Hugging Face's logo

pnfox
/
trainedmodel

Text-to-Image
Diffusers
TensorBoard
Safetensors
stable-diffusion
stable-diffusion-diffusers
custom-diffusion
diffusers-training
Model card Files
xet
Metrics Community
pnfox commited on
Commit
7c9c0a1
·
verified ·
1 Parent(s): d46eb63

End of training

Browse files
Files changed (19) hide show
  1. README.md +44 -0
  2. checkpoint-250/custom_checkpoint_0.pkl +3 -0
  3. checkpoint-250/model.safetensors +3 -0
  4. checkpoint-250/model_1.safetensors +3 -0
  5. checkpoint-250/optimizer.bin +3 -0
  6. checkpoint-250/random_states_0.pkl +3 -0
  7. checkpoint-250/scaler.pt +3 -0
  8. checkpoint-250/scheduler.bin +3 -0
  9. latex.safetensors +3 -0
  10. logs/custom-diffusion/1731078796.03431/events.out.tfevents.1731078796.fedora.51388.1 +3 -0
  11. logs/custom-diffusion/1731078796.0355015/hparams.yml +57 -0
  12. logs/custom-diffusion/1731078860.626023/events.out.tfevents.1731078860.fedora.52454.1 +3 -0
  13. logs/custom-diffusion/1731078860.627182/hparams.yml +57 -0
  14. logs/custom-diffusion/1731079077.4415827/events.out.tfevents.1731079077.fedora.55114.1 +3 -0
  15. logs/custom-diffusion/1731079077.4430447/hparams.yml +57 -0
  16. logs/custom-diffusion/events.out.tfevents.1731078796.fedora.51388.0 +3 -0
  17. logs/custom-diffusion/events.out.tfevents.1731078860.fedora.52454.0 +3 -0
  18. logs/custom-diffusion/events.out.tfevents.1731079077.fedora.55114.0 +3 -0
  19. pytorch_custom_diffusion_weights.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ inference: true
6
+ instance_prompt: photo of a latex catsuit
7
+ tags:
8
+ - text-to-image
9
+ - diffusers
10
+ - stable-diffusion
11
+ - stable-diffusion-diffusers
12
+ - custom-diffusion
13
+ - diffusers-training
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+
20
+ # Custom Diffusion - pnfox/trainedmodel
21
+
22
+ These are Custom Diffusion adaption weights for CompVis/stable-diffusion-v1-4. The weights were trained on photo of a latex catsuit using [Custom Diffusion](https://www.cs.cmu.edu/~custom-diffusion). You can find some example images in the following.
23
+
24
+
25
+
26
+
27
+ For more details on the training, please follow [this link](https://github.com/huggingface/diffusers/blob/main/examples/custom_diffusion).
28
+
29
+
30
+ ## Intended uses & limitations
31
+
32
+ #### How to use
33
+
34
+ ```python
35
+ # TODO: add an example code snippet for running this diffusion pipeline
36
+ ```
37
+
38
+ #### Limitations and bias
39
+
40
+ [TODO: provide examples of latent issues and potential remediations]
41
+
42
+ ## Training details
43
+
44
+ [TODO: describe the data used to train the model]
checkpoint-250/custom_checkpoint_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce50d16152dfadac6ccb26cfbf230cc9ca5f2560195f3f05e3a7b580b1df5675
3
+ size 76690022
checkpoint-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20b408deaa4bd8ec28cf63a609e27eeb16acec67b42d4d9f5348d343a447a3dc
3
+ size 76682360
checkpoint-250/model_1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ea93041f6e83035e29e9bfaca08729c71be588824d077cf2cd4fab1a63efdba
3
+ size 492268240
checkpoint-250/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88254394a65fd656e7f4803f83bddb1933d83568734771a2c92fdee0c307383
3
+ size 456951355
checkpoint-250/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:742ca69009790065765d3547a26a5df021de132606207acfc4b3721a22b13331
3
+ size 14344
checkpoint-250/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccec82ecb1db9fee8431a9924525ac42c65eba373a478c5528e653b68744a6a9
3
+ size 988
checkpoint-250/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a05ae0bdbe3ac7c61c54684792e44590359258624f8fe2ec148412c2d836beb
3
+ size 1000
latex.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9555cd87d1894d50490b2b7bd67e464db0a600dc56dd776025819a77f6a692c0
3
+ size 3176
logs/custom-diffusion/1731078796.03431/events.out.tfevents.1731078796.fedora.51388.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cdfd0d4530cdd532f427a8124922c4caf377e8eb01ff7bfb255b890467ee03f
3
+ size 2628
logs/custom-diffusion/1731078796.0355015/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ center_crop: false
7
+ checkpointing_steps: 250
8
+ checkpoints_total_limit: null
9
+ class_data_dir: null
10
+ class_prompt: null
11
+ concepts_list: null
12
+ dataloader_num_workers: 2
13
+ enable_xformers_memory_efficient_attention: false
14
+ freeze_model: crossattn_kv
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hflip: true
18
+ hub_model_id: null
19
+ hub_token: null
20
+ initializer_token: ktn+pll+ucd
21
+ instance_data_dir: ../../trainingset2
22
+ instance_prompt: photo of a latex catsuit
23
+ learning_rate: 1.0e-05
24
+ local_rank: -1
25
+ logging_dir: logs
26
+ lr_scheduler: constant
27
+ lr_warmup_steps: 0
28
+ max_grad_norm: 1.0
29
+ max_train_steps: 250
30
+ mixed_precision: null
31
+ modifier_token: latex
32
+ no_safe_serialization: false
33
+ noaug: false
34
+ num_class_images: 200
35
+ num_train_epochs: 1
36
+ num_validation_images: 2
37
+ output_dir: trainedmodel
38
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
39
+ prior_generation_precision: null
40
+ prior_loss_weight: 1.0
41
+ push_to_hub: false
42
+ real_prior: false
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: null
46
+ revision: null
47
+ sample_batch_size: 4
48
+ scale_lr: true
49
+ seed: 42
50
+ set_grads_to_none: false
51
+ tokenizer_name: null
52
+ train_batch_size: 2
53
+ use_8bit_adam: false
54
+ validation_prompt: null
55
+ validation_steps: 50
56
+ variant: null
57
+ with_prior_preservation: false
logs/custom-diffusion/1731078860.626023/events.out.tfevents.1731078860.fedora.52454.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e68c2aaff10383406b8565b991d4dbee8738b40e1137e107215522a8d5f984
3
+ size 2628
logs/custom-diffusion/1731078860.627182/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ center_crop: false
7
+ checkpointing_steps: 250
8
+ checkpoints_total_limit: null
9
+ class_data_dir: null
10
+ class_prompt: null
11
+ concepts_list: null
12
+ dataloader_num_workers: 2
13
+ enable_xformers_memory_efficient_attention: false
14
+ freeze_model: crossattn_kv
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hflip: true
18
+ hub_model_id: null
19
+ hub_token: null
20
+ initializer_token: ktn+pll+ucd
21
+ instance_data_dir: ../../trainingset2
22
+ instance_prompt: photo of a latex catsuit
23
+ learning_rate: 1.0e-05
24
+ local_rank: -1
25
+ logging_dir: logs
26
+ lr_scheduler: constant
27
+ lr_warmup_steps: 0
28
+ max_grad_norm: 1.0
29
+ max_train_steps: 250
30
+ mixed_precision: null
31
+ modifier_token: latex
32
+ no_safe_serialization: false
33
+ noaug: false
34
+ num_class_images: 200
35
+ num_train_epochs: 1
36
+ num_validation_images: 2
37
+ output_dir: trainedmodel
38
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
39
+ prior_generation_precision: null
40
+ prior_loss_weight: 1.0
41
+ push_to_hub: false
42
+ real_prior: false
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: null
46
+ revision: null
47
+ sample_batch_size: 4
48
+ scale_lr: true
49
+ seed: 42
50
+ set_grads_to_none: false
51
+ tokenizer_name: null
52
+ train_batch_size: 2
53
+ use_8bit_adam: false
54
+ validation_prompt: null
55
+ validation_steps: 50
56
+ variant: null
57
+ with_prior_preservation: false
logs/custom-diffusion/1731079077.4415827/events.out.tfevents.1731079077.fedora.55114.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9ab72c2d68997b1727f64ab7c3439b6c846b3551ef286699c9f09ccc8add9b
3
+ size 2628
logs/custom-diffusion/1731079077.4430447/hparams.yml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ center_crop: false
7
+ checkpointing_steps: 250
8
+ checkpoints_total_limit: null
9
+ class_data_dir: null
10
+ class_prompt: null
11
+ concepts_list: null
12
+ dataloader_num_workers: 2
13
+ enable_xformers_memory_efficient_attention: false
14
+ freeze_model: crossattn_kv
15
+ gradient_accumulation_steps: 1
16
+ gradient_checkpointing: false
17
+ hflip: true
18
+ hub_model_id: null
19
+ hub_token: null
20
+ initializer_token: ktn+pll+ucd
21
+ instance_data_dir: ../../trainingset2
22
+ instance_prompt: photo of a latex catsuit
23
+ learning_rate: 1.0e-05
24
+ local_rank: -1
25
+ logging_dir: logs
26
+ lr_scheduler: constant
27
+ lr_warmup_steps: 0
28
+ max_grad_norm: 1.0
29
+ max_train_steps: 250
30
+ mixed_precision: null
31
+ modifier_token: latex
32
+ no_safe_serialization: false
33
+ noaug: false
34
+ num_class_images: 200
35
+ num_train_epochs: 1
36
+ num_validation_images: 2
37
+ output_dir: trainedmodel
38
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
39
+ prior_generation_precision: null
40
+ prior_loss_weight: 1.0
41
+ push_to_hub: true
42
+ real_prior: false
43
+ report_to: tensorboard
44
+ resolution: 512
45
+ resume_from_checkpoint: null
46
+ revision: null
47
+ sample_batch_size: 4
48
+ scale_lr: true
49
+ seed: 42
50
+ set_grads_to_none: false
51
+ tokenizer_name: null
52
+ train_batch_size: 2
53
+ use_8bit_adam: false
54
+ validation_prompt: null
55
+ validation_steps: 50
56
+ variant: null
57
+ with_prior_preservation: false
logs/custom-diffusion/events.out.tfevents.1731078796.fedora.51388.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3aa0bddc24f7f942c7b612074b9ec07e7e03107551d424d8d4ce4273e1c02d6
3
+ size 4352
logs/custom-diffusion/events.out.tfevents.1731078860.fedora.52454.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:655d5f110a53267dc3c5388930c747a72a0e606d783892bacdf4d003ef69cf0e
3
+ size 20834
logs/custom-diffusion/events.out.tfevents.1731079077.fedora.55114.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42600bc00f9ca3f8ef3aa6657b6c85e49d39350843711fc9be3892f0e79217a
3
+ size 20834
pytorch_custom_diffusion_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20b408deaa4bd8ec28cf63a609e27eeb16acec67b42d4d9f5348d343a447a3dc
3
+ size 76682360