Hugging Face's logo

y22ma
/
sdxl-dabble-model

Text-to-Image
Diffusers
TensorBoard
Safetensors
StableDiffusionXLPipeline
stable-diffusion-xl
stable-diffusion-xl-diffusers
Inference Endpoints
Model card Files Metrics Community
y22ma commited on
Commit
8afd20e
·
1 Parent(s): c575204

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 +24 -0
  2. checkpoint-10000/optimizer.bin +3 -0
  3. checkpoint-10000/random_states_0.pkl +3 -0
  4. checkpoint-10000/scaler.pt +3 -0
  5. checkpoint-10000/scheduler.bin +3 -0
  6. checkpoint-10000/unet/config.json +71 -0
  7. checkpoint-10000/unet/diffusion_pytorch_model.safetensors +3 -0
  8. checkpoint-2000/optimizer.bin +3 -0
  9. checkpoint-2000/random_states_0.pkl +3 -0
  10. checkpoint-2000/scaler.pt +3 -0
  11. checkpoint-2000/scheduler.bin +3 -0
  12. checkpoint-2000/unet/config.json +71 -0
  13. checkpoint-2000/unet/diffusion_pytorch_model.safetensors +3 -0
  14. checkpoint-4000/optimizer.bin +3 -0
  15. checkpoint-4000/random_states_0.pkl +3 -0
  16. checkpoint-4000/scaler.pt +3 -0
  17. checkpoint-4000/scheduler.bin +3 -0
  18. checkpoint-4000/unet/config.json +71 -0
  19. checkpoint-4000/unet/diffusion_pytorch_model.safetensors +3 -0
  20. checkpoint-6000/optimizer.bin +3 -0
  21. checkpoint-6000/random_states_0.pkl +3 -0
  22. checkpoint-6000/scaler.pt +3 -0
  23. checkpoint-6000/scheduler.bin +3 -0
  24. checkpoint-6000/unet/config.json +71 -0
  25. checkpoint-6000/unet/diffusion_pytorch_model.safetensors +3 -0
  26. checkpoint-8000/optimizer.bin +3 -0
  27. checkpoint-8000/random_states_0.pkl +3 -0
  28. checkpoint-8000/scaler.pt +3 -0
  29. checkpoint-8000/scheduler.bin +3 -0
  30. checkpoint-8000/unet/config.json +71 -0
  31. checkpoint-8000/unet/diffusion_pytorch_model.safetensors +3 -0
  32. image_0.png +0 -0
  33. image_1.png +0 -0
  34. image_2.png +0 -0
  35. image_3.png +0 -0
  36. logs/text2image-fine-tune-sdxl/1693603937.15988/events.out.tfevents.1693603937.modal.10.1 +3 -0
  37. logs/text2image-fine-tune-sdxl/1693603937.5622382/hparams.yml +52 -0
  38. logs/text2image-fine-tune-sdxl/events.out.tfevents.1693603937.modal.10.0 +3 -0
  39. model_index.json +34 -0
  40. scheduler/scheduler_config.json +18 -0
  41. text_encoder/config.json +25 -0
  42. text_encoder/model.safetensors +3 -0
  43. text_encoder_2/config.json +25 -0
  44. text_encoder_2/model.safetensors +3 -0
  45. tokenizer/merges.txt +0 -0
  46. tokenizer/special_tokens_map.json +24 -0
  47. tokenizer/tokenizer_config.json +33 -0
  48. tokenizer/vocab.json +0 -0
  49. tokenizer_2/merges.txt +0 -0
  50. tokenizer_2/special_tokens_map.json +24 -0
README.md ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
5
+ dataset: y22ma/Dabble-interior-captions
6
+ tags:
7
+ - stable-diffusion-xl
8
+ - stable-diffusion-xl-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ inference: true
12
+ ---
13
+
14
+ # Text-to-image finetuning - y22ma/sdxl-dabble-model
15
+
16
+ This pipeline was finetuned from **stabilityai/stable-diffusion-xl-base-1.0** on the **y22ma/Dabble-interior-captions** dataset. Below are some example images generated with the finetuned pipeline using the following prompt: a beautiful living room:
17
+
18
+ ![img_0](./image_0.png)
19
+ ![img_1](./image_1.png)
20
+ ![img_2](./image_2.png)
21
+ ![img_3](./image_3.png)
22
+
23
+
24
+ Special VAE used for training: None.
checkpoint-10000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208e61c62e8b1d673f63c4208ed5588834e9341af366d902c34f0c2183e8342c
3
+ size 5151956387
checkpoint-10000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2731bd0f489bca1f581e949aabfb9d62cdd3a753eec4492b22a5c7de73894fe2
3
+ size 14727
checkpoint-10000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be2ad76dcbc923b00e6a142f6db62aad4a46c47bb83864ccb68ddc899d0ce78
3
+ size 557
checkpoint-10000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1e67bf679a34e18df9bb0f741ca0e698871230c037bdff2e97a5522cd2c3ce3
3
+ size 563
checkpoint-10000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
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": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
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
+ "layers_per_block": 2,
40
+ "mid_block_only_cross_attention": null,
41
+ "mid_block_scale_factor": 1,
42
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
43
+ "norm_eps": 1e-05,
44
+ "norm_num_groups": 32,
45
+ "num_attention_heads": null,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": 2816,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "sample_size": 128,
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": [
60
+ 1,
61
+ 2,
62
+ 10
63
+ ],
64
+ "up_block_types": [
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "UpBlock2D"
68
+ ],
69
+ "upcast_attention": null,
70
+ "use_linear_projection": true
71
+ }
checkpoint-10000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:876ef3ca6584b92dc1e15b28e3de1b58c1103dd260c7782d0c2b8f8b395546f0
3
+ size 10270077736
checkpoint-2000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7922fe60f45b3af0cab23bec7f5dda02d5bfadc0c6c96f67a31cdf0303d03113
3
+ size 5151956387
checkpoint-2000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:949a65526d2a62e19d315bcba9373380de5d3011002f52365fab408792abd8de
3
+ size 14727
checkpoint-2000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2de9749828adacdf103bf6e9592702bb7067a2c1df27dd62ab38c1eb8c070f
3
+ size 557
checkpoint-2000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223436be2788dc84d53d2c2e4303ade14df55ba01000214c925cafe35a59ad75
3
+ size 563
checkpoint-2000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
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": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
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
+ "layers_per_block": 2,
40
+ "mid_block_only_cross_attention": null,
41
+ "mid_block_scale_factor": 1,
42
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
43
+ "norm_eps": 1e-05,
44
+ "norm_num_groups": 32,
45
+ "num_attention_heads": null,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": 2816,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "sample_size": 128,
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": [
60
+ 1,
61
+ 2,
62
+ 10
63
+ ],
64
+ "up_block_types": [
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "UpBlock2D"
68
+ ],
69
+ "upcast_attention": null,
70
+ "use_linear_projection": true
71
+ }
checkpoint-2000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:096a4d89ebf04f6549539445bd66b1063dd5964a97b8accf05306d87c9aeeabe
3
+ size 10270077736
checkpoint-4000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:501f381680a90d2f651c71ccc186e534aa7a2701eb0538d76e5ce6429e3b6f6f
3
+ size 5151956387
checkpoint-4000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a86ad541b50026a460cfc3787a111a2601e37eff6303e47ff543ffc3d8d6a4e7
3
+ size 14791
checkpoint-4000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09a61ecdaa4a69ba865e0b9e19169660549c34c60a83537ab5ece413678520ab
3
+ size 557
checkpoint-4000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4f0b1924463e34e3dc4a27e2ebe7ee7a43bc8be36d5cff2a75500ff628d083
3
+ size 563
checkpoint-4000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
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": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
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
+ "layers_per_block": 2,
40
+ "mid_block_only_cross_attention": null,
41
+ "mid_block_scale_factor": 1,
42
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
43
+ "norm_eps": 1e-05,
44
+ "norm_num_groups": 32,
45
+ "num_attention_heads": null,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": 2816,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "sample_size": 128,
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": [
60
+ 1,
61
+ 2,
62
+ 10
63
+ ],
64
+ "up_block_types": [
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "UpBlock2D"
68
+ ],
69
+ "upcast_attention": null,
70
+ "use_linear_projection": true
71
+ }
checkpoint-4000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6374a26bd9e2f47fa015edda55f9f2effbf3ca75f80fffa827d3f64d1d91b603
3
+ size 10270077736
checkpoint-6000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11516b13b3790a146926c057975a948e54b9dc112b1f14ab0ee0cb04e6a470a
3
+ size 5151956387
checkpoint-6000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc16d218b52bfc77bc4b47c618578e23f39b8051f06a4af0021651ff9f37e804
3
+ size 14727
checkpoint-6000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a00ef97fc41c0d653df466126d855f16646dd10726d3ac99a23f55ca70ec19a
3
+ size 557
checkpoint-6000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2045310aaf65b27b6e6ead5f219951d64b6a5501ced0aba650be82bfb33d51a6
3
+ size 563
checkpoint-6000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
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": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
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
+ "layers_per_block": 2,
40
+ "mid_block_only_cross_attention": null,
41
+ "mid_block_scale_factor": 1,
42
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
43
+ "norm_eps": 1e-05,
44
+ "norm_num_groups": 32,
45
+ "num_attention_heads": null,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": 2816,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "sample_size": 128,
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": [
60
+ 1,
61
+ 2,
62
+ 10
63
+ ],
64
+ "up_block_types": [
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "UpBlock2D"
68
+ ],
69
+ "upcast_attention": null,
70
+ "use_linear_projection": true
71
+ }
checkpoint-6000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d45d3d7e41518001db20361054ddd3cad1384fee24907050e7bfe8ba67d7aec
3
+ size 10270077736
checkpoint-8000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d0f220dd3b6b1bfdee50d81d94802bc165956811afad9332f2ce860d20ba82
3
+ size 5151956387
checkpoint-8000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7147b55914af4c04eda7e9fd1e222677e6d9186d48df51b22db913ea4ced1365
3
+ size 14727
checkpoint-8000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b278cd6e09360f31a3d837f80dee4c2ce4d9c9d186a939ecf157e1a0deb793f3
3
+ size 557
checkpoint-8000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ab9dd6e8e22e4e6e87a9b8214953fa6c2e764a27309f3c2d1a03608e2cec8c1
3
+ size 563
checkpoint-8000/unet/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
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": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
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
+ "layers_per_block": 2,
40
+ "mid_block_only_cross_attention": null,
41
+ "mid_block_scale_factor": 1,
42
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
43
+ "norm_eps": 1e-05,
44
+ "norm_num_groups": 32,
45
+ "num_attention_heads": null,
46
+ "num_class_embeds": null,
47
+ "only_cross_attention": false,
48
+ "out_channels": 4,
49
+ "projection_class_embeddings_input_dim": 2816,
50
+ "resnet_out_scale_factor": 1.0,
51
+ "resnet_skip_time_act": false,
52
+ "resnet_time_scale_shift": "default",
53
+ "sample_size": 128,
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": [
60
+ 1,
61
+ 2,
62
+ 10
63
+ ],
64
+ "up_block_types": [
65
+ "CrossAttnUpBlock2D",
66
+ "CrossAttnUpBlock2D",
67
+ "UpBlock2D"
68
+ ],
69
+ "upcast_attention": null,
70
+ "use_linear_projection": true
71
+ }
checkpoint-8000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e43149c7b40ffe4ebd19fca29ad34f0311c36e1b78bb57bb149f9ca9aa48cf1
3
+ size 10270077736
image_0.png ADDED
image_1.png ADDED
image_2.png ADDED
image_3.png ADDED
logs/text2image-fine-tune-sdxl/1693603937.15988/events.out.tfevents.1693603937.modal.10.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976288b77e4f023275947f93ac8a027d8d216a94f77c7049d363265d686534b2
3
+ size 2348
logs/text2image-fine-tune-sdxl/1693603937.5622382/hparams.yml ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 2000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: y22ma/Dabble-interior-captions
14
+ enable_xformers_memory_efficient_attention: true
15
+ force_snr_gamma: false
16
+ gradient_accumulation_steps: 4
17
+ gradient_checkpointing: true
18
+ hub_model_id: null
19
+ hub_token: null
20
+ image_column: image
21
+ learning_rate: 1.0e-06
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: 10000
29
+ mixed_precision: null
30
+ noise_offset: 0
31
+ num_train_epochs: 87
32
+ num_validation_images: 4
33
+ output_dir: /sdxl-dabble-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
36
+ pretrained_vae_model_name_or_path: null
37
+ proportion_empty_prompts: 0.2
38
+ push_to_hub: true
39
+ random_flip: true
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: null
46
+ snr_gamma: null
47
+ train_batch_size: 1
48
+ train_data_dir: null
49
+ use_8bit_adam: true
50
+ use_ema: false
51
+ validation_epochs: 5
52
+ validation_prompt: a beautiful living room
logs/text2image-fine-tune-sdxl/events.out.tfevents.1693603937.modal.10.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:814e6ba8c559beb2976cce2c3d86c221744849652d064043d1de45e9851f8763
3
+ size 724489
model_index.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionXLPipeline",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
5
+ "force_zeros_for_empty_prompt": true,
6
+ "scheduler": [
7
+ "diffusers",
8
+ "EulerDiscreteScheduler"
9
+ ],
10
+ "text_encoder": [
11
+ "transformers",
12
+ "CLIPTextModel"
13
+ ],
14
+ "text_encoder_2": [
15
+ "transformers",
16
+ "CLIPTextModelWithProjection"
17
+ ],
18
+ "tokenizer": [
19
+ "transformers",
20
+ "CLIPTokenizer"
21
+ ],
22
+ "tokenizer_2": [
23
+ "transformers",
24
+ "CLIPTokenizer"
25
+ ],
26
+ "unet": [
27
+ "diffusers",
28
+ "UNet2DConditionModel"
29
+ ],
30
+ "vae": [
31
+ "diffusers",
32
+ "AutoencoderKL"
33
+ ]
34
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "EulerDiscreteScheduler",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "interpolation_type": "linear",
9
+ "num_train_timesteps": 1000,
10
+ "prediction_type": "epsilon",
11
+ "sample_max_value": 1.0,
12
+ "set_alpha_to_one": false,
13
+ "skip_prk_steps": true,
14
+ "steps_offset": 1,
15
+ "timestep_spacing": "leading",
16
+ "trained_betas": null,
17
+ "use_karras_sigmas": false
18
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/text_encoder",
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": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 768,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.32.1",
24
+ "vocab_size": 49408
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
3
+ size 246144152
text_encoder_2/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/text_encoder_2",
3
+ "architectures": [
4
+ "CLIPTextModelWithProjection"
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": 1280,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 5120,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 20,
19
+ "num_hidden_layers": 32,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 1280,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.32.1",
24
+ "vocab_size": 49408
25
+ }
text_encoder_2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
3
+ size 1389382176
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": "<|endoftext|>",
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
 
tokenizer_2/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/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
+ }