Hugging Face's logo

Shreyas21032003
/
sd_ffhq_shorter_captions_model_demo

Text-to-Image
Diffusers
TensorBoard
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
diffusers-training
Model card Files
xet
Metrics Community
Shreyas21032003 commited on
Commit
ca44cf0
·
verified ·
1 Parent(s): 9221ea6

End of training

Browse files
Files changed (18) hide show
  1. README.md +5 -0
  2. logs/text2image-fine-tune/1732682366.1085415/events.out.tfevents.1732682366.53e4570a39be.9889.1 +3 -0
  3. logs/text2image-fine-tune/1732682366.1102073/hparams.yml +55 -0
  4. logs/text2image-fine-tune/1732683457.749518/events.out.tfevents.1732683457.53e4570a39be.14691.1 +3 -0
  5. logs/text2image-fine-tune/1732683457.7512352/hparams.yml +55 -0
  6. logs/text2image-fine-tune/1732683640.7819858/events.out.tfevents.1732683640.53e4570a39be.15505.1 +3 -0
  7. logs/text2image-fine-tune/1732683640.7837331/hparams.yml +55 -0
  8. logs/text2image-fine-tune/1732684434.3393893/events.out.tfevents.1732684434.53e4570a39be.18871.1 +3 -0
  9. logs/text2image-fine-tune/1732684434.3410842/hparams.yml +55 -0
  10. logs/text2image-fine-tune/1732686554.0895178/events.out.tfevents.1732686554.53e4570a39be.27901.1 +3 -0
  11. logs/text2image-fine-tune/1732686554.0911813/hparams.yml +55 -0
  12. logs/text2image-fine-tune/events.out.tfevents.1732682366.53e4570a39be.9889.0 +3 -0
  13. logs/text2image-fine-tune/events.out.tfevents.1732683457.53e4570a39be.14691.0 +3 -0
  14. logs/text2image-fine-tune/events.out.tfevents.1732683640.53e4570a39be.15505.0 +3 -0
  15. logs/text2image-fine-tune/events.out.tfevents.1732684434.53e4570a39be.18871.0 +3 -0
  16. logs/text2image-fine-tune/events.out.tfevents.1732686554.53e4570a39be.27901.0 +3 -0
  17. unet/diffusion_pytorch_model.safetensors +1 -1
  18. val_imgs_grid.png +0 -0
README.md CHANGED
@@ -9,6 +9,11 @@ tags:
9
  - text-to-image
10
  - diffusers
11
  - diffusers-training
 
 
 
 
 
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the training script had access to. You
 
9
  - text-to-image
10
  - diffusers
11
  - diffusers-training
12
+ - stable-diffusion
13
+ - stable-diffusion-diffusers
14
+ - text-to-image
15
+ - diffusers
16
+ - diffusers-training
17
  ---
18
 
19
  <!-- This model card has been generated automatically according to the information the training script had access to. You
logs/text2image-fine-tune/1732682366.1085415/events.out.tfevents.1732682366.53e4570a39be.9889.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e2b41bb279ad6f4ac7f3283dcbac28860ec1c2be149e084efb7d6e90c5274e
3
+ size 2495
logs/text2image-fine-tune/1732682366.1102073/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 100000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: irodkin/ffhq_with_llava_shorter_captions
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: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 400
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 1
36
+ offload_ema: false
37
+ output_dir: sd_ffhq_shorter_captions_model_demo
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-2
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: null
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/1732683457.749518/events.out.tfevents.1732683457.53e4570a39be.14691.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6cbb0479899a391b77995be067e029d2cd869bd4a576d03b2b1aff5306dcba7
3
+ size 2495
logs/text2image-fine-tune/1732683457.7512352/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 100000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: irodkin/ffhq_with_llava_shorter_captions
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: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 2000
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 1
36
+ offload_ema: false
37
+ output_dir: sd_ffhq_shorter_captions_model_demo
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-2
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: null
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/1732683640.7819858/events.out.tfevents.1732683640.53e4570a39be.15505.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae2d6386e56cb384e79dbfe594dee7c6b347e42b06024f2301f216e6af71bff7
3
+ size 2495
logs/text2image-fine-tune/1732683640.7837331/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 100000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: irodkin/ffhq_with_llava_shorter_captions
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: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 400
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 1
36
+ offload_ema: false
37
+ output_dir: sd_ffhq_shorter_captions_model_demo
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-2
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: null
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/1732684434.3393893/events.out.tfevents.1732684434.53e4570a39be.18871.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5746b66820a40c8a8b600e15c7719aeb4506708fe2cb9847a036bac3c4b6d1c2
3
+ size 2495
logs/text2image-fine-tune/1732684434.3410842/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 100000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: irodkin/ffhq_with_llava_shorter_captions
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: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 400
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 1
36
+ offload_ema: false
37
+ output_dir: sd_ffhq_shorter_captions_model_demo
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-2
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: null
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/1732686554.0895178/events.out.tfevents.1732686554.53e4570a39be.27901.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3e20524e43befffa71f60af020278022765cf38163a411f6d71f0d016fddd6
3
+ size 2495
logs/text2image-fine-tune/1732686554.0911813/hparams.yml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 100000
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 0
12
+ dataset_config_name: null
13
+ dataset_name: irodkin/ffhq_with_llava_shorter_captions
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: 4
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ input_perturbation: 0
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ lr_scheduler: constant
28
+ lr_warmup_steps: 0
29
+ max_grad_norm: 1.0
30
+ max_train_samples: null
31
+ max_train_steps: 400
32
+ mixed_precision: fp16
33
+ noise_offset: 0
34
+ non_ema_revision: null
35
+ num_train_epochs: 1
36
+ offload_ema: false
37
+ output_dir: sd_ffhq_shorter_captions_model_demo
38
+ prediction_type: null
39
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-2
40
+ push_to_hub: true
41
+ random_flip: true
42
+ report_to: tensorboard
43
+ resolution: 512
44
+ resume_from_checkpoint: null
45
+ revision: null
46
+ scale_lr: false
47
+ seed: null
48
+ snr_gamma: null
49
+ tracker_project_name: text2image-fine-tune
50
+ train_batch_size: 1
51
+ train_data_dir: null
52
+ use_8bit_adam: false
53
+ use_ema: true
54
+ validation_epochs: 5
55
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1732682366.53e4570a39be.9889.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9624111818dfa3b55649b2827e81b05a0047833edfa62539c7efab3835eb1b0
3
+ size 19561
logs/text2image-fine-tune/events.out.tfevents.1732683457.53e4570a39be.14691.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c1a10a3884b3d755a9bb89896e43d04e684c78e454f9973fffe5acd6c78c0e
3
+ size 5224
logs/text2image-fine-tune/events.out.tfevents.1732683640.53e4570a39be.15505.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8287b3d7f85a77917edf7e1663a49fda652f0e0fd58813506b2a1d7adeb70ff
3
+ size 19561
logs/text2image-fine-tune/events.out.tfevents.1732684434.53e4570a39be.18871.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:732275e88b0f1ed0c7cd8d2aed6fd38e8c60681a6b5a183935b71ef5141e9f55
3
+ size 19561
logs/text2image-fine-tune/events.out.tfevents.1732686554.53e4570a39be.27901.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0764e7bef1e25af517a29430f616e8284a18ee24dde9454949bccd7d5a3a00a9
3
+ size 1018985
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39b496b42342b642d54ae67f58d9754ec4820d707f7bcfa42cf9387e9db1e0df
3
  size 3438167536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157e9f2966af1f18ed9a3f8a9b3d8ed2b4d53eefef3858b771bb04dc8d3e244d
3
  size 3438167536
val_imgs_grid.png ADDED