Hugging Face's logo

kmpartner
/
bkv2t-fttest

Diffusers
TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
kmpartner commited on
Commit
0ebc19c
·
verified ·
1 Parent(s): 093a9bb

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. checkpoint-8000/optimizer.bin +3 -0
  2. checkpoint-8000/random_states_0.pkl +3 -0
  3. checkpoint-8000/scaler.pt +3 -0
  4. checkpoint-8000/scheduler.bin +3 -0
  5. checkpoint-8000/unet/config.json +69 -0
  6. checkpoint-8000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. checkpoint-8000/unet_ema/config.json +76 -0
  8. checkpoint-8000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  9. logs/text2image-fine-tune/1749802320.2284496/events.out.tfevents.1749802320.239d8808d20f.6397.1 +3 -0
  10. logs/text2image-fine-tune/1749802320.230066/hparams.yml +56 -0
  11. logs/text2image-fine-tune/events.out.tfevents.1749802320.239d8808d20f.6397.0 +3 -0
checkpoint-8000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75aa41c6a55e6b4a52d1f156dd8dbba80ada7852b69c2a85fc7f31824465102f
3
+ size 2614904964
checkpoint-8000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30907eee5860941cdc3addb4a0c25710e3fedaa4180e98f73c1a264e214e6909
3
+ size 14344
checkpoint-8000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277aa13cb2ec6fbc8e4950a74aadb07696752963130be9aa03b65700e040b1b0
3
+ size 988
checkpoint-8000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292da4efc7a8f738c6def66954da40f3297d0ce66bc7f39bf63dc452f2047773
3
+ size 1000
checkpoint-8000/unet/config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "_name_or_path": "bkv2t-fttest/checkpoint-7000",
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
+ 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": 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": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": null,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "reverse_transformer_layers_per_block": null,
55
+ "sample_size": 64,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": 1,
62
+ "up_block_types": [
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D",
65
+ "CrossAttnUpBlock2D"
66
+ ],
67
+ "upcast_attention": false,
68
+ "use_linear_projection": true
69
+ }
checkpoint-8000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa79093c26a2e5c5a7085ebe2598aff5bc46887c48a99a8be17947bbdbc09556
3
+ size 1307346120
checkpoint-8000/unet_ema/config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "_name_or_path": "nota-ai/bk-sdm-v2-tiny",
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
+ 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": 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": false,
52
+ "optimization_step": 8000,
53
+ "out_channels": 4,
54
+ "power": 0.6666666666666666,
55
+ "projection_class_embeddings_input_dim": null,
56
+ "resnet_out_scale_factor": 1.0,
57
+ "resnet_skip_time_act": false,
58
+ "resnet_time_scale_shift": "default",
59
+ "reverse_transformer_layers_per_block": null,
60
+ "sample_size": 64,
61
+ "time_cond_proj_dim": null,
62
+ "time_embedding_act_fn": null,
63
+ "time_embedding_dim": null,
64
+ "time_embedding_type": "positional",
65
+ "timestep_post_act": null,
66
+ "transformer_layers_per_block": 1,
67
+ "up_block_types": [
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D",
70
+ "CrossAttnUpBlock2D"
71
+ ],
72
+ "upcast_attention": false,
73
+ "update_after_step": 0,
74
+ "use_ema_warmup": false,
75
+ "use_linear_projection": true
76
+ }
checkpoint-8000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb27e18b7db737fcc2bca94ac0bb37cdd82c6124492ce7e0e106a3fa66da587
3
+ size 1307346120
logs/text2image-fine-tune/1749802320.2284496/events.out.tfevents.1749802320.239d8808d20f.6397.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f2d52a94f33efc674b1fa6c5f83af2c50aa0025f93d32ccffe763ce544b1cb
3
+ size 2715
logs/text2image-fine-tune/1749802320.230066/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ./img-dataset
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: 1
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ image_interpolation_mode: lanczos
24
+ input_perturbation: 0
25
+ learning_rate: 1.0e-05
26
+ local_rank: -1
27
+ logging_dir: logs
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ max_grad_norm: 1.0
31
+ max_train_samples: null
32
+ max_train_steps: 8000
33
+ mixed_precision: fp16
34
+ noise_offset: 0
35
+ non_ema_revision: null
36
+ num_train_epochs: 16
37
+ offload_ema: false
38
+ output_dir: bkv2t-fttest
39
+ prediction_type: null
40
+ pretrained_model_name_or_path: nota-ai/bk-sdm-v2-tiny
41
+ push_to_hub: false
42
+ random_flip: true
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: checkpoint-7000
46
+ revision: null
47
+ scale_lr: false
48
+ seed: 42
49
+ snr_gamma: 5.0
50
+ tracker_project_name: text2image-fine-tune
51
+ train_batch_size: 16
52
+ train_data_dir: null
53
+ use_8bit_adam: false
54
+ use_ema: true
55
+ validation_epochs: 5
56
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1749802320.239d8808d20f.6397.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f7a1e7a15596de66ca51ea21c07440496b97060a0d35047c26cf4e16ae55ad
3
+ size 49137