Hugging Face's logo

spockren
/
sd-naruto-model

Text-to-Image
Diffusers
TensorBoard
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
diffusers-training
Inference Endpoints
Model card Files Metrics Community
1
spockren commited on
Commit
204a017
•
1 Parent(s): 79d1d24

Upload folder using huggingface_hub

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 +66 -0
  2. checkpoint-14000/optimizer.bin +3 -0
  3. checkpoint-14000/random_states_0.pkl +3 -0
  4. checkpoint-14000/scaler.pt +3 -0
  5. checkpoint-14000/scheduler.bin +3 -0
  6. checkpoint-14000/unet/config.json +68 -0
  7. checkpoint-14000/unet/diffusion_pytorch_model.safetensors +3 -0
  8. checkpoint-14000/unet_ema/config.json +75 -0
  9. checkpoint-14000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  10. checkpoint-14500/optimizer.bin +3 -0
  11. checkpoint-14500/random_states_0.pkl +3 -0
  12. checkpoint-14500/scaler.pt +3 -0
  13. checkpoint-14500/scheduler.bin +3 -0
  14. checkpoint-14500/unet/config.json +68 -0
  15. checkpoint-14500/unet/diffusion_pytorch_model.safetensors +3 -0
  16. checkpoint-14500/unet_ema/config.json +75 -0
  17. checkpoint-14500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  18. checkpoint-15000/optimizer.bin +3 -0
  19. checkpoint-15000/random_states_0.pkl +3 -0
  20. checkpoint-15000/scaler.pt +3 -0
  21. checkpoint-15000/scheduler.bin +3 -0
  22. checkpoint-15000/unet/config.json +68 -0
  23. checkpoint-15000/unet/diffusion_pytorch_model.safetensors +3 -0
  24. checkpoint-15000/unet_ema/config.json +75 -0
  25. checkpoint-15000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  26. feature_extractor/preprocessor_config.json +27 -0
  27. logs/text2image-fine-tune/1721297358.0539234/events.out.tfevents.1721297358.autodl-container-db4a40b195-60ebac9c.3089.1 +3 -0
  28. logs/text2image-fine-tune/1721297358.0551429/hparams.yml +55 -0
  29. logs/text2image-fine-tune/1721300210.5448987/events.out.tfevents.1721300210.autodl-container-db4a40b195-60ebac9c.1215.1 +3 -0
  30. logs/text2image-fine-tune/1721300210.546106/hparams.yml +55 -0
  31. logs/text2image-fine-tune/1721300341.25598/events.out.tfevents.1721300341.autodl-container-db4a40b195-60ebac9c.1325.1 +3 -0
  32. logs/text2image-fine-tune/1721300341.2572157/hparams.yml +55 -0
  33. logs/text2image-fine-tune/1721313875.276809/events.out.tfevents.1721313875.autodl-container-db4a40b195-60ebac9c.1168.1 +3 -0
  34. logs/text2image-fine-tune/1721313875.2780526/hparams.yml +55 -0
  35. logs/text2image-fine-tune/1721314076.4097009/events.out.tfevents.1721314076.autodl-container-db4a40b195-60ebac9c.1282.1 +3 -0
  36. logs/text2image-fine-tune/1721314076.4109404/hparams.yml +55 -0
  37. logs/text2image-fine-tune/1721317490.2784019/events.out.tfevents.1721317490.autodl-container-db4a40b195-60ebac9c.2847.1 +3 -0
  38. logs/text2image-fine-tune/1721317490.279717/hparams.yml +55 -0
  39. logs/text2image-fine-tune/1721317818.9334624/events.out.tfevents.1721317818.autodl-container-db4a40b195-60ebac9c.3028.1 +3 -0
  40. logs/text2image-fine-tune/1721317818.9347064/hparams.yml +55 -0
  41. logs/text2image-fine-tune/1721319061.1388721/events.out.tfevents.1721319061.autodl-container-db4a40b195-60ebac9c.3575.1 +3 -0
  42. logs/text2image-fine-tune/1721319061.1402483/hparams.yml +55 -0
  43. logs/text2image-fine-tune/events.out.tfevents.1721297358.autodl-container-db4a40b195-60ebac9c.3089.0 +3 -0
  44. logs/text2image-fine-tune/events.out.tfevents.1721300210.autodl-container-db4a40b195-60ebac9c.1215.0 +3 -0
  45. logs/text2image-fine-tune/events.out.tfevents.1721300341.autodl-container-db4a40b195-60ebac9c.1325.0 +3 -0
  46. logs/text2image-fine-tune/events.out.tfevents.1721313875.autodl-container-db4a40b195-60ebac9c.1168.0 +3 -0
  47. logs/text2image-fine-tune/events.out.tfevents.1721314076.autodl-container-db4a40b195-60ebac9c.1282.0 +3 -0
  48. logs/text2image-fine-tune/events.out.tfevents.1721317490.autodl-container-db4a40b195-60ebac9c.2847.0 +3 -0
  49. logs/text2image-fine-tune/events.out.tfevents.1721317818.autodl-container-db4a40b195-60ebac9c.3028.0 +3 -0
  50. logs/text2image-fine-tune/events.out.tfevents.1721319061.autodl-container-db4a40b195-60ebac9c.3575.0 +3 -0
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: runwayml/stable-diffusion-v1-5
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ tags:
6
+ - stable-diffusion
7
+ - stable-diffusion-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - diffusers-training
11
+ inference: true
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+
18
+ # Text-to-image finetuning - spockren/sd-naruto-model
19
+
20
+ This pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **lambdalabs/naruto-blip-captions** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A <cat-toy> backpack']:
21
+
22
+ ![val_imgs_grid](./val_imgs_grid.png)
23
+
24
+
25
+ ## Pipeline usage
26
+
27
+ You can use the pipeline like so:
28
+
29
+ ```python
30
+ from diffusers import DiffusionPipeline
31
+ import torch
32
+
33
+ pipeline = DiffusionPipeline.from_pretrained("spockren/sd-naruto-model", torch_dtype=torch.float16)
34
+ prompt = "A <cat-toy> backpack"
35
+ image = pipeline(prompt).images[0]
36
+ image.save("my_image.png")
37
+ ```
38
+
39
+ ## Training info
40
+
41
+ These are the key hyperparameters used during training:
42
+
43
+ * Epochs: 50
44
+ * Learning rate: 1e-05
45
+ * Batch size: 1
46
+ * Gradient accumulation steps: 4
47
+ * Image resolution: 512
48
+ * Mixed-precision: fp16
49
+
50
+
51
+
52
+ ## Intended uses & limitations
53
+
54
+ #### How to use
55
+
56
+ ```python
57
+ # TODO: add an example code snippet for running this diffusion pipeline
58
+ ```
59
+
60
+ #### Limitations and bias
61
+
62
+ [TODO: provide examples of latent issues and potential remediations]
63
+
64
+ ## Training details
65
+
66
+ [TODO: describe the data used to train the model]
checkpoint-14000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48aa12c03387aa4836666b84a4094c2b644fbfb92577ec2eedb841aaa1f80ffd
3
+ size 6876750164
checkpoint-14000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fbfa5d7df68b1fd9bb734ecba668973b5677a864eb9c3b78338bc7487b4abcd
3
+ size 14344
checkpoint-14000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8972e137dff582ed156c48a434d8d5304443a88bca38ef8e7f0e80298e6f0533
3
+ size 988
checkpoint-14000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee032204bba8930df676bada22732e1d1d4fce2e74de1dd6725c0a0c5840cb19
3
+ size 1000
checkpoint-14000/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "sd-naruto-model/checkpoint-13000",
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
+ "reverse_transformer_layers_per_block": null,
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
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
checkpoint-14000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f81fdef206c93f4f02ca195d86aea3970219a8384ad119bcca9657431ee60da
3
+ size 3438167536
checkpoint-14000/unet_ema/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
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": 1000,
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
+ "reverse_transformer_layers_per_block": null,
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
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "update_after_step": 0,
73
+ "use_ema_warmup": false,
74
+ "use_linear_projection": false
75
+ }
checkpoint-14000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5ee1169f58ac26c97ad47d511a3f779d1410115edc587bee9fe77115fdec45
3
+ size 3438167536
checkpoint-14500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3bf0a1a15463de9ec5b6d6a1a9b0945415a2e9cd255064578852a962d37888c
3
+ size 6876750164
checkpoint-14500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c75a40346ba3a197e7bc9533d8df2923f54a4cef3d375439003dccd41b7d34
3
+ size 14344
checkpoint-14500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231bcf5c942fc3abf338cd58a118326be49d93838524b0e91622d948c69dd19a
3
+ size 988
checkpoint-14500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dde392c63867243f73026beb29f7cdbfa91c220c86daca9f55482421fdc0eb3
3
+ size 1000
checkpoint-14500/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "sd-naruto-model/checkpoint-13000",
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
+ "reverse_transformer_layers_per_block": null,
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
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
checkpoint-14500/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20e0f8edd06d41e58840281b7274b6f52d439c56efa66a0c2298d03af5d5c53e
3
+ size 3438167536
checkpoint-14500/unet_ema/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
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": 1500,
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
+ "reverse_transformer_layers_per_block": null,
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
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "update_after_step": 0,
73
+ "use_ema_warmup": false,
74
+ "use_linear_projection": false
75
+ }
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:eb7cca58610d9bda93c396df86627cf95973cf956884aac85da153950f536761
3
+ size 3438167536
checkpoint-15000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e418aa6ce0dd0d389ed1c539e99f7b093785464cbe40d835ef7d4a5944fda9d8
3
+ size 6876750164
checkpoint-15000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42787719e4c1f1f0fb610a483c2812b09550a14a32b8f42a70cacde126d3e9a
3
+ size 14344
checkpoint-15000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a39f7a55c8dddbd7d0fc53178dd90ac90e20a16d2400b31f503b250a356bc5
3
+ size 988
checkpoint-15000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9700d5c8fee00359a65bf5fc823611a3cb001ecff42360c896b8cb0139e201ee
3
+ size 1000
checkpoint-15000/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "sd-naruto-model/checkpoint-13000",
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
+ "reverse_transformer_layers_per_block": null,
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
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
checkpoint-15000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727795dcd9861238b2164af1ff90c8a3ba1b80daadaf73f750631c927d62b63a
3
+ size 3438167536
checkpoint-15000/unet_ema/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
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": 2000,
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
+ "reverse_transformer_layers_per_block": null,
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
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "update_after_step": 0,
73
+ "use_ema_warmup": false,
74
+ "use_linear_projection": false
75
+ }
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:f5aa7abac474f95b390bddda251f7a66220386406fbf98752e9649cc37312d37
3
+ size 3438167536
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
logs/text2image-fine-tune/1721297358.0539234/events.out.tfevents.1721297358.autodl-container-db4a40b195-60ebac9c.3089.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56645c62c2f89cd131803480fbafd95733b470ce22df2b98316b7cca7ec4ffd2
3
+ size 2467
logs/text2image-fine-tune/1721297358.0551429/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: lambdalabs/naruto-blip-captions
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 15000
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 50
36
+ offload_ema: false
37
+ output_dir: sd-naruto-model
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: null
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/1721300210.5448987/events.out.tfevents.1721300210.autodl-container-db4a40b195-60ebac9c.1215.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4372974edb299977ceeea6c7bc83286680c428fe7873ec25855b1374ccdac1b2
3
+ size 2531
logs/text2image-fine-tune/1721300210.546106/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: lambdalabs/naruto-blip-captions
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 15000
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 50
36
+ offload_ema: false
37
+ output_dir: sd-naruto-model
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: latest
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/1721300341.25598/events.out.tfevents.1721300341.autodl-container-db4a40b195-60ebac9c.1325.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d08bfaef6e1e5ed609c2eabf5714d7bbe26768d1e7ee30be1f89cf8721e11b
3
+ size 2615
logs/text2image-fine-tune/1721300341.2572157/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: lambdalabs/naruto-blip-captions
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 15000
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 50
36
+ offload_ema: false
37
+ output_dir: sd-naruto-model
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: /root/autodl-tmp/spockren/diffusers/examples/text_to_image/sd-naruto-model/checkpoint-1500
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/1721313875.276809/events.out.tfevents.1721313875.autodl-container-db4a40b195-60ebac9c.1168.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b7b6b74c1997b4f7529a2852a9afac3658ce5b93154c012c2d69ed1c91daf8
3
+ size 2619
logs/text2image-fine-tune/1721313875.2780526/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: lambdalabs/naruto-blip-captions
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 15000
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 50
36
+ offload_ema: false
37
+ output_dir: sd-naruto-model
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: /root/autodl-tmp/spockren/diffusers/examples/text_to_image/sd-naruto-model/checkpoint-15=13000
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/1721314076.4097009/events.out.tfevents.1721314076.autodl-container-db4a40b195-60ebac9c.1282.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0b193feee548f95f8d983bc993f4f1e3c9864baebee6baf92b9b5eba4ea1b6
3
+ size 2616
logs/text2image-fine-tune/1721314076.4109404/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: lambdalabs/naruto-blip-captions
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 15000
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 50
36
+ offload_ema: false
37
+ output_dir: sd-naruto-model
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: /root/autodl-tmp/spockren/diffusers/examples/text_to_image/sd-naruto-model/checkpoint-13000
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/1721317490.2784019/events.out.tfevents.1721317490.autodl-container-db4a40b195-60ebac9c.2847.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0951a4da913a6596a64c863c0bf2d327aefad8d97ec817f546121e97e5eea74
3
+ size 2616
logs/text2image-fine-tune/1721317490.279717/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: lambdalabs/naruto-blip-captions
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 15000
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 50
36
+ offload_ema: false
37
+ output_dir: sd-naruto-model
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: /root/autodl-tmp/spockren/diffusers/examples/text_to_image/sd-naruto-model/checkpoint-15000
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/1721317818.9334624/events.out.tfevents.1721317818.autodl-container-db4a40b195-60ebac9c.3028.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc462c4b08d71c0b776871b81159557f7961d8b6f666b27d14bc155d3013a3d9
3
+ size 2616
logs/text2image-fine-tune/1721317818.9347064/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: lambdalabs/naruto-blip-captions
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 15000
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 50
36
+ offload_ema: false
37
+ output_dir: sd-naruto-model
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: /root/autodl-tmp/spockren/diffusers/examples/text_to_image/sd-naruto-model/checkpoint-15000
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/1721319061.1388721/events.out.tfevents.1721319061.autodl-container-db4a40b195-60ebac9c.3575.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:281a061ef3a426495b695189848e78f168796eae5ab90ba0a4b268d40d136f41
3
+ size 2616
logs/text2image-fine-tune/1721319061.1402483/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: lambdalabs/naruto-blip-captions
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ foreach_ema: false
18
+ gradient_accumulation_steps: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 15000
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 50
36
+ offload_ema: false
37
+ output_dir: sd-naruto-model
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: /root/autodl-tmp/spockren/diffusers/examples/text_to_image/sd-naruto-model/checkpoint-15000
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1721297358.autodl-container-db4a40b195-60ebac9c.3089.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a11dd7ceccf088ae7373f469195cd259c921755867d0bf983060aa47917ee1
3
+ size 97961
logs/text2image-fine-tune/events.out.tfevents.1721300210.autodl-container-db4a40b195-60ebac9c.1215.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e7ac74adc25b756a83f79602452e8d0ab6b0bfe9a2b18f5ea8a110d1357c86
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1721300341.autodl-container-db4a40b195-60ebac9c.1325.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:605492124a9f416772d36e7dffd905a90a2ec40914d2630861adcde4abfacd84
3
+ size 574907
logs/text2image-fine-tune/events.out.tfevents.1721313875.autodl-container-db4a40b195-60ebac9c.1168.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c6d677f398e11d1574851f854e8bd74912cac4951ec733e445b0d7ef4e8eac
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1721314076.autodl-container-db4a40b195-60ebac9c.1282.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364c0c0129eb65c061b156ce86767b609d637c5278b0c3874918df660824cf2b
3
+ size 98088
logs/text2image-fine-tune/events.out.tfevents.1721317490.autodl-container-db4a40b195-60ebac9c.2847.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da8cb64347d4c05b20489cfa61974f08c6a5793637fd9ebac6f262620631e5f
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1721317818.autodl-container-db4a40b195-60ebac9c.3028.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05371371ac96cc691adc1959477b5f677666fe675e52c47380991e57f73d249e
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1721319061.autodl-container-db4a40b195-60ebac9c.3575.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06cd8c03565a67f7c28fa4a3d1d04fc019f2132e2edeb29542251937f9c0dee3
3
+ size 88