_regress_blocks": 3,
|
63 |
+
"num_views": 6,
|
64 |
+
"only_cross_attention": false,
|
65 |
+
"optimization_step": 40000,
|
66 |
+
"out_channels": 4,
|
67 |
+
"power": 0.6666666666666666,
|
68 |
+
"projection_camera_embeddings_input_dim": 4,
|
69 |
+
"projection_class_embeddings_input_dim": 2048,
|
70 |
+
"regress_elevation": true,
|
71 |
+
"regress_focal_length": true,
|
72 |
+
"resnet_out_scale_factor": 1.0,
|
73 |
+
"resnet_skip_time_act": false,
|
74 |
+
"resnet_time_scale_shift": "default",
|
75 |
+
"sample_size": 64,
|
76 |
+
"selfattn_block": "self_rowwise",
|
77 |
+
"sparse_mv_attention": true,
|
78 |
+
"time_cond_proj_dim": null,
|
79 |
+
"time_embedding_act_fn": null,
|
80 |
+
"time_embedding_dim": null,
|
81 |
+
"time_embedding_type": "positional",
|
82 |
+
"timestep_post_act": null,
|
83 |
+
"transformer_layers_per_block": 1,
|
84 |
+
"up_block_types": [
|
85 |
+
"UpBlock2D",
|
86 |
+
"CrossAttnUpBlockMV2D",
|
87 |
+
"CrossAttnUpBlockMV2D",
|
88 |
+
"CrossAttnUpBlockMV2D"
|
89 |
+
],
|
90 |
+
"upcast_attention": true,
|
91 |
+
"update_after_step": 0,
|
92 |
+
"use_dino": false,
|
93 |
+
"use_ema_warmup": false,
|
94 |
+
"use_linear_projection": true
|
95 |
+
}
|
MacLab-Era3D-512-6view/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af12a68fdbfa51bb857422b42bd5ac5101467e22e5e58ea6d8b06dd9426c93af
|
3 |
+
size 1895432652
|
MacLab-Era3D-512-6view/vae/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.26.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1-unclip",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"block_out_channels": [
|
7 |
+
128,
|
8 |
+
256,
|
9 |
+
512,
|
10 |
+
512
|
11 |
+
],
|
12 |
+
"down_block_types": [
|
13 |
+
"DownEncoderBlock2D",
|
14 |
+
"DownEncoderBlock2D",
|
15 |
+
"DownEncoderBlock2D",
|
16 |
+
"DownEncoderBlock2D"
|
17 |
+
],
|
18 |
+
"force_upcast": true,
|
19 |
+
"in_channels": 3,
|
20 |
+
"latent_channels": 4,
|
21 |
+
"layers_per_block": 2,
|
22 |
+
"norm_num_groups": 32,
|
23 |
+
"out_channels": 3,
|
24 |
+
"sample_size": 768,
|
25 |
+
"scaling_factor": 0.18215,
|
26 |
+
"up_block_types": [
|
27 |
+
"UpDecoderBlock2D",
|
28 |
+
"UpDecoderBlock2D",
|
29 |
+
"UpDecoderBlock2D",
|
30 |
+
"UpDecoderBlock2D"
|
31 |
+
]
|
32 |
+
}
|
MacLab-Era3D-512-6view/vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
|
3 |
+
size 167335342
|