jbeomlee93 commited on
Commit
e040c57
1 Parent(s): 0ef2b97

End of training

Browse files
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: openrail++
4
+ base_model: diffusers/stable-diffusion-xl-1.0-inpainting-0.1
5
+ tags:
6
+ - stable-diffusion-xl
7
+ - stable-diffusion-xl-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - controlnet
11
+ inference: true
12
+ ---
13
+
14
+ # controlnet-jbeomlee93/output_lr1e-5_datav3_modify_size1024_step1000_zoomin_textprompt_v2
15
+
16
+ These are controlnet weights trained on diffusers/stable-diffusion-xl-1.0-inpainting-0.1 with new type of conditioning.
17
+
checkpoint-1000/controlnet/config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "_name_or_path": "diffusers/controlnet-canny-sdxl-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "block_out_channels": [
15
+ 320,
16
+ 640,
17
+ 1280
18
+ ],
19
+ "class_embed_type": null,
20
+ "conditioning_channels": 3,
21
+ "conditioning_embedding_out_channels": [
22
+ 16,
23
+ 32,
24
+ 96,
25
+ 256
26
+ ],
27
+ "controlnet_conditioning_channel_order": "rgb",
28
+ "cross_attention_dim": 2048,
29
+ "down_block_types": [
30
+ "DownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "global_pool_conditions": false,
40
+ "in_channels": 4,
41
+ "layers_per_block": 2,
42
+ "mid_block_scale_factor": 1,
43
+ "norm_eps": 1e-05,
44
+ "norm_num_groups": 32,
45
+ "num_attention_heads": null,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "projection_class_embeddings_input_dim": 2816,
49
+ "resnet_time_scale_shift": "default",
50
+ "transformer_layers_per_block": [
51
+ 1,
52
+ 2,
53
+ 10
54
+ ],
55
+ "upcast_attention": null,
56
+ "use_linear_projection": true
57
+ }
checkpoint-1000/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ae8ab7c0212972aea1ad76fb04b8092b9976c57116430ab19ba521e7da93884
3
+ size 5004167864
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4234995b791642541ebe87c4b354dcafbca70ecec2d2fd6db7d717a583a392
3
+ size 2510393614
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a81fb3fcb214f6ff8d6e672f4f2ff4a645e1ea680bc2312bbad21b01a1fc8946
3
+ size 16036
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
3
+ size 988
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d16ae9dedf4c45ceadc467593037d83423677715e75ab402a9f44aa81de9b84
3
+ size 1000
checkpoint-500/controlnet/config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "_name_or_path": "diffusers/controlnet-canny-sdxl-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "block_out_channels": [
15
+ 320,
16
+ 640,
17
+ 1280
18
+ ],
19
+ "class_embed_type": null,
20
+ "conditioning_channels": 3,
21
+ "conditioning_embedding_out_channels": [
22
+ 16,
23
+ 32,
24
+ 96,
25
+ 256
26
+ ],
27
+ "controlnet_conditioning_channel_order": "rgb",
28
+ "cross_attention_dim": 2048,
29
+ "down_block_types": [
30
+ "DownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "global_pool_conditions": false,
40
+ "in_channels": 4,
41
+ "layers_per_block": 2,
42
+ "mid_block_scale_factor": 1,
43
+ "norm_eps": 1e-05,
44
+ "norm_num_groups": 32,
45
+ "num_attention_heads": null,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "projection_class_embeddings_input_dim": 2816,
49
+ "resnet_time_scale_shift": "default",
50
+ "transformer_layers_per_block": [
51
+ 1,
52
+ 2,
53
+ 10
54
+ ],
55
+ "upcast_attention": null,
56
+ "use_linear_projection": true
57
+ }
checkpoint-500/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7445b6980e5327ae1940ffc27e578c136c244e410aa540b0006925d260597f80
3
+ size 5004167864
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f2004d7c5ca8242aaccbf144efc066fe101eb481582da960ff257542c016864
3
+ size 2510393614
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de01a9299f232fbd0927ea715881c91897bdbc641d9229a62088913105909ac1
3
+ size 16036
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b984273ea2d45b7ffb1d047bb359d93111e41fcad70d16a1b453fd38f72636
3
+ size 988
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d7b85c46d195e3cd6e587d94878d77f315e0a073acfab811251f39fbe891fc
3
+ size 1000
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.24.0.dev0",
4
+ "_name_or_path": "diffusers/controlnet-canny-sdxl-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "block_out_channels": [
15
+ 320,
16
+ 640,
17
+ 1280
18
+ ],
19
+ "class_embed_type": null,
20
+ "conditioning_channels": 3,
21
+ "conditioning_embedding_out_channels": [
22
+ 16,
23
+ 32,
24
+ 96,
25
+ 256
26
+ ],
27
+ "controlnet_conditioning_channel_order": "rgb",
28
+ "cross_attention_dim": 2048,
29
+ "down_block_types": [
30
+ "DownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "global_pool_conditions": false,
40
+ "in_channels": 4,
41
+ "layers_per_block": 2,
42
+ "mid_block_scale_factor": 1,
43
+ "norm_eps": 1e-05,
44
+ "norm_num_groups": 32,
45
+ "num_attention_heads": null,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "projection_class_embeddings_input_dim": 2816,
49
+ "resnet_time_scale_shift": "default",
50
+ "transformer_layers_per_block": [
51
+ 1,
52
+ 2,
53
+ 10
54
+ ],
55
+ "upcast_attention": null,
56
+ "use_linear_projection": true
57
+ }
diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ae8ab7c0212972aea1ad76fb04b8092b9976c57116430ab19ba521e7da93884
3
+ size 5004167864
logs/sd_xl_train_controlnet/1703014899.6594174/events.out.tfevents.1703014899.pytorch-2-0-0-gpu-ml-p3dn-24xlarge-051a6d0780b7e55a6ff84c63b4cd.292.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d659b2d55a741901a198a828ea2fd8e7f536d8287b0800d0d521d94843ccec6
3
+ size 2668
logs/sd_xl_train_controlnet/1703014899.7058423/hparams.yml ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 500
9
+ checkpoints_total_limit: null
10
+ conditioning_image_column: conditioning_image
11
+ controlnet_model_name_or_path: diffusers/controlnet-canny-sdxl-1.0
12
+ crops_coords_top_left_h: 0
13
+ crops_coords_top_left_w: 0
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: dataset_JB
17
+ enable_xformers_memory_efficient_attention: true
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: false
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ learning_rate: 1.0e-05
24
+ logging_dir: logs
25
+ lr_num_cycles: 1
26
+ lr_power: 1.0
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 500
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 1000
32
+ mixed_precision: fp16
33
+ num_train_epochs: 4
34
+ num_validation_images: 4
35
+ output_dir: output_lr1e-5_datav3_modify_size1024_step1000_zoomin_textprompt_v2
36
+ pretrained_model_name_or_path: diffusers/stable-diffusion-xl-1.0-inpainting-0.1
37
+ pretrained_vae_model_name_or_path: null
38
+ proportion_empty_prompts: 0
39
+ push_to_hub: true
40
+ report_to: tensorboard
41
+ resolution: 1024
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: 42
46
+ set_grads_to_none: true
47
+ tokenizer_name: null
48
+ tracker_project_name: sd_xl_train_controlnet
49
+ train_batch_size: 1
50
+ train_data_dir: null
51
+ use_8bit_adam: true
52
+ validation_steps: 10000
53
+ variant: null
logs/sd_xl_train_controlnet/events.out.tfevents.1703014899.pytorch-2-0-0-gpu-ml-p3dn-24xlarge-051a6d0780b7e55a6ff84c63b4cd.292.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc14d8e46297266d23333135e2f4db5cb195c3b363023b77dd81ef6ebfcec0db
3
+ size 334298