Hugging Face's logo

yuxinhang
/
model_out

Text-to-Image
Diffusers
TensorBoard
Safetensors
stable-diffusion
stable-diffusion-diffusers
controlnet
Model card Files Metrics Community
yuxinhang commited on
Commit
0a7c3a7
•
1 Parent(s): 96bf8b3

End of training

Browse files
Files changed (22) hide show
  1. .gitattributes +3 -0
  2. README.md +24 -0
  3. checkpoint-5/controlnet/config.json +56 -0
  4. checkpoint-5/controlnet/diffusion_pytorch_model.safetensors +3 -0
  5. checkpoint-5/optimizer.bin +3 -0
  6. checkpoint-5/random_states_0.pkl +3 -0
  7. checkpoint-5/scheduler.bin +3 -0
  8. config.json +56 -0
  9. diffusion_pytorch_model.safetensors +3 -0
  10. image_control.png +0 -0
  11. images_0.png +3 -0
  12. images_1.png +3 -0
  13. images_2.png +3 -0
  14. logs/controlnet/1704360704.2371767/events.out.tfevents.1704360704.9570e9745b9f.75281.1 +3 -0
  15. logs/controlnet/1704360704.2407382/hparams.yml +50 -0
  16. logs/controlnet/1704360915.709316/events.out.tfevents.1704360915.9570e9745b9f.77363.1 +3 -0
  17. logs/controlnet/1704360915.7125561/hparams.yml +50 -0
  18. logs/controlnet/1704361149.2166028/events.out.tfevents.1704361149.9570e9745b9f.80007.1 +3 -0
  19. logs/controlnet/1704361149.2200058/hparams.yml +50 -0
  20. logs/controlnet/events.out.tfevents.1704360704.9570e9745b9f.75281.0 +3 -0
  21. logs/controlnet/events.out.tfevents.1704360915.9570e9745b9f.77363.0 +3 -0
  22. logs/controlnet/events.out.tfevents.1704361149.9570e9745b9f.80007.0 +3 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ images_0.png filter=lfs diff=lfs merge=lfs -text
37
+ images_1.png filter=lfs diff=lfs merge=lfs -text
38
+ images_2.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: stabilityai/stable-diffusion-2-1-base
5
+ tags:
6
+ - stable-diffusion
7
+ - stable-diffusion-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - controlnet
11
+ inference: true
12
+ ---
13
+
14
+ # controlnet-yuxinhang/model_out
15
+
16
+ These are controlnet weights trained on stabilityai/stable-diffusion-2-1-base with new type of conditioning.
17
+ You can find some example images below.
18
+ prompt: High-quality close-up dslr photo of man wearing a hat with trees in the background
19
+ ![images_0)](./images_0.png)
20
+ prompt: Girl smiling, professional dslr photograph, dark background, studio lights, high quality
21
+ ![images_1)](./images_1.png)
22
+ prompt: Portrait of a clown face, oil on canvas, bittersweet expression
23
+ ![images_2)](./images_2.png)
24
+
checkpoint-5/controlnet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.25.0.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": [
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": 3,
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": false,
55
+ "use_linear_projection": true
56
+ }
checkpoint-5/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:103fe98226048b1c5269faec0faff8b920dffb1e90308efe93f6afeeff15317c
3
+ size 1456953560
checkpoint-5/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b188437c6dad869067c142d739b42aa9adbba8a767549a7494a0167cad0af8c3
3
+ size 2914111182
checkpoint-5/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59a573d47066cbe1c6a29cf2bc5342bce2dd7db0674a52b62fdefb88493b8c76
3
+ size 14668
checkpoint-5/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:963103e32e7ba69c25f618584c5ad295f366f0d5165463d0433856933a788d64
3
+ size 1000
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.25.0.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": [
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": 3,
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": false,
55
+ "use_linear_projection": true
56
+ }
diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e386e1ba94725ce8c41298c80618cf4b14f0bab998e75bdc8292b65ec41b5da4
3
+ size 1456953560
image_control.png ADDED
images_0.png ADDED

Git LFS Details

  • SHA256: d6289c5c74cef356b960b61a74c55fe33f5d7b4e1ea55fb21c4f103c626b6307
  • Pointer size: 132 Bytes
  • Size of remote file: 1.64 MB
images_1.png ADDED

Git LFS Details

  • SHA256: 9fc9b1c7d52379eaae5d0a4d846bf56d8c1656a2cfa0581da40d5c7fde20149f
  • Pointer size: 132 Bytes
  • Size of remote file: 1.63 MB
images_2.png ADDED

Git LFS Details

  • SHA256: e911dd0bb32e6468333120e5a6d8759a4264a3afa930f3371b250eadd4d255b8
  • Pointer size: 132 Bytes
  • Size of remote file: 1.8 MB
logs/controlnet/1704360704.2371767/events.out.tfevents.1704360704.9570e9745b9f.75281.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40bbb6b4150c1c10920bd13748d188a78b121feae716cad28b97ef35fc3fec12
3
+ size 2302
logs/controlnet/1704360704.2407382/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: image_caption
8
+ checkpointing_steps: 50
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: spiga_seg
11
+ controlnet_model_name_or_path: null
12
+ dataloader_num_workers: 0
13
+ dataset_config_name: null
14
+ dataset_name: multimodalart/facesyntheticsspigacaptioned
15
+ enable_xformers_memory_efficient_attention: true
16
+ gradient_accumulation_steps: 1
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: 25000
30
+ mixed_precision: null
31
+ num_train_epochs: 1
32
+ num_validation_images: 4
33
+ output_dir: model_out
34
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1-base
35
+ proportion_empty_prompts: 0
36
+ push_to_hub: false
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: controlnet
46
+ train_batch_size: 4
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ validation_steps: 100
50
+ variant: null
logs/controlnet/1704360915.709316/events.out.tfevents.1704360915.9570e9745b9f.77363.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a0ea67d816243a498ce489241b3b6f28e785d18049d23e8193611dab9ae820
3
+ size 2302
logs/controlnet/1704360915.7125561/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: image_caption
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: spiga_seg
11
+ controlnet_model_name_or_path: null
12
+ dataloader_num_workers: 0
13
+ dataset_config_name: null
14
+ dataset_name: multimodalart/facesyntheticsspigacaptioned
15
+ enable_xformers_memory_efficient_attention: true
16
+ gradient_accumulation_steps: 1
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: 75000
30
+ mixed_precision: null
31
+ num_train_epochs: 3
32
+ num_validation_images: 4
33
+ output_dir: model_out
34
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1-base
35
+ proportion_empty_prompts: 0
36
+ push_to_hub: false
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: controlnet
46
+ train_batch_size: 4
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ validation_steps: 5000
50
+ variant: null
logs/controlnet/1704361149.2166028/events.out.tfevents.1704361149.9570e9745b9f.80007.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e4eec1024a56148179a8d80e4cfb97cf8b53740585131f89ff7bf4f6ccb3fa
3
+ size 2302
logs/controlnet/1704361149.2200058/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: image_caption
8
+ checkpointing_steps: 5000
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: spiga_seg
11
+ controlnet_model_name_or_path: null
12
+ dataloader_num_workers: 0
13
+ dataset_config_name: null
14
+ dataset_name: multimodalart/facesyntheticsspigacaptioned
15
+ enable_xformers_memory_efficient_attention: true
16
+ gradient_accumulation_steps: 1
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: 75000
30
+ mixed_precision: null
31
+ num_train_epochs: 3
32
+ num_validation_images: 4
33
+ output_dir: model_out
34
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1-base
35
+ proportion_empty_prompts: 0
36
+ push_to_hub: false
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: controlnet
46
+ train_batch_size: 4
47
+ train_data_dir: null
48
+ use_8bit_adam: false
49
+ validation_steps: 5000
50
+ variant: null
logs/controlnet/events.out.tfevents.1704360704.9570e9745b9f.75281.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ce4f04c6312076024f44963c7a6264e7b488844ea4246740822c6ead7e97646
3
+ size 88
logs/controlnet/events.out.tfevents.1704360915.9570e9745b9f.77363.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:611b349db0f6c02369ea587c0b1528fbe6a6460316dd05f14c4d6816fa5ecae1
3
+ size 88
logs/controlnet/events.out.tfevents.1704361149.9570e9745b9f.80007.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6c0b04167b7e26bd7f323eb257cb58dbe9a395b950660b596db833c531c1c2
3
+ size 1482