Hugging Face's logo

kmpartner
/
sdxs-09fttest

Text-to-Image
Diffusers
TensorBoard
Safetensors
StableDiffusionPipeline
Model card Files
xet
 Metrics Community
kmpartner commited on
Commit
28b2c82
·
verified ·
1 Parent(s): def1b3c

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. checkpoint-6000/optimizer.bin +3 -0
  2. checkpoint-6000/random_states_0.pkl +3 -0
  3. checkpoint-6000/scaler.pt +3 -0
  4. checkpoint-6000/scheduler.bin +3 -0
  5. checkpoint-6000/unet/config.json +73 -0
  6. checkpoint-6000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. checkpoint-6000/unet_ema/config.json +80 -0
  8. checkpoint-6000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  9. logs/text2image-fine-tune/1716963695.1039982/events.out.tfevents.1716963695.5bb9e31bd71a.2171.1 +3 -0
  10. logs/text2image-fine-tune/1716963695.1110828/hparams.yml +53 -0
  11. logs/text2image-fine-tune/events.out.tfevents.1716963695.5bb9e31bd71a.2171.0 +3 -0
  12. model_index.json +1 -1
  13. scheduler/scheduler_config.json +1 -1
  14. text_encoder/config.json +1 -1
  15. unet/config.json +2 -2
  16. unet/diffusion_pytorch_model.safetensors +1 -1
  17. vae/config.json +1 -1
checkpoint-6000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a3b0428c9e6aa0f28fecf7d9e66a7df4a188d818a9745bbe1c4f5421c188ea7
3
+ size 2625718404
checkpoint-6000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60db28b2514a28b193cff8d1909cbe6de027fc116f9d6c7798d97182a4eb3264
3
+ size 14344
checkpoint-6000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23c6abec96b9d238cb94e3e6ca47ebac7366e65b2c1f7f780949153075612b6e
3
+ size 988
checkpoint-6000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee5dfbcb11f39797466c733b73a4b72d5ce9cd980aa33b83191eda39b8f80d9
3
+ size 1000
checkpoint-6000/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "sdxs-09fttest/checkpoint-5000",
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": [
10
+ 8,
11
+ 8,
12
+ 8
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": 1024,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "CrossAttnDownBlock2D",
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": 1,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": null,
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": [
49
+ true,
50
+ false,
51
+ false
52
+ ],
53
+ "out_channels": 4,
54
+ "projection_class_embeddings_input_dim": null,
55
+ "resnet_out_scale_factor": 1.0,
56
+ "resnet_skip_time_act": false,
57
+ "resnet_time_scale_shift": "default",
58
+ "reverse_transformer_layers_per_block": null,
59
+ "sample_size": 64,
60
+ "time_cond_proj_dim": null,
61
+ "time_embedding_act_fn": null,
62
+ "time_embedding_dim": null,
63
+ "time_embedding_type": "positional",
64
+ "timestep_post_act": null,
65
+ "transformer_layers_per_block": 1,
66
+ "up_block_types": [
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
+ }
checkpoint-6000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0578b8144cb09c1607347423c7ef3e9283f9414e53d12d854b880816224c12c
3
+ size 1312752864
checkpoint-6000/unet_ema/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "./sdxs-09fttest",
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": [
10
+ 8,
11
+ 8,
12
+ 8
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": 1024,
26
+ "cross_attention_norm": null,
27
+ "decay": 0.9999,
28
+ "down_block_types": [
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D"
32
+ ],
33
+ "downsample_padding": 1,
34
+ "dropout": 0.0,
35
+ "dual_cross_attention": false,
36
+ "encoder_hid_dim": null,
37
+ "encoder_hid_dim_type": null,
38
+ "flip_sin_to_cos": true,
39
+ "freq_shift": 0,
40
+ "in_channels": 4,
41
+ "inv_gamma": 1.0,
42
+ "layers_per_block": 1,
43
+ "mid_block_only_cross_attention": null,
44
+ "mid_block_scale_factor": 1,
45
+ "mid_block_type": null,
46
+ "min_decay": 0.0,
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": [
52
+ true,
53
+ false,
54
+ false
55
+ ],
56
+ "optimization_step": 1000,
57
+ "out_channels": 4,
58
+ "power": 0.6666666666666666,
59
+ "projection_class_embeddings_input_dim": null,
60
+ "resnet_out_scale_factor": 1.0,
61
+ "resnet_skip_time_act": false,
62
+ "resnet_time_scale_shift": "default",
63
+ "reverse_transformer_layers_per_block": null,
64
+ "sample_size": 64,
65
+ "time_cond_proj_dim": null,
66
+ "time_embedding_act_fn": null,
67
+ "time_embedding_dim": null,
68
+ "time_embedding_type": "positional",
69
+ "timestep_post_act": null,
70
+ "transformer_layers_per_block": 1,
71
+ "up_block_types": [
72
+ "CrossAttnUpBlock2D",
73
+ "CrossAttnUpBlock2D",
74
+ "CrossAttnUpBlock2D"
75
+ ],
76
+ "upcast_attention": null,
77
+ "update_after_step": 0,
78
+ "use_ema_warmup": false,
79
+ "use_linear_projection": true
80
+ }
checkpoint-6000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:426f8420243ac78b8db0541fa0e8d4a2cf7f974dc21b3932f09567c8d5d9e6af
3
+ size 1312752864
logs/text2image-fine-tune/1716963695.1039982/events.out.tfevents.1716963695.5bb9e31bd71a.2171.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46dbce8b435aa74bb35eaa9aa0f777ec271e9a370a4e39275ecb7c5c2231121
3
+ size 2494
logs/text2image-fine-tune/1716963695.1110828/hparams.yml ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 1000
10
+ checkpoints_total_limit: 1
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: fantasyfish/laion-art
14
+ dream_detail_preservation: 1.0
15
+ dream_training: false
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ image_column: image
22
+ input_perturbation: 0
23
+ learning_rate: 1.0e-05
24
+ local_rank: -1
25
+ logging_dir: logs
26
+ lr_scheduler: constant
27
+ lr_warmup_steps: 500
28
+ max_grad_norm: 1.0
29
+ max_train_samples: null
30
+ max_train_steps: 6000
31
+ mixed_precision: fp16
32
+ noise_offset: 0
33
+ non_ema_revision: null
34
+ num_train_epochs: 2
35
+ output_dir: sdxs-09fttest
36
+ prediction_type: null
37
+ pretrained_model_name_or_path: ./sdxs-09fttest
38
+ push_to_hub: false
39
+ random_flip: true
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: checkpoint-5000
43
+ revision: null
44
+ scale_lr: false
45
+ seed: null
46
+ snr_gamma: null
47
+ tracker_project_name: text2image-fine-tune
48
+ train_batch_size: 1
49
+ train_data_dir: null
50
+ use_8bit_adam: false
51
+ use_ema: true
52
+ validation_epochs: 5
53
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1716963695.5bb9e31bd71a.2171.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58dea1ead8e5f8c22b0651f6a521b64936efbd9eab71cf5213442133f5213f06
3
+ size 49088
model_index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.28.0.dev0",
4
  "_name_or_path": "./sdxs-09fttest",
5
  "feature_extractor": [
6
  "transformers",
 
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.29.0.dev0",
4
  "_name_or_path": "./sdxs-09fttest",
5
  "feature_extractor": [
6
  "transformers",
scheduler/scheduler_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "PNDMScheduler",
3
- "_diffusers_version": "0.28.0.dev0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
 
1
  {
2
  "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.29.0.dev0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
text_encoder/config.json CHANGED
@@ -20,6 +20,6 @@
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
  "torch_dtype": "float16",
23
- "transformers_version": "4.41.0",
24
  "vocab_size": 49408
25
  }
 
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
  "torch_dtype": "float16",
23
+ "transformers_version": "4.41.1",
24
  "vocab_size": 49408
25
  }
unet/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.28.0.dev0",
4
- "_name_or_path": "sdxs-09fttest/checkpoint-4000",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.29.0.dev0",
4
+ "_name_or_path": "sdxs-09fttest/checkpoint-5000",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a238bd74ab3841dca16d5775016a9a7da0a6e58f60947730cca8b31282303ce
3
  size 1312752864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:426f8420243ac78b8db0541fa0e8d4a2cf7f974dc21b3932f09567c8d5d9e6af
3
  size 1312752864
vae/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.28.0.dev0",
4
  "_name_or_path": "./sdxs-09fttest",
5
  "act_fn": "silu",
6
  "block_out_channels": [
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.29.0.dev0",
4
  "_name_or_path": "./sdxs-09fttest",
5
  "act_fn": "silu",
6
  "block_out_channels": [