Hugging Face's logo

Miayan
/
project

Diffusers
Safetensors
Model card Files
xet
 Community
Miayan commited on
Commit
5cb71a9
·
verified ·
1 Parent(s): 454fd35

Add checkpoint for train_ex8_11

Browse files
Files changed (11) hide show
  1. train_ex8_11/checkpoint-235260/albedo_estimator/config.json +18 -0
  2. train_ex8_11/checkpoint-235260/albedo_estimator/diffusion_pytorch_model.safetensors +3 -0
  3. train_ex8_11/checkpoint-235260/controlnet/config.json +57 -0
  4. train_ex8_11/checkpoint-235260/controlnet/diffusion_pytorch_model.safetensors +3 -0
  5. train_ex8_11/checkpoint-235260/custom_encoder/config.json +10 -0
  6. train_ex8_11/checkpoint-235260/custom_encoder/diffusion_pytorch_model.safetensors +3 -0
  7. train_ex8_11/checkpoint-235260/custom_unet.pth +3 -0
  8. train_ex8_11/checkpoint-235260/optimizer.bin +3 -0
  9. train_ex8_11/checkpoint-235260/random_states_0.pkl +3 -0
  10. train_ex8_11/checkpoint-235260/scheduler.bin +3 -0
  11. train_ex8_11/config.yaml +140 -0
train_ex8_11/checkpoint-235260/albedo_estimator/config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AlbedoWrapper",
3
+ "_diffusers_version": "0.33.1",
4
+ "_name_or_path": "train_ex8_11/checkpoint-65000",
5
+ "cfg": {
6
+ "enabled": true,
7
+ "frozen_components": [
8
+ "ord_model",
9
+ "iid_model",
10
+ "col_model"
11
+ ],
12
+ "load_stage": 3,
13
+ "trainable_components": [
14
+ "alb_model"
15
+ ],
16
+ "version": "v2"
17
+ }
18
+ }
train_ex8_11/checkpoint-235260/albedo_estimator/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7fe3bdd8de36ef717b3eb2d1e5bf625c588333ec083836e3a75491332723440
3
+ size 422422660
train_ex8_11/checkpoint-235260/controlnet/config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.33.1",
4
+ "_name_or_path": "train_ex8_11/checkpoint-65000",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280,
19
+ 1280
20
+ ],
21
+ "class_embed_type": null,
22
+ "conditioning_channels": 6,
23
+ "conditioning_embedding_out_channels": [
24
+ 16,
25
+ 32,
26
+ 96,
27
+ 256
28
+ ],
29
+ "controlnet_conditioning_channel_order": "rgb",
30
+ "cross_attention_dim": 1024,
31
+ "down_block_types": [
32
+ "CrossAttnDownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "CrossAttnDownBlock2D",
35
+ "DownBlock2D"
36
+ ],
37
+ "downsample_padding": 1,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "global_pool_conditions": false,
43
+ "in_channels": 4,
44
+ "layers_per_block": 2,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "projection_class_embeddings_input_dim": null,
53
+ "resnet_time_scale_shift": "default",
54
+ "transformer_layers_per_block": 1,
55
+ "upcast_attention": true,
56
+ "use_linear_projection": true
57
+ }
train_ex8_11/checkpoint-235260/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:434e14b644aa4093fc598bb10bbf89092be7dd18c3d61c95c9ced637112f7190
3
+ size 1461729992
train_ex8_11/checkpoint-235260/custom_encoder/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Ba": 4,
3
+ "Bc": 4,
4
+ "Bi": 4,
5
+ "K": 4,
6
+ "_class_name": "CustomEncoder",
7
+ "_diffusers_version": "0.33.1",
8
+ "_name_or_path": "train_ex8_11/checkpoint-65000",
9
+ "cross_dim": 1024
10
+ }
train_ex8_11/checkpoint-235260/custom_encoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a944959b9092d55c1bc21924708d175a5a1178da09e435df83ac4dc0264ee02b
3
+ size 4541016
train_ex8_11/checkpoint-235260/custom_unet.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770a62e012b2bbf384427e6e50765cbdbdcaeadf2390341f03062a1d510eded3
3
+ size 3463973299
train_ex8_11/checkpoint-235260/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e1310f804aa8460ff3ae6e8148bde532916fa4527d8705718e1381a9fc978
3
+ size 6407500783
train_ex8_11/checkpoint-235260/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa00770d49ee1c0457d2b588efce473d7b239a5d947d49a9f29ea31d0225c04a
3
+ size 14821
train_ex8_11/checkpoint-235260/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f2bf6325ce12a3caa925c7153dfb341055dbe7f64dae17474e39c554ccc0f5f
3
+ size 1401
train_ex8_11/config.yaml ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ experiment:
2
+ project_name: relighting_indoors
3
+ output_dir: train_ex8_11
4
+ logging_dir: logs
5
+ report_to: tensorboard
6
+ model:
7
+ pretrained_model_name_or_path: /mnt/HDD3/miayan/paper/envs/huggingface_cache/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6
8
+ revision: null
9
+ variant: null
10
+ tokenizer_name: null
11
+ hf_repo_id: Miayan/project
12
+ hf_version: null
13
+ pretrain_unet_path: scribblelight_controlnet/checkpoint-10000
14
+ resume_from_checkpoint: latest
15
+ enable_ambient_cond: true
16
+ light_encoder:
17
+ cross_dim: 768
18
+ K: 4
19
+ Bi: 4
20
+ Bc: 4
21
+ Ba: 4
22
+ albedo_estimator:
23
+ enabled: true
24
+ version: v2
25
+ load_stage: 3
26
+ frozen_components:
27
+ - ord_model
28
+ - iid_model
29
+ - col_model
30
+ trainable_components:
31
+ - alb_model
32
+ data:
33
+ dataset_cache_dir: /mnt/HDD3/miayan/paper/relighting_datasets/
34
+ data_hf_repo_id: Miayan/physical-relighting-dataset
35
+ data_split: test
36
+ resolution: 512
37
+ dataloader_num_workers: 0
38
+ condition_mode: lightmap_normal
39
+ relighting_impl: gemini_amb
40
+ use_ambient_in_controlnet: false
41
+ colors:
42
+ - - 255
43
+ - 255
44
+ - 255
45
+ - - 255
46
+ - 0
47
+ - 0
48
+ - - 0
49
+ - 255
50
+ - 0
51
+ - - 0
52
+ - 0
53
+ - 255
54
+ - - 255
55
+ - 255
56
+ - 0
57
+ - - 255
58
+ - 165
59
+ - 0
60
+ - - 128
61
+ - 0
62
+ - 128
63
+ - - 255
64
+ - 192
65
+ - 203
66
+ - - 0
67
+ - 255
68
+ - 255
69
+ - - 255
70
+ - 0
71
+ - 255
72
+ intensities:
73
+ - 0.0
74
+ - 0.1
75
+ - 0.2
76
+ - 0.4
77
+ - 0.7
78
+ - 1.0
79
+ training:
80
+ batch_size: 1
81
+ num_epochs: 20
82
+ max_train_steps: null
83
+ max_train_samples: null
84
+ seed: 42
85
+ mixed_precision: 'no'
86
+ allow_tf32: true
87
+ gradient_accumulation_steps: 1
88
+ checkpointing_steps: 5000
89
+ checkpoints_total_limit: 5
90
+ learning_rate: 5.0e-06
91
+ scale_lr: false
92
+ lr_scheduler: constant
93
+ lr_warmup_steps: 500
94
+ adam_beta1: 0.9
95
+ adam_beta2: 0.999
96
+ adam_weight_decay: 0.01
97
+ adam_epsilon: 1.0e-08
98
+ max_grad_norm: 1.0
99
+ use_8bit_adam: false
100
+ set_grads_to_none: false
101
+ losses:
102
+ phys_loss:
103
+ enabled: true
104
+ weight: 1.0
105
+ latent_loss:
106
+ enabled: true
107
+ weight: 1.0
108
+ image_loss:
109
+ enabled: true
110
+ weight: 1.0
111
+ area_loss:
112
+ enabled: false
113
+ weight: 10.0
114
+ intensity_loss:
115
+ enabled: false
116
+ weight: 1.0
117
+ recon_loss:
118
+ enabled: false
119
+ weight: 1.0
120
+ keep_aux_models_on_gpu: true
121
+ sup_structure_loss:
122
+ enabled: true
123
+ weight: 1.0
124
+ enable_decay: true
125
+ start_weight: 1.0
126
+ end_weight: 0.1
127
+ decay_steps: 5000
128
+ self_recon_loss:
129
+ enabled: true
130
+ mode: teacher
131
+ weight: 2.0
132
+ affine_alignment: true
133
+ epsilon: 0.05
134
+ staging:
135
+ switch_epoch: 5
136
+ stage1_weight: 2.0
137
+ stage2_weight: 0.5
138
+ consistency_loss:
139
+ enabled: true
140
+ weight: 1.0