Hugging Face's logo

Stevenzhanshi
/
instruct-pix2pix-model

Diffusers
TensorBoard
Safetensors
StableDiffusionInstructPix2PixPipeline
Model card Files
xet
Metrics Community
Stevenzhanshi commited on
Commit
f32d53d
·
verified ·
1 Parent(s): c5a1e1a

End of training

Browse files
Files changed (12) hide show
  1. checkpoint-10000/optimizer.bin +3 -0
  2. checkpoint-10000/random_states_0.pkl +3 -0
  3. checkpoint-10000/scaler.pt +3 -0
  4. checkpoint-10000/scheduler.bin +3 -0
  5. checkpoint-10000/unet/config.json +68 -0
  6. checkpoint-10000/unet/diffusion_pytorch_model.safetensors +3 -0
  7. checkpoint-10000/unet_ema/config.json +75 -0
  8. checkpoint-10000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  9. logs/instruct-pix2pix/1745646932.3061192/events.out.tfevents.1745646932.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-vilfkk-worker.623.1 +3 -0
  10. logs/instruct-pix2pix/1745646932.336767/hparams.yml +51 -0
  11. logs/instruct-pix2pix/events.out.tfevents.1745646932.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-vilfkk-worker.623.0 +3 -0
  12. unet/diffusion_pytorch_model.safetensors +1 -1
checkpoint-10000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f207fc980900f3b9c20465ffc09a3026eecc7d6e6d1e172d8208c8cba72f28f3
3
+ size 6876842324
checkpoint-10000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e45ceb5b74c50f3788fc25c894d2155f651a70664625e0cc165e57afb5ccde
3
+ size 14408
checkpoint-10000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9edab58c0c3df351bc9a8b3914358cb4b7af163b56063f195d98b42d019fd11
3
+ size 988
checkpoint-10000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20bbef0c8fecac2668563417c5ed2ebcdecc2a3024abda5059c94bc08a3f3fea
3
+ size 1000
checkpoint-10000/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "_name_or_path": "timbrooks/instruct-pix2pix",
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": 8,
10
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
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,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 8,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_attention_heads": null,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "reverse_transformer_layers_per_block": null,
53
+ "sample_size": 64,
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": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
checkpoint-10000/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:230702d1c1ff6d66ff91b4111485c9f399712a22c55898057d18a5b0132aa616
3
+ size 3438213624
checkpoint-10000/unet_ema/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "_name_or_path": "timbrooks/instruct-pix2pix",
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": 8,
10
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "decay": 0.9999,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dropout": 0.0,
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": 8,
39
+ "inv_gamma": 1.0,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "min_decay": 0.0,
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "optimization_step": 10000,
51
+ "out_channels": 4,
52
+ "power": 0.6666666666666666,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 64,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "update_after_step": 0,
73
+ "use_ema_warmup": false,
74
+ "use_linear_projection": false
75
+ }
checkpoint-10000/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b69e0a5419a5ac11b4883e23fef8f703e3ed9df6b9afdd7f33db5faefe5c0d4
3
+ size 3438213624
logs/instruct-pix2pix/1745646932.3061192/events.out.tfevents.1745646932.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-vilfkk-worker.623.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ceeefc2a75ae2bcdec00931157c88f7c5b41a58de8c9cbf093c211e4b16916
3
+ size 2392
logs/instruct-pix2pix/1745646932.336767/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: true
6
+ cache_dir: null
7
+ center_crop: false
8
+ checkpointing_steps: 500
9
+ checkpoints_total_limit: 1
10
+ conditioning_dropout_prob: 0.1
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: Aurora1609/RoboTwin
14
+ edit_prompt_column: prompt
15
+ edited_image_column: after
16
+ enable_xformers_memory_efficient_attention: true
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 20
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 10000
29
+ mixed_precision: fp16
30
+ non_ema_revision: null
31
+ num_train_epochs: 9
32
+ num_validation_images: 4
33
+ original_image_column: before
34
+ output_dir: instruct-pix2pix-model
35
+ pretrained_model_name_or_path: timbrooks/instruct-pix2pix
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 128
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
44
+ train_batch_size: 1
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: true
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
51
+ variant: null
logs/instruct-pix2pix/events.out.tfevents.1745646932.mlxlabzvy78jw467d8df06-20250318024839-7a3w86-vilfkk-worker.623.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a864bf01562bc76ca9858557e055ecfc47223f6da14f02f83baa5169f19bfda0
3
+ size 489961
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8e5c65e6affc479dfe006024306e169d820fbd14f068a0f50bb9201dc4769da
3
  size 3438213624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b69e0a5419a5ac11b4883e23fef8f703e3ed9df6b9afdd7f33db5faefe5c0d4
3
  size 3438213624