Hugging Face's logo

briannlongzhao
/
88

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
b597e90
•
1 Parent(s): c776b18

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/1706461843.5323582/events.out.tfevents.1706461843.node-0.2817.1 +3 -0
  4. logs/textual_inversion/1706461844.4379125/hparams.yml +50 -0
  5. logs/textual_inversion/1706473807.3924835/events.out.tfevents.1706473807.node-0.2763.1 +3 -0
  6. logs/textual_inversion/1706473808.2736444/hparams.yml +50 -0
  7. logs/textual_inversion/events.out.tfevents.1706461843.node-0.2817.0 +3 -0
  8. logs/textual_inversion/events.out.tfevents.1706473806.node-0.2763.0 +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> tripod
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/88
 
16
 
17
- These are Custom Diffusion adaption weights for stabilityai/stable-diffusion-2-1. The weights were trained on a photo of <new1> tripod 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/88
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 sha256:344181de85b980da1d82991a4a0f6b98d79d6def60527c72fd63612623efdd26
3
  size 4208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25eb5ebcf4f2ffcc73e1a1e58b922c5ac6e13ff24b69bc33d077eb3170f137f0
3
  size 4208
logs/textual_inversion/1706461843.5323582/events.out.tfevents.1706461843.node-0.2817.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f5ff0932cfe2289a1adc22a6e9948e56507e30b1676958de818e8384a6a1fb
3
+ size 2499
logs/textual_inversion/1706461844.4379125/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: tripod
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: 88
17
+ initializer_token: tripod
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/88
32
+ placeholder_token: <tripod>
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/n04485082
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n04485082
logs/textual_inversion/1706473807.3924835/events.out.tfevents.1706473807.node-0.2763.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64bd357693413387eb7d70b7aab39e993bf01c6a1e373dbffb8f968703c03961
3
+ size 2499
logs/textual_inversion/1706473808.2736444/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: tripod
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: 88
17
+ initializer_token: tripod
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/88
32
+ placeholder_token: <tripod>
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/n04485082
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n04485082
logs/textual_inversion/events.out.tfevents.1706461843.node-0.2817.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d918528e0d191e62a655ee4016a7f3ab0c790c1f41a0ec479d318a617771e09a
3
+ size 6800
logs/textual_inversion/events.out.tfevents.1706473806.node-0.2763.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518fa1c3bf7150a68f2c0bef1e6578fd5aff9743ce664e39a44aa3c7f0de19ab
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 sha256:9f07292ce88c5e9844aad01d04d57d27c1864462af0871b131f3a633d6e56b15
3
+ size 1361601112
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b36c96c38982adb0f123f0dd89b44dd85ed0d0b0af334adb81db3c9ec707e38
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