Skiittoo commited on
Commit
2ef5356
·
1 Parent(s): 1413f79

End of training

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +46 -0
  2. checkpoint-14500/optimizer.bin +3 -0
  3. checkpoint-14500/random_states_0.pkl +3 -0
  4. checkpoint-14500/scaler.pt +3 -0
  5. checkpoint-14500/scheduler.bin +3 -0
  6. checkpoint-14500/unet/config.json +67 -0
  7. checkpoint-14500/unet/diffusion_pytorch_model.safetensors +3 -0
  8. checkpoint-14500/unet_ema/config.json +74 -0
  9. checkpoint-14500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  10. checkpoint-15000/optimizer.bin +3 -0
  11. checkpoint-15000/random_states_0.pkl +3 -0
  12. checkpoint-15000/scaler.pt +3 -0
  13. checkpoint-15000/scheduler.bin +3 -0
  14. checkpoint-15000/unet/config.json +67 -0
  15. checkpoint-15000/unet/diffusion_pytorch_model.safetensors +3 -0
  16. checkpoint-15000/unet_ema/config.json +74 -0
  17. checkpoint-15000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  18. feature_extractor/preprocessor_config.json +28 -0
  19. logs/text2image-fine-tune/1696858589.9366672/events.out.tfevents.1696858589.aa1d505ac963.3709.1 +3 -0
  20. logs/text2image-fine-tune/1696858589.9385805/hparams.yml +50 -0
  21. logs/text2image-fine-tune/1696868180.564194/events.out.tfevents.1696868180.aa1d505ac963.42976.1 +3 -0
  22. logs/text2image-fine-tune/1696868180.5659726/hparams.yml +50 -0
  23. logs/text2image-fine-tune/1696868236.4700205/events.out.tfevents.1696868236.aa1d505ac963.43269.1 +3 -0
  24. logs/text2image-fine-tune/1696868236.4717777/hparams.yml +50 -0
  25. logs/text2image-fine-tune/1696868286.7558248/events.out.tfevents.1696868286.aa1d505ac963.43512.1 +3 -0
  26. logs/text2image-fine-tune/1696868286.757576/hparams.yml +50 -0
  27. logs/text2image-fine-tune/1696868333.0287201/events.out.tfevents.1696868333.aa1d505ac963.43737.1 +3 -0
  28. logs/text2image-fine-tune/1696868333.0305436/hparams.yml +50 -0
  29. logs/text2image-fine-tune/1696876771.8024945/events.out.tfevents.1696876771.aa1d505ac963.78270.1 +3 -0
  30. logs/text2image-fine-tune/1696876771.8045502/hparams.yml +50 -0
  31. logs/text2image-fine-tune/1696880869.211845/events.out.tfevents.1696880869.aa1d505ac963.94988.1 +3 -0
  32. logs/text2image-fine-tune/1696880869.2136056/hparams.yml +50 -0
  33. logs/text2image-fine-tune/1696890174.7166543/events.out.tfevents.1696890174.aa1d505ac963.133152.1 +3 -0
  34. logs/text2image-fine-tune/1696890174.7184038/hparams.yml +50 -0
  35. logs/text2image-fine-tune/1696890463.2686615/events.out.tfevents.1696890463.aa1d505ac963.134410.1 +3 -0
  36. logs/text2image-fine-tune/1696890463.27048/hparams.yml +50 -0
  37. logs/text2image-fine-tune/1696890634.3582013/events.out.tfevents.1696890634.aa1d505ac963.135158.1 +3 -0
  38. logs/text2image-fine-tune/1696890634.3599777/hparams.yml +50 -0
  39. logs/text2image-fine-tune/1696890884.8080351/events.out.tfevents.1696890884.aa1d505ac963.136224.1 +3 -0
  40. logs/text2image-fine-tune/1696890884.8099892/hparams.yml +50 -0
  41. logs/text2image-fine-tune/1696891063.54499/events.out.tfevents.1696891063.aa1d505ac963.136996.1 +3 -0
  42. logs/text2image-fine-tune/1696891063.5467377/hparams.yml +50 -0
  43. logs/text2image-fine-tune/events.out.tfevents.1696858589.aa1d505ac963.3709.0 +3 -0
  44. logs/text2image-fine-tune/events.out.tfevents.1696868180.aa1d505ac963.42976.0 +3 -0
  45. logs/text2image-fine-tune/events.out.tfevents.1696868236.aa1d505ac963.43269.0 +3 -0
  46. logs/text2image-fine-tune/events.out.tfevents.1696868286.aa1d505ac963.43512.0 +3 -0
  47. logs/text2image-fine-tune/events.out.tfevents.1696868333.aa1d505ac963.43737.0 +3 -0
  48. logs/text2image-fine-tune/events.out.tfevents.1696876771.aa1d505ac963.78270.0 +3 -0
  49. logs/text2image-fine-tune/events.out.tfevents.1696880869.aa1d505ac963.94988.0 +3 -0
  50. logs/text2image-fine-tune/events.out.tfevents.1696890174.aa1d505ac963.133152.0 +3 -0
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: CompVis/stable-diffusion-v1-4
5
+ datasets:
6
+ - Skiittoo/cartoon-faces
7
+ tags:
8
+ - stable-diffusion
9
+ - stable-diffusion-diffusers
10
+ - text-to-image
11
+ - diffusers
12
+ inference: true
13
+ ---
14
+
15
+ # Text-to-image finetuning - Skiittoo/sd-cartoon-faces-model
16
+
17
+ This pipeline was finetuned from **CompVis/stable-diffusion-v1-4** on the **Skiittoo/cartoon-faces** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['[Cartoon face with white skin]']:
18
+
19
+ ![val_imgs_grid](./val_imgs_grid.png)
20
+
21
+
22
+ ## Pipeline usage
23
+
24
+ You can use the pipeline like so:
25
+
26
+ ```python
27
+ from diffusers import DiffusionPipeline
28
+ import torch
29
+
30
+ pipeline = DiffusionPipeline.from_pretrained("Skiittoo/sd-cartoon-faces-model", torch_dtype=torch.float16)
31
+ prompt = "[Cartoon face with white skin]"
32
+ image = pipeline(prompt).images[0]
33
+ image.save("my_image.png")
34
+ ```
35
+
36
+ ## Training info
37
+
38
+ These are the key hyperparameters used during training:
39
+
40
+ * Epochs: 6
41
+ * Learning rate: 1e-05
42
+ * Batch size: 1
43
+ * Gradient accumulation steps: 4
44
+ * Image resolution: 512
45
+ * Mixed-precision: fp16
46
+
checkpoint-14500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4bac1f9e21c6acc343d2c09c97cf9bfa13d9ca4098f6f230815afd0fe269780
3
+ size 6876749715
checkpoint-14500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2c0f93c6cd86a094f38422da6906b0e8222f2591620effefbc67bad5311cab
3
+ size 14663
checkpoint-14500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:758b5efccc94ae3dce5ab02f9e56406db2e8470bcbc0b4c6cf4f237887f7af02
3
+ size 557
checkpoint-14500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbcb008f8dc46a29160ee9e407bab9c3574356d74be5b27f03ffaba17d470692
3
+ size 563
checkpoint-14500/unet/config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "sd-cartoon-faces-model/checkpoint-11500",
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
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
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
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "sample_size": 64,
53
+ "time_cond_proj_dim": null,
54
+ "time_embedding_act_fn": null,
55
+ "time_embedding_dim": null,
56
+ "time_embedding_type": "positional",
57
+ "timestep_post_act": null,
58
+ "transformer_layers_per_block": 1,
59
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "use_linear_projection": false
67
+ }
checkpoint-14500/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7abcb587558a76e5a56dce8b344f0a44f8d09fd26b8c756e18f01bd9da3ed948
3
+ size 3438167536
checkpoint-14500/unet_ema/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
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
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "decay": 0.9999,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dropout": 0.0,
33
+ "dual_cross_attention": false,
34
+ "encoder_hid_dim": null,
35
+ "encoder_hid_dim_type": null,
36
+ "flip_sin_to_cos": true,
37
+ "freq_shift": 0,
38
+ "in_channels": 4,
39
+ "inv_gamma": 1.0,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "min_decay": 0.0,
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "optimization_step": 3000,
51
+ "out_channels": 4,
52
+ "power": 0.6666666666666666,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "sample_size": 64,
58
+ "time_cond_proj_dim": null,
59
+ "time_embedding_act_fn": null,
60
+ "time_embedding_dim": null,
61
+ "time_embedding_type": "positional",
62
+ "timestep_post_act": null,
63
+ "transformer_layers_per_block": 1,
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": false
74
+ }
checkpoint-14500/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef65409ab4afaf0ffb6b1a6019d68e6554dcfd4e240baeeb4348de1cba0786d7
3
+ size 3438167536
checkpoint-15000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6891810b3ef080685186d8dbe803e25013c1ec7cbe897e1ae0de555c9f6f6be
3
+ size 6876749715
checkpoint-15000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e4247258b8c8c5100f7a9ee66f0f90cd199134cd1766f46a6860314ea18958
3
+ size 14663
checkpoint-15000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ad52168ca2fac679d8a62b9514f4be00d52a29ff4c454fab5128d5d41a32e6
3
+ size 557
checkpoint-15000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd3861b12ce8bab1de0854853d701de29b52e1f5098be09db4dd571459cfa2bf
3
+ size 563
checkpoint-15000/unet/config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "sd-cartoon-faces-model/checkpoint-11500",
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
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
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
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "sample_size": 64,
53
+ "time_cond_proj_dim": null,
54
+ "time_embedding_act_fn": null,
55
+ "time_embedding_dim": null,
56
+ "time_embedding_type": "positional",
57
+ "timestep_post_act": null,
58
+ "transformer_layers_per_block": 1,
59
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "use_linear_projection": false
67
+ }
checkpoint-15000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a585349a68aeb806408299d4f99ea0f5633cc6d0d8a1329956fd097760db32
3
+ size 3438167536
checkpoint-15000/unet_ema/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
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
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "decay": 0.9999,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dropout": 0.0,
33
+ "dual_cross_attention": false,
34
+ "encoder_hid_dim": null,
35
+ "encoder_hid_dim_type": null,
36
+ "flip_sin_to_cos": true,
37
+ "freq_shift": 0,
38
+ "in_channels": 4,
39
+ "inv_gamma": 1.0,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "min_decay": 0.0,
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "optimization_step": 3500,
51
+ "out_channels": 4,
52
+ "power": 0.6666666666666666,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "sample_size": 64,
58
+ "time_cond_proj_dim": null,
59
+ "time_embedding_act_fn": null,
60
+ "time_embedding_dim": null,
61
+ "time_embedding_type": "positional",
62
+ "timestep_post_act": null,
63
+ "transformer_layers_per_block": 1,
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": false
74
+ }
checkpoint-15000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3baf9124a34e8c61b69f0e5445b1f035dfea57c293ce7bec8d7efbf6d15e2295
3
+ size 3438167536
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/1696858589.9366672/events.out.tfevents.1696858589.aa1d505ac963.3709.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1769e18af3f7b5595ae2a426e940c21b10b7fa597528ffe917449d85804a2f
3
+ size 2258
logs/text2image-fine-tune/1696858589.9385805/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1696868180.564194/events.out.tfevents.1696868180.aa1d505ac963.42976.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:859dee8763742f897f2a7a2f8b072fda24239d2a8959cc1e1691404da5e906b0
3
+ size 2320
logs/text2image-fine-tune/1696868180.5659726/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: 'True'
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1696868236.4700205/events.out.tfevents.1696868236.aa1d505ac963.43269.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256a0b4356f135c6c515ce27385544a4eeeee84b53ae75b09bf8beb53cf8fc70
3
+ size 2320
logs/text2image-fine-tune/1696868236.4717777/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: '5000'
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1696868286.7558248/events.out.tfevents.1696868286.aa1d505ac963.43512.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d05adb8d59cf3176b6db620b10c043d915913d3a2084dec953dbdf08ccb1cc44
3
+ size 2363
logs/text2image-fine-tune/1696868286.757576/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /content/sd-cartoon-faces-model/checkpoint-5500
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1696868333.0287201/events.out.tfevents.1696868333.aa1d505ac963.43737.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178a1301f186c2a1807eb69b482f12c901ab595400ad87b59ce098dbefdf0205
3
+ size 2363
logs/text2image-fine-tune/1696868333.0305436/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /content/sd-cartoon-faces-model/checkpoint-5000
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1696876771.8024945/events.out.tfevents.1696876771.aa1d505ac963.78270.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6d2dcb4a12fa0ec94871ba756b553bb36e77d0cdf152325c0ed5c27b399cea3
3
+ size 2363
logs/text2image-fine-tune/1696876771.8045502/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /content/sd-cartoon-faces-model/checkpoint-9500
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1696880869.211845/events.out.tfevents.1696880869.aa1d505ac963.94988.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a23ab0488e304ce2af0d06dbb4c7e5d7ff1f694801c737867d0a8b13e34403c8
3
+ size 2364
logs/text2image-fine-tune/1696880869.2136056/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /content/sd-cartoon-faces-model/checkpoint-11500
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1696890174.7166543/events.out.tfevents.1696890174.aa1d505ac963.133152.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6383dd5ceb12e8b5f6253b3789145c19a2ebfc11f4aae70aeebea99d5d3d3812
3
+ size 2364
logs/text2image-fine-tune/1696890174.7184038/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /content/sd-cartoon-faces-model/checkpoint-15000
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1696890463.2686615/events.out.tfevents.1696890463.aa1d505ac963.134410.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85981e7218d7cf6c29e79a3d8a81f0944d96b1a4633d91eb5c77e2268a09c68e
3
+ size 2364
logs/text2image-fine-tune/1696890463.27048/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /content/sd-cartoon-faces-model/checkpoint-15000
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1696890634.3582013/events.out.tfevents.1696890634.aa1d505ac963.135158.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:271a2ab05ee1fdec1a952a72f77adcde5e658ab4c9548e8e792816da04a1b4cf
3
+ size 2364
logs/text2image-fine-tune/1696890634.3599777/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /content/sd-cartoon-faces-model/checkpoint-15000
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1696890884.8080351/events.out.tfevents.1696890884.aa1d505ac963.136224.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36dea15924f30652ed830ac20a3ca2c7512556b4402797c088c684cf06d9ef2
3
+ size 2364
logs/text2image-fine-tune/1696890884.8099892/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /content/sd-cartoon-faces-model/checkpoint-15000
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/1696891063.54499/events.out.tfevents.1696891063.aa1d505ac963.136996.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c71d716db28f963aaba667f1973157907e8fab829a6598a2754cf303172e612
3
+ size 2364
logs/text2image-fine-tune/1696891063.5467377/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: Skiittoo/cartoon-faces
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: true
17
+ hub_model_id: null
18
+ hub_token: null
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: 15000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 6
33
+ output_dir: sd-cartoon-faces-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: true
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: /content/sd-cartoon-faces-model/checkpoint-15000
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: null
48
+ use_8bit_adam: false
49
+ use_ema: true
50
+ validation_epochs: 5
logs/text2image-fine-tune/events.out.tfevents.1696858589.aa1d505ac963.3709.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:819534b3074840c9f05dd5e8cf0cc399c51d79fa1f65ca5bd0ac903493df1611
3
+ size 269461
logs/text2image-fine-tune/events.out.tfevents.1696868180.aa1d505ac963.42976.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f29c0c03435c4b9f370c9ba6566240de535d9a08d81b04e0e8528d81a83fb1f0
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1696868236.aa1d505ac963.43269.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0746e67c734286d43c0361e37186309c3f14e7147ce58a916c4d31e0afb6614
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1696868286.aa1d505ac963.43512.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7224a2575cb63fe51a9741fe74982c5d0596c66d53446e3e123e100a95cfe60c
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1696868333.aa1d505ac963.43737.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a12bb8b6267985a1543c5b6102f7e15c2bf3b3357a4ee6e98483b81ac2101e
3
+ size 245088
logs/text2image-fine-tune/events.out.tfevents.1696876771.aa1d505ac963.78270.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb1b1e6f9bd68597ee7f6f1893b7bb78562ce18126e3296cabbc5ead9087bfe
3
+ size 125038
logs/text2image-fine-tune/events.out.tfevents.1696880869.aa1d505ac963.94988.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:730b3f7002e54c62f0e63966be96d147162979a6d9ff38ee072d35abfb48b84e
3
+ size 171588
logs/text2image-fine-tune/events.out.tfevents.1696890174.aa1d505ac963.133152.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21c0a038c45bf91669c74284d3705ed45c87a34a104b40aa3fd3f8b4298080d
3
+ size 88