Hugging Face's logo

awang11
/
vggsound_diffusion

Text-to-Image
Diffusers
TensorBoard
Safetensors
stable-diffusion
stable-diffusion-diffusers
controlnet
diffusers-training
Model card Files Metrics Community
awang11 commited on
Commit
d6da68b
•
1 Parent(s): c16f103

End of training

Browse files
Files changed (30) hide show
  1. README.md +39 -0
  2. checkpoint-1200/controlnet/config.json +51 -0
  3. checkpoint-1200/controlnet/diffusion_pytorch_model.safetensors +3 -0
  4. checkpoint-1200/optimizer.bin +3 -0
  5. checkpoint-1200/random_states_0.pkl +3 -0
  6. checkpoint-1200/scheduler.bin +3 -0
  7. checkpoint-1800/controlnet/config.json +51 -0
  8. checkpoint-1800/controlnet/diffusion_pytorch_model.safetensors +3 -0
  9. checkpoint-1800/optimizer.bin +3 -0
  10. checkpoint-1800/random_states_0.pkl +3 -0
  11. checkpoint-1800/scheduler.bin +3 -0
  12. checkpoint-600/controlnet/config.json +51 -0
  13. checkpoint-600/controlnet/diffusion_pytorch_model.safetensors +3 -0
  14. checkpoint-600/optimizer.bin +3 -0
  15. checkpoint-600/random_states_0.pkl +3 -0
  16. checkpoint-600/scheduler.bin +3 -0
  17. config.json +51 -0
  18. diffusion_pytorch_model.safetensors +3 -0
  19. logs/train_controlnet/1715467276.8193219/events.out.tfevents.1715467276.090bfa06f9d8.658.1 +3 -0
  20. logs/train_controlnet/1715467276.829244/hparams.yml +50 -0
  21. logs/train_controlnet/1715467773.8443022/events.out.tfevents.1715467773.090bfa06f9d8.1417.1 +3 -0
  22. logs/train_controlnet/1715467773.8536825/hparams.yml +50 -0
  23. logs/train_controlnet/1715467841.6531563/events.out.tfevents.1715467841.090bfa06f9d8.1511.1 +3 -0
  24. logs/train_controlnet/1715467841.6622374/hparams.yml +50 -0
  25. logs/train_controlnet/1715467878.7687037/events.out.tfevents.1715467878.090bfa06f9d8.1587.1 +3 -0
  26. logs/train_controlnet/1715467878.7810872/hparams.yml +50 -0
  27. logs/train_controlnet/events.out.tfevents.1715467276.090bfa06f9d8.658.0 +3 -0
  28. logs/train_controlnet/events.out.tfevents.1715467773.090bfa06f9d8.1417.0 +3 -0
  29. logs/train_controlnet/events.out.tfevents.1715467841.090bfa06f9d8.1511.0 +3 -0
  30. logs/train_controlnet/events.out.tfevents.1715467878.090bfa06f9d8.1587.0 +3 -0
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: creativeml-openrail-m
3
+ library_name: diffusers
4
+ tags:
5
+ - stable-diffusion
6
+ - stable-diffusion-diffusers
7
+ - text-to-image
8
+ - diffusers
9
+ - controlnet
10
+ - diffusers-training
11
+ base_model: runwayml/stable-diffusion-v1-5
12
+ inference: true
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+
19
+ # controlnet-awang11/vggsound_diffusion
20
+
21
+ These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.
22
+
23
+
24
+
25
+ ## Intended uses & limitations
26
+
27
+ #### How to use
28
+
29
+ ```python
30
+ # TODO: add an example code snippet for running this diffusion pipeline
31
+ ```
32
+
33
+ #### Limitations and bias
34
+
35
+ [TODO: provide examples of latent issues and potential remediations]
36
+
37
+ ## Training details
38
+
39
+ [TODO: describe the data used to train the model]
checkpoint-1200/controlnet/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.28.0.dev0",
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": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "class_embed_type": null,
16
+ "conditioning_channels": 3,
17
+ "conditioning_embedding_out_channels": [
18
+ 16,
19
+ 32,
20
+ 96,
21
+ 256
22
+ ],
23
+ "controlnet_conditioning_channel_order": "rgb",
24
+ "cross_attention_dim": 768,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "encoder_hid_dim": null,
33
+ "encoder_hid_dim_type": null,
34
+ "flip_sin_to_cos": true,
35
+ "freq_shift": 0,
36
+ "global_pool_conditions": false,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_scale_factor": 1,
40
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
41
+ "norm_eps": 1e-05,
42
+ "norm_num_groups": 32,
43
+ "num_attention_heads": null,
44
+ "num_class_embeds": null,
45
+ "only_cross_attention": false,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_time_scale_shift": "default",
48
+ "transformer_layers_per_block": 1,
49
+ "upcast_attention": false,
50
+ "use_linear_projection": false
51
+ }
checkpoint-1200/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3557a4d78676b8512b16776b7c7bec24db26f683e4d8a7c44bed567dca8cd7
3
+ size 1445157120
checkpoint-1200/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f7f036d71c99db5724445e8af9ba03236153e78be06ba1d564b4883b078cca
3
+ size 2890518041
checkpoint-1200/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd3adf589d447c114daf31446da61313cee8645ed0e608dbe4846a51c1e598c5
3
+ size 14663
checkpoint-1200/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eaf4e05fa9eb1da7701be9b300c13754d0f398206792933f9128143042c65bc
3
+ size 563
checkpoint-1800/controlnet/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.28.0.dev0",
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": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "class_embed_type": null,
16
+ "conditioning_channels": 3,
17
+ "conditioning_embedding_out_channels": [
18
+ 16,
19
+ 32,
20
+ 96,
21
+ 256
22
+ ],
23
+ "controlnet_conditioning_channel_order": "rgb",
24
+ "cross_attention_dim": 768,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "encoder_hid_dim": null,
33
+ "encoder_hid_dim_type": null,
34
+ "flip_sin_to_cos": true,
35
+ "freq_shift": 0,
36
+ "global_pool_conditions": false,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_scale_factor": 1,
40
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
41
+ "norm_eps": 1e-05,
42
+ "norm_num_groups": 32,
43
+ "num_attention_heads": null,
44
+ "num_class_embeds": null,
45
+ "only_cross_attention": false,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_time_scale_shift": "default",
48
+ "transformer_layers_per_block": 1,
49
+ "upcast_attention": false,
50
+ "use_linear_projection": false
51
+ }
checkpoint-1800/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1889902a3ba092ccfdfa5f00a2a11ae2381e52a1a5d8c9a96f9f4df7da3eb661
3
+ size 1445157120
checkpoint-1800/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30b52835fda0fbc89e1a19e827295c5663c1e63987ab4aeb9d6f08cacd9d322
3
+ size 2890518041
checkpoint-1800/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fa4aa9b941e25d4524b7a28709c30f789a413bf8c8c72a32702da9e1954507d
3
+ size 14727
checkpoint-1800/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a49c788ff9804489df1dc4f9f992e029245132b6cf711a809e680d56f58c20c
3
+ size 563
checkpoint-600/controlnet/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.28.0.dev0",
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": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "class_embed_type": null,
16
+ "conditioning_channels": 3,
17
+ "conditioning_embedding_out_channels": [
18
+ 16,
19
+ 32,
20
+ 96,
21
+ 256
22
+ ],
23
+ "controlnet_conditioning_channel_order": "rgb",
24
+ "cross_attention_dim": 768,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "encoder_hid_dim": null,
33
+ "encoder_hid_dim_type": null,
34
+ "flip_sin_to_cos": true,
35
+ "freq_shift": 0,
36
+ "global_pool_conditions": false,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_scale_factor": 1,
40
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
41
+ "norm_eps": 1e-05,
42
+ "norm_num_groups": 32,
43
+ "num_attention_heads": null,
44
+ "num_class_embeds": null,
45
+ "only_cross_attention": false,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_time_scale_shift": "default",
48
+ "transformer_layers_per_block": 1,
49
+ "upcast_attention": false,
50
+ "use_linear_projection": false
51
+ }
checkpoint-600/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cce5649067ac88d2e84824780baeb96d052448221a70c96b334d1802e12ddbc7
3
+ size 1445157120
checkpoint-600/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944cecf03514876c24244d50e16df6809833e5125350f7664345249552baa773
3
+ size 2890518041
checkpoint-600/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93bce387ced9f991774508448b79f9dab0eddaf4aa01f6668f8fdea24c5e2ac8
3
+ size 14663
checkpoint-600/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165a371731b2b217fa84b0fb6ac8892a3d58c8b376ef3e6ce2927f89c8fff141
3
+ size 563
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.28.0.dev0",
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": 8,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "class_embed_type": null,
16
+ "conditioning_channels": 3,
17
+ "conditioning_embedding_out_channels": [
18
+ 16,
19
+ 32,
20
+ 96,
21
+ 256
22
+ ],
23
+ "controlnet_conditioning_channel_order": "rgb",
24
+ "cross_attention_dim": 768,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "encoder_hid_dim": null,
33
+ "encoder_hid_dim_type": null,
34
+ "flip_sin_to_cos": true,
35
+ "freq_shift": 0,
36
+ "global_pool_conditions": false,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_scale_factor": 1,
40
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
41
+ "norm_eps": 1e-05,
42
+ "norm_num_groups": 32,
43
+ "num_attention_heads": null,
44
+ "num_class_embeds": null,
45
+ "only_cross_attention": false,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_time_scale_shift": "default",
48
+ "transformer_layers_per_block": 1,
49
+ "upcast_attention": false,
50
+ "use_linear_projection": false
51
+ }
diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d39b1014bdc5b50f624108ac45220699b715d28d2c0fff561c73323ca65559c8
3
+ size 1445157120
logs/train_controlnet/1715467276.8193219/events.out.tfevents.1715467276.090bfa06f9d8.658.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:522d6ae634b5600cdc0a5f6de804ab17b9ed427e361f09310eb65822a37e8801
3
+ size 2302
logs/train_controlnet/1715467276.829244/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ checkpointing_steps: 3000
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: conditioning_image
11
+ controlnet_model_name_or_path: null
12
+ dataloader_num_workers: 0
13
+ dataset_config_name: null
14
+ dataset_name: awang11/VGGSound_ControlNet
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 4
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-05
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 500
27
+ max_grad_norm: 1.0
28
+ max_train_samples: null
29
+ max_train_steps: 2312
30
+ mixed_precision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: ../../../workspace/models
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ proportion_empty_prompts: 0
36
+ push_to_hub: true
37
+ report_to: tensorboard
38
+ resolution: 512
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: null
43
+ set_grads_to_none: false
44
+ tokenizer_name: null
45
+ tracker_project_name: train_controlnet
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ validation_steps: 100
50
+ variant: null
logs/train_controlnet/1715467773.8443022/events.out.tfevents.1715467773.090bfa06f9d8.1417.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c960217123a86fd760fd047ec23f5cca7495f8752da6be5d26e1a4088ebc654a
3
+ size 2366
logs/train_controlnet/1715467773.8536825/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ checkpointing_steps: 3000
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: conditioning_image
11
+ controlnet_model_name_or_path: null
12
+ dataloader_num_workers: 0
13
+ dataset_config_name: null
14
+ dataset_name: awang11/VGGSound_ControlNet
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 4
17
+ gradient_checkpointing: false
18
+ hub_model_id: awang11/vggsound_diffusion
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-05
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 500
27
+ max_grad_norm: 1.0
28
+ max_train_samples: null
29
+ max_train_steps: 2312
30
+ mixed_precision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: ../../../workspace/models
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ proportion_empty_prompts: 0
36
+ push_to_hub: true
37
+ report_to: tensorboard
38
+ resolution: 512
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: null
43
+ set_grads_to_none: false
44
+ tokenizer_name: null
45
+ tracker_project_name: train_controlnet
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ validation_steps: 100
50
+ variant: null
logs/train_controlnet/1715467841.6531563/events.out.tfevents.1715467841.090bfa06f9d8.1511.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:187674143a4dd51769652d3cefb2ca948f9eafd70e9edafb60e108d03e8bc2f6
3
+ size 2366
logs/train_controlnet/1715467841.6622374/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ checkpointing_steps: 3000
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: conditioning_image
11
+ controlnet_model_name_or_path: null
12
+ dataloader_num_workers: 0
13
+ dataset_config_name: null
14
+ dataset_name: awang11/VGGSound_ControlNet
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 4
17
+ gradient_checkpointing: false
18
+ hub_model_id: awang11/vggsound_diffusion
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-05
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 500
27
+ max_grad_norm: 1.0
28
+ max_train_samples: null
29
+ max_train_steps: 2312
30
+ mixed_precision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: ../../../workspace/models
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ proportion_empty_prompts: 0
36
+ push_to_hub: true
37
+ report_to: tensorboard
38
+ resolution: 512
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: null
43
+ set_grads_to_none: false
44
+ tokenizer_name: null
45
+ tracker_project_name: train_controlnet
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ validation_steps: 100
50
+ variant: null
logs/train_controlnet/1715467878.7687037/events.out.tfevents.1715467878.090bfa06f9d8.1587.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f5281d42db1da9fffd5149916a9c880e6d2d008c95422f5220b97d016bddc11
3
+ size 2366
logs/train_controlnet/1715467878.7810872/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ checkpointing_steps: 600
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: conditioning_image
11
+ controlnet_model_name_or_path: null
12
+ dataloader_num_workers: 0
13
+ dataset_config_name: null
14
+ dataset_name: awang11/VGGSound_ControlNet
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 4
17
+ gradient_checkpointing: false
18
+ hub_model_id: awang11/vggsound_diffusion
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-05
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 500
27
+ max_grad_norm: 1.0
28
+ max_train_samples: null
29
+ max_train_steps: 2312
30
+ mixed_precision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: ../../../workspace/models
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ proportion_empty_prompts: 0
36
+ push_to_hub: true
37
+ report_to: tensorboard
38
+ resolution: 512
39
+ resume_from_checkpoint: null
40
+ revision: null
41
+ scale_lr: false
42
+ seed: null
43
+ set_grads_to_none: false
44
+ tokenizer_name: null
45
+ tracker_project_name: train_controlnet
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ validation_steps: 100
50
+ variant: null
logs/train_controlnet/events.out.tfevents.1715467276.090bfa06f9d8.658.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af8be16654e37abfdf6abf3d6f541c5d870bc911ce4ea87b7abcc0bea77eccf7
3
+ size 88
logs/train_controlnet/events.out.tfevents.1715467773.090bfa06f9d8.1417.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba979d94135b02cc41bfc906dd4c065692e9feddedd389d1f9134ad05116559
3
+ size 88
logs/train_controlnet/events.out.tfevents.1715467841.090bfa06f9d8.1511.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ed86904cf3aef48cac9ecb3f8ff7f1cfd98d58a93a57c328bcc9a8a4104a98
3
+ size 1470
logs/train_controlnet/events.out.tfevents.1715467878.090bfa06f9d8.1587.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:608c45d2baaa8fa7feba8a6cdf2a707263936ad824c282ef413b633ca853961a
3
+ size 775886