Hugging Face's logo

viktfb
/
sdxl-fashion-model

Text-to-Image
Diffusers
TensorBoard
Safetensors
StableDiffusionXLPipeline
stable-diffusion-xl
stable-diffusion-xl-diffusers
Inference Endpoints
Model card Files Metrics Community
viktfb commited on
Commit
0543416
•
1 Parent(s): c37e7af

End of training

Browse files
Files changed (45) hide show
  1. .gitattributes +4 -0
  2. README.md +24 -0
  3. checkpoint-1000/optimizer.bin +3 -0
  4. checkpoint-1000/random_states_0.pkl +3 -0
  5. checkpoint-1000/scaler.pt +3 -0
  6. checkpoint-1000/scheduler.bin +3 -0
  7. checkpoint-1000/unet/config.json +72 -0
  8. checkpoint-1000/unet/diffusion_pytorch_model.safetensors +3 -0
  9. checkpoint-2000/optimizer.bin +3 -0
  10. checkpoint-2000/random_states_0.pkl +3 -0
  11. checkpoint-2000/scaler.pt +3 -0
  12. checkpoint-2000/scheduler.bin +3 -0
  13. checkpoint-2000/unet/config.json +72 -0
  14. checkpoint-2000/unet/diffusion_pytorch_model.safetensors +3 -0
  15. checkpoint-3000/optimizer.bin +3 -0
  16. checkpoint-3000/random_states_0.pkl +3 -0
  17. checkpoint-3000/scaler.pt +3 -0
  18. checkpoint-3000/scheduler.bin +3 -0
  19. checkpoint-3000/unet/config.json +72 -0
  20. checkpoint-3000/unet/diffusion_pytorch_model.safetensors +3 -0
  21. image_0.png +3 -0
  22. image_1.png +3 -0
  23. image_2.png +3 -0
  24. image_3.png +3 -0
  25. logs/text2image-fine-tune-sdxl/1693894084.6221647/events.out.tfevents.1693894084.8cd71ab8b414.832.1 +3 -0
  26. logs/text2image-fine-tune-sdxl/1693894084.6258872/hparams.yml +52 -0
  27. logs/text2image-fine-tune-sdxl/events.out.tfevents.1693894084.8cd71ab8b414.832.0 +3 -0
  28. model_index.json +34 -0
  29. scheduler/scheduler_config.json +18 -0
  30. text_encoder/config.json +25 -0
  31. text_encoder/model.safetensors +3 -0
  32. text_encoder_2/config.json +25 -0
  33. text_encoder_2/model.safetensors +3 -0
  34. tokenizer/merges.txt +0 -0
  35. tokenizer/special_tokens_map.json +24 -0
  36. tokenizer/tokenizer_config.json +33 -0
  37. tokenizer/vocab.json +0 -0
  38. tokenizer_2/merges.txt +0 -0
  39. tokenizer_2/special_tokens_map.json +24 -0
  40. tokenizer_2/tokenizer_config.json +33 -0
  41. tokenizer_2/vocab.json +0 -0
  42. unet/config.json +72 -0
  43. unet/diffusion_pytorch_model.safetensors +3 -0
  44. vae/config.json +32 -0
  45. vae/diffusion_pytorch_model.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ image_0.png filter=lfs diff=lfs merge=lfs -text
37
+ image_1.png filter=lfs diff=lfs merge=lfs -text
38
+ image_2.png filter=lfs diff=lfs merge=lfs -text
39
+ image_3.png filter=lfs diff=lfs merge=lfs -text
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: None
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 - viktfb/sdxl-fashion-model
15
+
16
+ This pipeline was finetuned from **stabilityai/stable-diffusion-xl-base-1.0** on the **None** dataset. Below are some example images generated with the finetuned pipeline using the following prompt: a cute Sundar Pichai creature:
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: madebyollin/sdxl-vae-fp16-fix.
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52322f25aafd3585c54227b605e6a19215d35b6dd9d226214de43b7de980405d
3
+ size 5151956387
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b40b5f6ae4604148015b4a577d88d78f9a66747883ed0b7cd42fb99c8c18a1f
3
+ size 14663
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68cff80b680ddf6e7abbef98b5f336b97f9b5963e2209307f639383870e8cc71
3
+ size 557
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b7809f518a96a4fa4069f707e8433d0ae60949b56c65c39b0a64950d711aeb
3
+ size 563
checkpoint-1000/unet/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "sample_size": 128,
55
+ "time_cond_proj_dim": null,
56
+ "time_embedding_act_fn": null,
57
+ "time_embedding_dim": null,
58
+ "time_embedding_type": "positional",
59
+ "timestep_post_act": null,
60
+ "transformer_layers_per_block": [
61
+ 1,
62
+ 2,
63
+ 10
64
+ ],
65
+ "up_block_types": [
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "UpBlock2D"
69
+ ],
70
+ "upcast_attention": null,
71
+ "use_linear_projection": true
72
+ }
checkpoint-1000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b1c8de84ae20c5169b53e683caf0ccf26320f4b75e83927b2df29bedcc6f3eb
3
+ size 10270077736
checkpoint-2000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7d7e88b0336e898f132dc6e8701b2ecfb27ab8f34c4c3e56883bb31b1c0402f
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:f0d857719b52fe62f90611c25ca886983c33af97b3a4b51c5c88d640f3ebd936
3
+ size 14663
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 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "sample_size": 128,
55
+ "time_cond_proj_dim": null,
56
+ "time_embedding_act_fn": null,
57
+ "time_embedding_dim": null,
58
+ "time_embedding_type": "positional",
59
+ "timestep_post_act": null,
60
+ "transformer_layers_per_block": [
61
+ 1,
62
+ 2,
63
+ 10
64
+ ],
65
+ "up_block_types": [
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "UpBlock2D"
69
+ ],
70
+ "upcast_attention": null,
71
+ "use_linear_projection": true
72
+ }
checkpoint-2000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4442bee7c1666e5445bf906be01763b2db04bada857ed81d8515ec1d257a30dc
3
+ size 10270077736
checkpoint-3000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ba0e556f7b5430717e5d62a09ed3deae9169d853f32e07ab03ff0b30c9ac4d
3
+ size 5151956387
checkpoint-3000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc0b0031a1024e00aa1b380c3696080208966f2c89457ff4dfa53d528ede62f
3
+ size 14663
checkpoint-3000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1f9398b77268202e8e1465734a63d123b1ef11c27f20f2473677e9883a6869
3
+ size 557
checkpoint-3000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7be764cabe8a7de848698b3c50662a14a6678e140228a345f6150b6286c7a070
3
+ size 563
checkpoint-3000/unet/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "sample_size": 128,
55
+ "time_cond_proj_dim": null,
56
+ "time_embedding_act_fn": null,
57
+ "time_embedding_dim": null,
58
+ "time_embedding_type": "positional",
59
+ "timestep_post_act": null,
60
+ "transformer_layers_per_block": [
61
+ 1,
62
+ 2,
63
+ 10
64
+ ],
65
+ "up_block_types": [
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "UpBlock2D"
69
+ ],
70
+ "upcast_attention": null,
71
+ "use_linear_projection": true
72
+ }
checkpoint-3000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d753d9567da3effd039b848deecddb56fd74e5ac6e7188c11e9acd658b26a67
3
+ size 10270077736
image_0.png ADDED

Git LFS Details

  • SHA256: e77310e5c87c2166b77e5c1a62468368c78e125a397ca19f8352157721154d8c
  • Pointer size: 132 Bytes
  • Size of remote file: 1.3 MB
image_1.png ADDED

Git LFS Details

  • SHA256: def4ab70d55316eb9bda09166bbcc553c51edbfcc72a7fa8459cc77cb22f03e1
  • Pointer size: 132 Bytes
  • Size of remote file: 1.13 MB
image_2.png ADDED

Git LFS Details

  • SHA256: b89c16d3b13826974119311e0f0a9b00d51301aa4f5ce6ca1fdb3b1856659f70
  • Pointer size: 132 Bytes
  • Size of remote file: 1.42 MB
image_3.png ADDED

Git LFS Details

  • SHA256: 0dd9335fc2877b9f2a4df7bc3d4d4b60f753678cb6b428c6c0269c41d7f9974c
  • Pointer size: 132 Bytes
  • Size of remote file: 1.14 MB
logs/text2image-fine-tune-sdxl/1693894084.6221647/events.out.tfevents.1693894084.8cd71ab8b414.832.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ee213e2964b22ef40015f43c47176570de4f6e8edb6c881f0ca5cd57538d8e
3
+ size 2521
logs/text2image-fine-tune-sdxl/1693894084.6258872/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: additional_feature
8
+ center_crop: true
9
+ checkpointing_steps: 1000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: 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: 3000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ num_train_epochs: 27
32
+ num_validation_images: 4
33
+ output_dir: sdxl-fashion-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: madebyollin/sdxl-vae-fp16-fix
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: /root/train_fashion_v1
49
+ use_8bit_adam: true
50
+ use_ema: false
51
+ validation_epochs: 5
52
+ validation_prompt: a cute Sundar Pichai creature
logs/text2image-fine-tune-sdxl/events.out.tfevents.1693894084.8cd71ab8b414.832.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba1ec91ba6cb23ff11293ae31f8f89ec8c9c4cb94c46e5053f4d5c1721d566a0
3
+ size 34948798
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/f898a3e026e802f68796b95e9702464bac78d76f/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": "4.33.0",
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/f898a3e026e802f68796b95e9702464bac78d76f/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": "4.33.0",
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
+ }
tokenizer_2/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": "!",
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_2/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "sample_size": 128,
55
+ "time_cond_proj_dim": null,
56
+ "time_embedding_act_fn": null,
57
+ "time_embedding_dim": null,
58
+ "time_embedding_type": "positional",
59
+ "timestep_post_act": null,
60
+ "transformer_layers_per_block": [
61
+ 1,
62
+ 2,
63
+ 10
64
+ ],
65
+ "up_block_types": [
66
+ "CrossAttnUpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "UpBlock2D"
69
+ ],
70
+ "upcast_attention": null,
71
+ "use_linear_projection": true
72
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d753d9567da3effd039b848deecddb56fd74e5ac6e7188c11e9acd658b26a67
3
+ size 10270077736
vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "madebyollin/sdxl-vae-fp16-fix",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": false,
19
+ "in_channels": 3,
20
+ "latent_channels": 4,
21
+ "layers_per_block": 2,
22
+ "norm_num_groups": 32,
23
+ "out_channels": 3,
24
+ "sample_size": 512,
25
+ "scaling_factor": 0.13025,
26
+ "up_block_types": [
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D"
31
+ ]
32
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
3
+ size 167335342