Upload folder using huggingface_hub

#2
logs/text2image-fine-tune/1696313639.948389/events.out.tfevents.1696313639.87091f96a405.9023.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81770f8f82a4597db67dc75c76cd4df55e9bf81b11ba4e4a6a2f958a24abcd24
3
+ size 2336
logs/text2image-fine-tune/1696313639.9500043/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 200
10
+ checkpoints_total_limit: 1
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: null
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ input_perturbation: 0
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 0
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 5000
29
+ mixed_precision: fp16
30
+ noise_offset: 0
31
+ non_ema_revision: null
32
+ num_train_epochs: 21
33
+ output_dir: batik-model
34
+ prediction_type: null
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ push_to_hub: false
37
+ random_flip: true
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: null
44
+ snr_gamma: null
45
+ tracker_project_name: text2image-fine-tune
46
+ train_batch_size: 2
47
+ train_data_dir: /content/drive/MyDrive/vektor/processed/
48
+ use_8bit_adam: false
49
+ use_ema: false
50
+ validation_epochs: 5
logs/text2image-fine-tune/events.out.tfevents.1696313639.87091f96a405.9023.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:086888fa49a767473a7a393c73929b43c5513d13c140c7577371f53e0eea904b
3
+ size 3607395
model_index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.21.0.dev0",
4
- "_name_or_path": "aibatik/batik_bakaran",
5
  "feature_extractor": [
6
  "transformers",
7
  "CLIPImageProcessor"
 
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
  "feature_extractor": [
6
  "transformers",
7
  "CLIPImageProcessor"
safety_checker/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/root/.cache/huggingface/hub/models--aibatik--batik_bakaran/snapshots/ae1ed561b321ce8e1f948b1f6b6c0014c8d4644c/safety_checker",
3
  "architectures": [
4
  "StableDiffusionSafetyChecker"
5
  ],
@@ -15,7 +15,7 @@
15
  "num_attention_heads": 12
16
  },
17
  "torch_dtype": "float32",
18
- "transformers_version": "4.32.1",
19
  "vision_config": {
20
  "dropout": 0.0,
21
  "hidden_size": 1024,
 
1
  {
2
+ "_name_or_path": "/root/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/safety_checker",
3
  "architectures": [
4
  "StableDiffusionSafetyChecker"
5
  ],
 
15
  "num_attention_heads": 12
16
  },
17
  "torch_dtype": "float32",
18
+ "transformers_version": "4.33.3",
19
  "vision_config": {
20
  "dropout": 0.0,
21
  "hidden_size": 1024,
scheduler/scheduler_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "PNDMScheduler",
3
- "_diffusers_version": "0.21.0.dev0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
 
1
  {
2
  "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.22.0.dev0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
text_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "aibatik/batik_bakaran",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -20,6 +20,6 @@
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
  "torch_dtype": "float16",
23
- "transformers_version": "4.32.1",
24
  "vocab_size": 49408
25
  }
 
1
  {
2
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
  "torch_dtype": "float16",
23
+ "transformers_version": "4.33.3",
24
  "vocab_size": 49408
25
  }
unet/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.21.0.dev0",
4
- "_name_or_path": "aibatik/batik_bakaran",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
@@ -28,6 +28,7 @@
28
  "DownBlock2D"
29
  ],
30
  "downsample_padding": 1,
 
31
  "dual_cross_attention": false,
32
  "encoder_hid_dim": null,
33
  "encoder_hid_dim_type": null,
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
 
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,
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:837203341dfafddebf8cc84ee68f520ab29e2baf62520a5c23e5ef1399a411c4
3
  size 3438167536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a950a0b4627b49dfa094c2c8dc8dd2bde6aabe183caf6186d89984a61f922f4
3
  size 3438167536
vae/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.21.0.dev0",
4
- "_name_or_path": "aibatik/batik_bakaran",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,