Hugging Face's logo

indu22
/
instruct-pix2pix-v2

Diffusers
TensorBoard
Model card Files
xet
 Metrics Community
indu22 commited on
Commit
cd7bb73
·
1 Parent(s): c69c34c

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/optimizer.bin +3 -0
  2. pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/random_states_0.pkl +3 -0
  3. pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/scaler.pt +3 -0
  4. pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/scheduler.bin +3 -0
  5. pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/unet/config.json +65 -0
  6. pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/unet/diffusion_pytorch_model.bin +3 -0
  7. pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/1694408974.2714436/events.out.tfevents.1694408974.ip-172-31-5-183.5572.1 +3 -0
  8. pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/1694408974.2726908/hparams.yml +50 -0
  9. pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/1694409126.1515908/events.out.tfevents.1694409126.ip-172-31-5-183.5928.1 +3 -0
  10. pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/1694409126.1528986/hparams.yml +50 -0
  11. pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/events.out.tfevents.1694408974.ip-172-31-5-183.5572.0 +3 -0
  12. pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/events.out.tfevents.1694409126.ip-172-31-5-183.5928.0 +3 -0
pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66e53a449d12ca68da9aeb46bbd389c180df310ad567143c378a4c044cd4a469
3
+ size 6876841875
pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640bd612a0d9ab5312eb2821ef5cbb85ac35be1144a6b25d750e36bcb8b904b7
3
+ size 14599
pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10f43b556514deea43daf4bd92ba77224db90325f5f279910e84cc3fc7142df4
3
+ size 557
pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e056e57fcef3616d3000a46b782c3c130c405f8888d080b7242a97c8485c4263
3
+ size 563
pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/unet/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.19.3",
4
+ "_name_or_path": "riffusion/riffusion-model-v1",
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
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "center_input_sample": false,
17
+ "class_embed_type": null,
18
+ "class_embeddings_concat": false,
19
+ "conv_in_kernel": 3,
20
+ "conv_out_kernel": 3,
21
+ "cross_attention_dim": 768,
22
+ "cross_attention_norm": null,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "encoder_hid_dim": null,
32
+ "encoder_hid_dim_type": null,
33
+ "flip_sin_to_cos": true,
34
+ "freq_shift": 0,
35
+ "in_channels": 8,
36
+ "layers_per_block": 2,
37
+ "mid_block_only_cross_attention": null,
38
+ "mid_block_scale_factor": 1,
39
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
40
+ "norm_eps": 1e-05,
41
+ "norm_num_groups": 32,
42
+ "num_attention_heads": null,
43
+ "num_class_embeds": null,
44
+ "only_cross_attention": false,
45
+ "out_channels": 4,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_out_scale_factor": 1.0,
48
+ "resnet_skip_time_act": false,
49
+ "resnet_time_scale_shift": "default",
50
+ "sample_size": 32,
51
+ "time_cond_proj_dim": null,
52
+ "time_embedding_act_fn": null,
53
+ "time_embedding_dim": null,
54
+ "time_embedding_type": "positional",
55
+ "timestep_post_act": null,
56
+ "transformer_layers_per_block": 1,
57
+ "up_block_types": [
58
+ "UpBlock2D",
59
+ "CrossAttnUpBlock2D",
60
+ "CrossAttnUpBlock2D",
61
+ "CrossAttnUpBlock2D"
62
+ ],
63
+ "upcast_attention": false,
64
+ "use_linear_projection": false
65
+ }
pix2pix-riff-ckpt/checkpoint-30000/checkpoint-30000/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da426cdeec8818e199d96c5437997d008976832e23cb601235aa6093f43bb6f7
3
+ size 3438422053
pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/1694408974.2714436/events.out.tfevents.1694408974.ip-172-31-5-183.5572.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350796fd8479cc7c6cce0522f88d93b1f43fd09379a292f347c9cfa943288395
3
+ size 2506
pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/1694408974.2726908/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
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
12
+ dataset_config_name: null
13
+ dataset_name: indu22/combined-training-data
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 1
18
+ gradient_checkpointing: false
19
+ hub_model_id: indu22/instruct-pix2pix-v2
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: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 300000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 8
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: ./data/pix2pix-riff-ckpt
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 256
40
+ resume_from_checkpoint: latest
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
44
+ train_batch_size: 1
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: false
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/1694409126.1515908/events.out.tfevents.1694409126.ip-172-31-5-183.5928.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7038fd46ce117033457343e834556fb3dd37870a013a22556043ba366d9ce3b1
3
+ size 2575
pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/1694409126.1528986/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
+ center_crop: false
8
+ checkpointing_steps: 30000
9
+ checkpoints_total_limit: 3
10
+ conditioning_dropout_prob: 0.05
11
+ dataloader_num_workers: 16
12
+ dataset_config_name: null
13
+ dataset_name: indu22/combined-training-data
14
+ edit_prompt_column: edit_prompt
15
+ edited_image_column: edited_image
16
+ enable_xformers_memory_efficient_attention: false
17
+ gradient_accumulation_steps: 1
18
+ gradient_checkpointing: false
19
+ hub_model_id: indu22/instruct-pix2pix-v2
20
+ hub_token: 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
21
+ learning_rate: 1.0e-05
22
+ local_rank: -1
23
+ logging_dir: logs
24
+ lr_scheduler: constant
25
+ lr_warmup_steps: 500
26
+ max_grad_norm: 1.0
27
+ max_train_samples: null
28
+ max_train_steps: 300000
29
+ mixed_precision: null
30
+ non_ema_revision: null
31
+ num_train_epochs: 8
32
+ num_validation_images: 4
33
+ original_image_column: original_image
34
+ output_dir: ./data/pix2pix-riff-ckpt
35
+ pretrained_model_name_or_path: riffusion/riffusion-model-v1
36
+ push_to_hub: true
37
+ random_flip: false
38
+ report_to: tensorboard
39
+ resolution: 256
40
+ resume_from_checkpoint: latest
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 0
44
+ train_batch_size: 1
45
+ train_data_dir: null
46
+ use_8bit_adam: false
47
+ use_ema: false
48
+ val_image_url: null
49
+ validation_epochs: 1
50
+ validation_prompt: null
pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/events.out.tfevents.1694408974.ip-172-31-5-183.5572.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc739c99899a7c3f3850bb3d9c102f1729a195cc5ded7063fc2ed40603b435b2
3
+ size 10251
pix2pix-riff-ckpt/checkpoint-30000/logs/instruct-pix2pix/events.out.tfevents.1694409126.ip-172-31-5-183.5928.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cdea023796a83d26cf20f3668db417581b22cd2fd65c7ecf2cfddccddaafa8c
3
+ size 2983578