Hugging Face's logo

merensoykok
/
output

Text-to-Image
Diffusers
TensorBoard
Safetensors
stable-diffusion
stable-diffusion-diffusers
controlnet
diffusers-training
Model card Files
xet
 Metrics Community
merensoykok commited on
Commit
996d9e3
·
verified ·
1 Parent(s): f10fb83

End of training

Browse files
Files changed (17) hide show
  1. README.md +39 -0
  2. checkpoint-2000/controlnet/config.json +52 -0
  3. checkpoint-2000/controlnet/diffusion_pytorch_model.safetensors +3 -0
  4. checkpoint-2000/optimizer.bin +3 -0
  5. checkpoint-2000/random_states_0.pkl +3 -0
  6. checkpoint-2000/scheduler.bin +3 -0
  7. config.json +52 -0
  8. diffusion_pytorch_model.safetensors +3 -0
  9. logs/train_controlnet/1746778500.419717/events.out.tfevents.1746778500.b349201978fb.8955.1 +3 -0
  10. logs/train_controlnet/1746778500.421157/hparams.yml +51 -0
  11. logs/train_controlnet/1746778596.8412447/events.out.tfevents.1746778596.b349201978fb.9604.1 +3 -0
  12. logs/train_controlnet/1746778596.8426833/hparams.yml +51 -0
  13. logs/train_controlnet/1746778851.2719972/events.out.tfevents.1746778851.b349201978fb.10780.1 +3 -0
  14. logs/train_controlnet/1746778851.273483/hparams.yml +51 -0
  15. logs/train_controlnet/events.out.tfevents.1746778500.b349201978fb.8955.0 +3 -0
  16. logs/train_controlnet/events.out.tfevents.1746778596.b349201978fb.9604.0 +3 -0
  17. logs/train_controlnet/events.out.tfevents.1746778851.b349201978fb.10780.0 +3 -0
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-inpainting
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ inference: true
6
+ tags:
7
+ - stable-diffusion
8
+ - stable-diffusion-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ - controlnet
12
+ - diffusers-training
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-merensoykok/output
20
+
21
+ These are controlnet weights trained on stable-diffusion-v1-5/stable-diffusion-inpainting 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-2000/controlnet/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "_name_or_path": "lllyasviel/control_v11p_sd15_inpaint",
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": 8,
10
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "class_embed_type": null,
17
+ "conditioning_channels": 3,
18
+ "conditioning_embedding_out_channels": [
19
+ 16,
20
+ 32,
21
+ 96,
22
+ 256
23
+ ],
24
+ "controlnet_conditioning_channel_order": "rgb",
25
+ "cross_attention_dim": 768,
26
+ "down_block_types": [
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "DownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "global_pool_conditions": false,
38
+ "in_channels": 4,
39
+ "layers_per_block": 2,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_attention_heads": null,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "projection_class_embeddings_input_dim": null,
48
+ "resnet_time_scale_shift": "default",
49
+ "transformer_layers_per_block": 1,
50
+ "upcast_attention": false,
51
+ "use_linear_projection": false
52
+ }
checkpoint-2000/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6bf1eca5f0e0318c1f53afc1c9f6bb39d7089e42923d1bfa4d0e4e13b70808
3
+ size 1445157120
checkpoint-2000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:033011f24f8af49b290046514f0a1bad3e3fb26a4bb6a2f7a350c85f1ab447c8
3
+ size 2890518478
checkpoint-2000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513a71a600de0040773dcdab562c5fda646d53a051d82aa472685f5ae330ea09
3
+ size 14408
checkpoint-2000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebfe21ebf717fd6e4118374475c255f5df2d20d71ad2f0211578b00a982aae56
3
+ size 1000
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "_name_or_path": "lllyasviel/control_v11p_sd15_inpaint",
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": 8,
10
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "class_embed_type": null,
17
+ "conditioning_channels": 3,
18
+ "conditioning_embedding_out_channels": [
19
+ 16,
20
+ 32,
21
+ 96,
22
+ 256
23
+ ],
24
+ "controlnet_conditioning_channel_order": "rgb",
25
+ "cross_attention_dim": 768,
26
+ "down_block_types": [
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "DownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "global_pool_conditions": false,
38
+ "in_channels": 4,
39
+ "layers_per_block": 2,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_attention_heads": null,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "projection_class_embeddings_input_dim": null,
48
+ "resnet_time_scale_shift": "default",
49
+ "transformer_layers_per_block": 1,
50
+ "upcast_attention": false,
51
+ "use_linear_projection": false
52
+ }
diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6bf1eca5f0e0318c1f53afc1c9f6bb39d7089e42923d1bfa4d0e4e13b70808
3
+ size 1445157120
logs/train_controlnet/1746778500.419717/events.out.tfevents.1746778500.b349201978fb.8955.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7920a70defe88ad07234795329f21b10cb36327556585eed4cc6e50b5faafec
3
+ size 2513
logs/train_controlnet/1746778500.421157/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: prompt
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: source
11
+ controlnet_model_name_or_path: lllyasviel/control_v11p_sd15_inpaint
12
+ dataloader_num_workers: 0
13
+ dataset_config_name: null
14
+ dataset_name: merensoykok/vitonhd-dataset-for-controlnet
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: target
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: 0
27
+ mask_column: mask
28
+ max_grad_norm: 1.0
29
+ max_train_samples: null
30
+ max_train_steps: 5000
31
+ mixed_precision: bf16
32
+ num_train_epochs: 7
33
+ num_validation_images: 4
34
+ output_dir: /content/output
35
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-inpainting
36
+ proportion_empty_prompts: 0
37
+ push_to_hub: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ set_grads_to_none: false
45
+ tokenizer_name: null
46
+ tracker_project_name: train_controlnet
47
+ train_batch_size: 16
48
+ train_data_dir: null
49
+ use_8bit_adam: false
50
+ validation_steps: 100
51
+ variant: null
logs/train_controlnet/1746778596.8412447/events.out.tfevents.1746778596.b349201978fb.9604.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:176dbe7d2e463cf487132826ceae3f3418337bfcc3f575cdef3fb6c2625ab0bd
3
+ size 2513
logs/train_controlnet/1746778596.8426833/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: prompt
8
+ checkpointing_steps: 2000
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: source
11
+ controlnet_model_name_or_path: lllyasviel/control_v11p_sd15_inpaint
12
+ dataloader_num_workers: 0
13
+ dataset_config_name: null
14
+ dataset_name: merensoykok/vitonhd-dataset-for-controlnet
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: target
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: 0
27
+ mask_column: mask
28
+ max_grad_norm: 1.0
29
+ max_train_samples: null
30
+ max_train_steps: 2000
31
+ mixed_precision: bf16
32
+ num_train_epochs: 3
33
+ num_validation_images: 4
34
+ output_dir: /content/output
35
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-inpainting
36
+ proportion_empty_prompts: 0
37
+ push_to_hub: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ set_grads_to_none: false
45
+ tokenizer_name: null
46
+ tracker_project_name: train_controlnet
47
+ train_batch_size: 16
48
+ train_data_dir: null
49
+ use_8bit_adam: false
50
+ validation_steps: 100
51
+ variant: null
logs/train_controlnet/1746778851.2719972/events.out.tfevents.1746778851.b349201978fb.10780.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a8fc3727a00505f72ddaff41bf3449833a1c9a13e8446df907364945f84dc9
3
+ size 2513
logs/train_controlnet/1746778851.273483/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: prompt
8
+ checkpointing_steps: 2000
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: source
11
+ controlnet_model_name_or_path: lllyasviel/control_v11p_sd15_inpaint
12
+ dataloader_num_workers: 0
13
+ dataset_config_name: null
14
+ dataset_name: merensoykok/vitonhd-dataset-for-controlnet
15
+ enable_xformers_memory_efficient_attention: false
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: target
21
+ learning_rate: 5.0e-06
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 0
27
+ mask_column: mask
28
+ max_grad_norm: 1.0
29
+ max_train_samples: null
30
+ max_train_steps: 2000
31
+ mixed_precision: bf16
32
+ num_train_epochs: 3
33
+ num_validation_images: 4
34
+ output_dir: /content/output
35
+ pretrained_model_name_or_path: stable-diffusion-v1-5/stable-diffusion-inpainting
36
+ proportion_empty_prompts: 0
37
+ push_to_hub: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ set_grads_to_none: false
45
+ tokenizer_name: null
46
+ tracker_project_name: train_controlnet
47
+ train_batch_size: 16
48
+ train_data_dir: null
49
+ use_8bit_adam: false
50
+ validation_steps: 100
51
+ variant: null
logs/train_controlnet/events.out.tfevents.1746778500.b349201978fb.8955.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f031652cbcd127cd2eaa511d0b928ba230b35e99c9dd188286ae9f8d4ddf25
3
+ size 4024
logs/train_controlnet/events.out.tfevents.1746778596.b349201978fb.9604.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0b8bd4c7620484dcd66d8f6ed74d3447507db7c3f0540c1ba23b485e8652f1
3
+ size 16634
logs/train_controlnet/events.out.tfevents.1746778851.b349201978fb.10780.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f4babb96797c9175a973d388d7d1c72db37cf4b5685a8af879990613527b9c0
3
+ size 167834