Hugging Face's logo

briannlongzhao
/
81

Text-to-Image
Diffusers
TensorBoard
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
custom-diffusion
Inference Endpoints
Model card Files Metrics Community
briannlongzhao commited on
Commit
32c482c
•
1 Parent(s): 36c763c

End of training

Browse files
Files changed (13) hide show
  1. README.md +3 -8
  2. learned_embeds.safetensors +1 -1
  3. logs/textual_inversion/1706461809.9393141/events.out.tfevents.1706461810.node-0.2635.1 +3 -0
  4. logs/textual_inversion/1706461810.7973723/hparams.yml +50 -0
  5. logs/textual_inversion/1706473901.1964645/events.out.tfevents.1706473902.node-0.2850.1 +3 -0
  6. logs/textual_inversion/1706473905.060807/hparams.yml +50 -0
  7. logs/textual_inversion/events.out.tfevents.1706461809.node-0.2635.0 +3 -0
  8. logs/textual_inversion/events.out.tfevents.1706473899.node-0.2850.0 +3 -0
  9. text_encoder/config.json +2 -2
  10. text_encoder/model.safetensors +2 -2
  11. unet/diffusion_pytorch_model.safetensors +2 -2
  12. vae/config.json +1 -1
  13. vae/diffusion_pytorch_model.safetensors +2 -2
README.md CHANGED
@@ -2,21 +2,16 @@
2
  ---
3
  license: creativeml-openrail-m
4
  base_model: stabilityai/stable-diffusion-2-1
5
- instance_prompt: a photo of <new1> sarong
6
  tags:
7
  - stable-diffusion
8
  - stable-diffusion-diffusers
9
  - text-to-image
10
  - diffusers
11
- - custom-diffusion
12
  inference: true
13
  ---
14
 
15
- # Custom Diffusion - briannlongzhao/81
 
16
 
17
- These are Custom Diffusion adaption weights for stabilityai/stable-diffusion-2-1. The weights were trained on a photo of <new1> sarong using [Custom Diffusion](https://www.cs.cmu.edu/~custom-diffusion). You can find some example images in the following.
18
 
19
-
20
-
21
-
22
- For more details on the training, please follow [this link](https://github.com/huggingface/diffusers/blob/main/examples/custom_diffusion).
 
2
  ---
3
  license: creativeml-openrail-m
4
  base_model: stabilityai/stable-diffusion-2-1
 
5
  tags:
6
  - stable-diffusion
7
  - stable-diffusion-diffusers
8
  - text-to-image
9
  - diffusers
10
+ - textual_inversion
11
  inference: true
12
  ---
13
 
14
+ # Textual inversion text2image fine-tuning - briannlongzhao/81
15
+ These are textual inversion adaption weights for stabilityai/stable-diffusion-2-1. You can find some example images in the following.
16
 
 
17
 
 
 
 
 
learned_embeds.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39d9ca155a9861c1e9471166cb59c4997fa1d4ae8ae6ab593242362da7b2f39e
3
  size 4208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa1deeb3f496b5ef73b00911fc361ef1d5a1ea100698c6c15add2a259aac13e
3
  size 4208
logs/textual_inversion/1706461809.9393141/events.out.tfevents.1706461810.node-0.2635.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22a0034682d1843ea17c99841ca7b76d5fdfdfbadcb094cf9f5251ade69bff4
3
+ size 2499
logs/textual_inversion/1706461810.7973723/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
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: sarong
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 81
17
+ initializer_token: sarong
18
+ learnable_property: object
19
+ learning_rate: 0.008
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 35
26
+ mixed_precision: fp16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 5
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: /mnt/default/textual_inversion_models_medium/81
32
+ placeholder_token: <sarong>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: true
35
+ repeats: 1
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 4
46
+ train_data_dir: /mnt/default/imagenet/images/train_medium/n04136333
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n04136333
logs/textual_inversion/1706473901.1964645/events.out.tfevents.1706473902.node-0.2850.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b56232a78a15b2493c5c59a315c436d0dc47a674dc53b505258a21d5a1ab83
3
+ size 2499
logs/textual_inversion/1706473905.060807/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
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: sarong
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 81
17
+ initializer_token: sarong
18
+ learnable_property: object
19
+ learning_rate: 0.008
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 35
26
+ mixed_precision: fp16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 5
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: /mnt/default/textual_inversion_models_medium/81
32
+ placeholder_token: <sarong>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: true
35
+ repeats: 1
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 4
46
+ train_data_dir: /mnt/default/imagenet/images/train_medium/n04136333
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n04136333
logs/textual_inversion/events.out.tfevents.1706461809.node-0.2635.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64dd43b0bebdf7afb6cd9af513e2254139698fd6400654fb08b6c60a964471d2
3
+ size 10326
logs/textual_inversion/events.out.tfevents.1706473899.node-0.2850.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:594a0ec2c0caa3645ede1a7f3c9e66a5dd5ea6a47db77da68ad74e91a6077ff5
3
+ size 10326
text_encoder/config.json CHANGED
@@ -19,7 +19,7 @@
19
  "num_hidden_layers": 23,
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
- "torch_dtype": "float16",
23
  "transformers_version": "4.28.1",
24
- "vocab_size": 49408
25
  }
 
19
  "num_hidden_layers": 23,
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
+ "torch_dtype": "float32",
23
  "transformers_version": "4.28.1",
24
+ "vocab_size": 49409
25
  }
text_encoder/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:681c555376658c81dc273f2d737a2aeb23ddb6d1d8e5b3a7064636d359a22668
3
- size 680821096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed0d61ac0631b31037e3b3cca8432e2932979332b3512a378778e76b77bdb49d
3
+ size 1361601112
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c48f3cefe357f0f085f526fbebb10fa1b1a001e8d8a272d6d3f21e4f73b5685f
3
- size 3463726504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3a4d7978884c5e4ef00b62641b1b544b257be2f6715d984188610ad6475ad2
3
+ size 1731904736
vae/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.25.1",
4
- "_name_or_path": "/home/aiscuser/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6/vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.25.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
vae/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
3
- size 334643268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
3
+ size 167335342