Hugging Face's logo

Miayan
/
project

Diffusers
Safetensors
Model card Files
xet
 Community
Miayan commited on
Commit
05f2d72
·
verified ·
1 Parent(s): 5cb71a9

Add checkpoint for train_ex8_12

Browse files
Files changed (11) hide show
  1. train_ex8_12/checkpoint-235260/albedo_estimator/config.json +17 -0
  2. train_ex8_12/checkpoint-235260/albedo_estimator/diffusion_pytorch_model.safetensors +3 -0
  3. train_ex8_12/checkpoint-235260/controlnet/config.json +56 -0
  4. train_ex8_12/checkpoint-235260/controlnet/diffusion_pytorch_model.safetensors +3 -0
  5. train_ex8_12/checkpoint-235260/custom_encoder/config.json +9 -0
  6. train_ex8_12/checkpoint-235260/custom_encoder/diffusion_pytorch_model.safetensors +3 -0
  7. train_ex8_12/checkpoint-235260/custom_unet.pth +3 -0
  8. train_ex8_12/checkpoint-235260/optimizer.bin +3 -0
  9. train_ex8_12/checkpoint-235260/random_states_0.pkl +3 -0
  10. train_ex8_12/checkpoint-235260/scheduler.bin +3 -0
  11. train_ex8_12/config.yaml +140 -0
train_ex8_12/checkpoint-235260/albedo_estimator/config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AlbedoWrapper",
3
+ "_diffusers_version": "0.33.1",
4
+ "cfg": {
5
+ "enabled": true,
6
+ "frozen_components": [
7
+ "ord_model",
8
+ "iid_model",
9
+ "col_model"
10
+ ],
11
+ "load_stage": 3,
12
+ "trainable_components": [
13
+ "alb_model"
14
+ ],
15
+ "version": "v2"
16
+ }
17
+ }
train_ex8_12/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:afe467f689c55cb4da985be1db6ffa2d1258cca601ec767b01dc114e936b205d
3
+ size 422422660
train_ex8_12/checkpoint-235260/controlnet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.33.1",
4
+ "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": null,
8
+ "attention_head_dim": [
9
+ 5,
10
+ 10,
11
+ 20,
12
+ 20
13
+ ],
14
+ "block_out_channels": [
15
+ 320,
16
+ 640,
17
+ 1280,
18
+ 1280
19
+ ],
20
+ "class_embed_type": null,
21
+ "conditioning_channels": 6,
22
+ "conditioning_embedding_out_channels": [
23
+ 16,
24
+ 32,
25
+ 96,
26
+ 256
27
+ ],
28
+ "controlnet_conditioning_channel_order": "rgb",
29
+ "cross_attention_dim": 1024,
30
+ "down_block_types": [
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "DownBlock2D"
35
+ ],
36
+ "downsample_padding": 1,
37
+ "encoder_hid_dim": null,
38
+ "encoder_hid_dim_type": null,
39
+ "flip_sin_to_cos": true,
40
+ "freq_shift": 0,
41
+ "global_pool_conditions": false,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "norm_eps": 1e-05,
47
+ "norm_num_groups": 32,
48
+ "num_attention_heads": null,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "projection_class_embeddings_input_dim": null,
52
+ "resnet_time_scale_shift": "default",
53
+ "transformer_layers_per_block": 1,
54
+ "upcast_attention": true,
55
+ "use_linear_projection": true
56
+ }
train_ex8_12/checkpoint-235260/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fed000ee56540c66e2e9034f9b78bd0331ad03d8ec661a87a8fb8ea7ed71cc3
3
+ size 1461729992
train_ex8_12/checkpoint-235260/custom_encoder/config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Ba": 4,
3
+ "Bc": 4,
4
+ "Bi": 4,
5
+ "K": 4,
6
+ "_class_name": "CustomEncoder",
7
+ "_diffusers_version": "0.33.1",
8
+ "cross_dim": 1024
9
+ }
train_ex8_12/checkpoint-235260/custom_encoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:128b3c129993af4b26532250bf813d4618c594a7afd745c4da340a8a8c2768c2
3
+ size 4541016
train_ex8_12/checkpoint-235260/custom_unet.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ad59fcfda4d0680c2edbf4f205ab4ac461fdf4519a8a65a4c7943b0b8f21bb
3
+ size 3463973299
train_ex8_12/checkpoint-235260/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ece1355a44539153cd716665eef3b80f80f4813b8c3356b9e6756955c1f1428
3
+ size 6407500783
train_ex8_12/checkpoint-235260/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fea1c8ec4eef756e5891d4de02e73464ba897a2f5554ee760898b4c458838ed
3
+ size 14821
train_ex8_12/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_12/config.yaml ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ experiment:
2
+ project_name: relighting_indoors
3
+ output_dir: train_ex8_12
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: 768
37
+ dataloader_num_workers: 0
38
+ condition_mode: lightmap_normal
39
+ relighting_impl: gemini_amb
40
+ use_ambient_in_controlnet: true
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