Hugging Face's logo

aellaboudy
/
weights2

Text-to-Image
Diffusers
TensorBoard
StableDiffusionPipeline
Model card Files
xet
Metrics Community
aellaboudy commited on
Commit
5f2abfa
·
1 Parent(s): 7bfc3ab

End of training

Browse files
Files changed (40) hide show
  1. checkpoint-1000/optimizer.bin +3 -0
  2. checkpoint-1000/random_states_0.pkl +3 -0
  3. checkpoint-1000/scaler.pt +3 -0
  4. checkpoint-1000/scheduler.bin +3 -0
  5. checkpoint-1000/unet/config.json +67 -0
  6. checkpoint-1000/unet/diffusion_pytorch_model.bin +3 -0
  7. checkpoint-1000/unet_ema/config.json +74 -0
  8. checkpoint-1000/unet_ema/diffusion_pytorch_model.bin +3 -0
  9. checkpoint-1500/optimizer.bin +3 -0
  10. checkpoint-1500/random_states_0.pkl +3 -0
  11. checkpoint-1500/scaler.pt +3 -0
  12. checkpoint-1500/scheduler.bin +3 -0
  13. checkpoint-1500/unet/config.json +67 -0
  14. checkpoint-1500/unet/diffusion_pytorch_model.bin +3 -0
  15. checkpoint-1500/unet_ema/config.json +74 -0
  16. checkpoint-1500/unet_ema/diffusion_pytorch_model.bin +3 -0
  17. checkpoint-500/optimizer.bin +3 -0
  18. checkpoint-500/random_states_0.pkl +3 -0
  19. checkpoint-500/scaler.pt +3 -0
  20. checkpoint-500/scheduler.bin +3 -0
  21. checkpoint-500/unet/config.json +67 -0
  22. checkpoint-500/unet/diffusion_pytorch_model.bin +3 -0
  23. checkpoint-500/unet_ema/config.json +74 -0
  24. checkpoint-500/unet_ema/diffusion_pytorch_model.bin +3 -0
  25. feature_extractor/preprocessor_config.json +28 -0
  26. logs/text2image-fine-tune/1686295480.793312/events.out.tfevents.1686295480.209-20-157-246.95925.1 +3 -0
  27. logs/text2image-fine-tune/1686295480.7960658/hparams.yml +50 -0
  28. logs/text2image-fine-tune/events.out.tfevents.1686295480.209-20-157-246.95925.0 +3 -0
  29. model_index.json +33 -0
  30. scheduler/scheduler_config.json +14 -0
  31. text_encoder/config.json +25 -0
  32. text_encoder/pytorch_model.bin +3 -0
  33. tokenizer/merges.txt +0 -0
  34. tokenizer/special_tokens_map.json +24 -0
  35. tokenizer/tokenizer_config.json +33 -0
  36. tokenizer/vocab.json +0 -0
  37. unet/config.json +67 -0
  38. unet/diffusion_pytorch_model.bin +3 -0
  39. vae/config.json +31 -0
  40. vae/diffusion_pytorch_model.bin +3 -0
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:075e80bbfae79eef1b26c19f7954b2e1835848fc9f46435d8068dadd141764ac
3
+ size 6927867604
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:736de244c5f495f6465baa83bf85b03735920dddcbbd8ff74be6b72997e881ab
3
+ size 14280
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-1000/unet/config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
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
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 1024,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "DownBlock2D"
32
+ ],
33
+ "downsample_padding": 1,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": null,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "use_linear_projection": true
67
+ }
checkpoint-1000/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123186543db3a8d2ec3769b60ee8edb97f07ddd7e110582e828d5362b77596e7
3
+ size 3463935158
checkpoint-1000/unet_ema/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
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
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 1024,
26
+ "cross_attention_norm": null,
27
+ "decay": 0.9999,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "DownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 4,
41
+ "inv_gamma": 1.0,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "min_decay": 0.0,
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "optimization_step": 1000,
52
+ "out_channels": 4,
53
+ "power": 0.6666666666666666,
54
+ "projection_class_embeddings_input_dim": null,
55
+ "resnet_out_scale_factor": 1.0,
56
+ "resnet_skip_time_act": false,
57
+ "resnet_time_scale_shift": "default",
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "up_block_types": [
65
+ "UpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D"
69
+ ],
70
+ "upcast_attention": false,
71
+ "update_after_step": 0,
72
+ "use_ema_warmup": false,
73
+ "use_linear_projection": true
74
+ }
checkpoint-1000/unet_ema/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c34fa844292553bcb92693c4cb1376da77d3d21a518b90c3b1445a61c3ca8f23
3
+ size 3463925558
checkpoint-1500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0b2184a651ae8c7508c2b98979e9d3eca497a938237764e08b72e3d6797a164
3
+ size 6927867604
checkpoint-1500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c0cf2f0b78a2b98eec5cdf5e84566f531d5f7125685a56937fed937a5a0f9a
3
+ size 14280
checkpoint-1500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a4b6e0ef05ca249f2d6b7f9f3ad1dff81e55842a962df795bb9740c17c8e92
3
+ size 988
checkpoint-1500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcdd883061f8f3514731c51041dc7231d10951713a9abbd57d4f968a9c567ce3
3
+ size 1000
checkpoint-1500/unet/config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
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
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 1024,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "DownBlock2D"
32
+ ],
33
+ "downsample_padding": 1,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": null,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "use_linear_projection": true
67
+ }
checkpoint-1500/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23e2987d6aa6ed9f55f4ebede5dfc1489816887304c9063760b5e221ff65864
3
+ size 3463935158
checkpoint-1500/unet_ema/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
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
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 1024,
26
+ "cross_attention_norm": null,
27
+ "decay": 0.9999,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "DownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 4,
41
+ "inv_gamma": 1.0,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "min_decay": 0.0,
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "optimization_step": 1500,
52
+ "out_channels": 4,
53
+ "power": 0.6666666666666666,
54
+ "projection_class_embeddings_input_dim": null,
55
+ "resnet_out_scale_factor": 1.0,
56
+ "resnet_skip_time_act": false,
57
+ "resnet_time_scale_shift": "default",
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "up_block_types": [
65
+ "UpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D"
69
+ ],
70
+ "upcast_attention": false,
71
+ "update_after_step": 0,
72
+ "use_ema_warmup": false,
73
+ "use_linear_projection": true
74
+ }
checkpoint-1500/unet_ema/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb2090f6791ec658b1f40e8edd4fd01223006be30885ed80104c5bf1f2605e92
3
+ size 3463925558
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc6c40d4eac4ee93d09670e6c02af7b6529aa379b94219da040a43ae1c50359
3
+ size 6927867604
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb07108dd62a76ace6038048560aec32e13b74be16ffd55e2a9afa89d5bf190
3
+ size 14280
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
checkpoint-500/unet/config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
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
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 1024,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "DownBlock2D"
32
+ ],
33
+ "downsample_padding": 1,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": null,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "use_linear_projection": true
67
+ }
checkpoint-500/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de9bfd7b317aeec9f086e9d957d562dfd85d080a27b5df60c9b6d6073d166ad9
3
+ size 3463935158
checkpoint-500/unet_ema/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
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
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 1024,
26
+ "cross_attention_norm": null,
27
+ "decay": 0.9999,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "DownBlock2D"
33
+ ],
34
+ "downsample_padding": 1,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 4,
41
+ "inv_gamma": 1.0,
42
+ "layers_per_block": 2,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
46
+ "min_decay": 0.0,
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_class_embeds": null,
50
+ "only_cross_attention": false,
51
+ "optimization_step": 500,
52
+ "out_channels": 4,
53
+ "power": 0.6666666666666666,
54
+ "projection_class_embeddings_input_dim": null,
55
+ "resnet_out_scale_factor": 1.0,
56
+ "resnet_skip_time_act": false,
57
+ "resnet_time_scale_shift": "default",
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "up_block_types": [
65
+ "UpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D"
69
+ ],
70
+ "upcast_attention": false,
71
+ "update_after_step": 0,
72
+ "use_ema_warmup": false,
73
+ "use_linear_projection": true
74
+ }
checkpoint-500/unet_ema/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc88cac2beb0f6916b7666a083d32c37d726377a5f8c17c0c68ac90ae1b8104d
3
+ size 3463925558
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPImageProcessor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
logs/text2image-fine-tune/1686295480.793312/events.out.tfevents.1686295480.209-20-157-246.95925.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8fa0973b4b10db3d8da032d659fff7fba813afd9fcb58a411dece77513615b
3
+ size 2380
logs/text2image-fine-tune/1686295480.7960658/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
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: 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
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 1500
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 100
33
+ output_dir: /home/ubuntu/diffusers/examples/text_to_image/weights2/
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1-base
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 1
47
+ train_data_dir: /home/ubuntu/FurnitureDataset/
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/events.out.tfevents.1686295480.209-20-157-246.95925.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6583ac3ad367e86d64dbd1505bb4659167a547ff95197dd017c638716bf6a7c6
3
+ size 73461
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPImageProcessor"
7
+ ],
8
+ "requires_safety_checker": false,
9
+ "safety_checker": [
10
+ null,
11
+ null
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "PNDMScheduler"
16
+ ],
17
+ "text_encoder": [
18
+ "transformers",
19
+ "CLIPTextModel"
20
+ ],
21
+ "tokenizer": [
22
+ "transformers",
23
+ "CLIPTokenizer"
24
+ ],
25
+ "unet": [
26
+ "diffusers",
27
+ "UNet2DConditionModel"
28
+ ],
29
+ "vae": [
30
+ "diffusers",
31
+ "AutoencoderKL"
32
+ ]
33
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "trained_betas": null
14
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.29.2",
24
+ "vocab_size": 49408
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8426208d26b3b8a4293964395552a070b99499cf4d32c7880adf0e5b35a27aaf
3
+ size 680904670
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "!",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "pad_token": "<|endoftext|>",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
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
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 1024,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "DownBlock2D"
32
+ ],
33
+ "downsample_padding": 1,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": null,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "use_linear_projection": true
67
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9e60164ca7962aa1a14604d74dc40f01fbbc578ef18f28ad220c0e03f40665
3
+ size 3463935158
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 768,
24
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:774d64909483c737fe946c1338f4de098e284eaf216802ce807410d7903dcbb2
3
+ size 167408322