End of training
Browse files- README.md +41 -0
- logs/text2image-fine-tune-sdxl/1725939996.2971735/events.out.tfevents.1725939996.datasec2.engr.uconn.edu.3162987.1 +3 -0
- logs/text2image-fine-tune-sdxl/1725939996.298438/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/1725940292.1553288/events.out.tfevents.1725940292.datasec2.engr.uconn.edu.3163194.1 +3 -0
- logs/text2image-fine-tune-sdxl/1725940292.1573727/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/1725940592.6629992/events.out.tfevents.1725940592.datasec2.engr.uconn.edu.3163636.1 +3 -0
- logs/text2image-fine-tune-sdxl/1725940592.665023/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/1725940673.437566/events.out.tfevents.1725940673.datasec2.engr.uconn.edu.3163851.1 +3 -0
- logs/text2image-fine-tune-sdxl/1725940673.438938/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/1725940759.4802158/events.out.tfevents.1725940759.datasec2.engr.uconn.edu.3164079.1 +3 -0
- logs/text2image-fine-tune-sdxl/1725940759.4820197/hparams.yml +58 -0
- logs/text2image-fine-tune-sdxl/events.out.tfevents.1725939996.datasec2.engr.uconn.edu.3162987.0 +3 -0
- logs/text2image-fine-tune-sdxl/events.out.tfevents.1725940292.datasec2.engr.uconn.edu.3163194.0 +3 -0
- logs/text2image-fine-tune-sdxl/events.out.tfevents.1725940592.datasec2.engr.uconn.edu.3163636.0 +3 -0
- logs/text2image-fine-tune-sdxl/events.out.tfevents.1725940673.datasec2.engr.uconn.edu.3163851.0 +3 -0
- logs/text2image-fine-tune-sdxl/events.out.tfevents.1725940759.datasec2.engr.uconn.edu.3164079.0 +3 -0
- model_index.json +42 -0
- scheduler/scheduler_config.json +23 -0
- text_encoder/config.json +25 -0
- text_encoder/model.safetensors +3 -0
- text_encoder_2/config.json +25 -0
- text_encoder_2/model.safetensors +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +24 -0
- tokenizer/tokenizer_config.json +30 -0
- tokenizer/vocab.json +0 -0
- tokenizer_2/merges.txt +0 -0
- tokenizer_2/special_tokens_map.json +24 -0
- tokenizer_2/tokenizer_config.json +38 -0
- tokenizer_2/vocab.json +0 -0
- unet/config.json +73 -0
- unet/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
- unet/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
- unet/diffusion_pytorch_model.safetensors.index.json +0 -0
- vae/config.json +38 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: stabilityai/stable-diffusion-xl-base-1.0
|
3 |
+
library_name: diffusers
|
4 |
+
license: creativeml-openrail-m
|
5 |
+
tags:
|
6 |
+
- stable-diffusion-xl
|
7 |
+
- stable-diffusion-xl-diffusers
|
8 |
+
- text-to-image
|
9 |
+
- diffusers-training
|
10 |
+
- diffusers
|
11 |
+
inference: true
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
|
18 |
+
# Text-to-image finetuning - haorandai/temp
|
19 |
+
|
20 |
+
This pipeline was finetuned from **stabilityai/stable-diffusion-xl-base-1.0** on the **haorandai/Vehicle_Bicycle_lr0.01_e0.1_20_with20constraints** dataset. Below are some example images generated with the finetuned pipeline using the following prompt: None:
|
21 |
+
|
22 |
+
|
23 |
+
|
24 |
+
Special VAE used for training: None.
|
25 |
+
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
#### How to use
|
30 |
+
|
31 |
+
```python
|
32 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
33 |
+
```
|
34 |
+
|
35 |
+
#### Limitations and bias
|
36 |
+
|
37 |
+
[TODO: provide examples of latent issues and potential remediations]
|
38 |
+
|
39 |
+
## Training details
|
40 |
+
|
41 |
+
[TODO: describe the data used to train the model]
|
logs/text2image-fine-tune-sdxl/1725939996.2971735/events.out.tfevents.1725939996.datasec2.engr.uconn.edu.3162987.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41a14c9546e7444566067c1f9abcbeb0b59732f8654905a8dc7df6f86abf96e5
|
3 |
+
size 2673
|
logs/text2image-fine-tune-sdxl/1725939996.298438/hparams.yml
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 500
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: haorandai/Vehicle_Bicycle_lr0.01_e0.1_20_with20constraints
|
14 |
+
enable_npu_flash_attention: false
|
15 |
+
enable_xformers_memory_efficient_attention: false
|
16 |
+
gradient_accumulation_steps: 4
|
17 |
+
gradient_checkpointing: true
|
18 |
+
hub_model_id: null
|
19 |
+
hub_token: null
|
20 |
+
image_column: image
|
21 |
+
learning_rate: 1.0e-05
|
22 |
+
local_rank: 0
|
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: 200
|
29 |
+
mixed_precision: fp16
|
30 |
+
noise_offset: 0
|
31 |
+
num_train_epochs: 40
|
32 |
+
num_validation_images: 4
|
33 |
+
output_dir: ./temp/.
|
34 |
+
prediction_type: null
|
35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
36 |
+
pretrained_vae_model_name_or_path: null
|
37 |
+
proportion_empty_prompts: 0
|
38 |
+
push_to_hub: true
|
39 |
+
random_flip: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 512
|
42 |
+
resume_from_checkpoint: null
|
43 |
+
revision: null
|
44 |
+
scale_lr: false
|
45 |
+
seed: null
|
46 |
+
snr_gamma: null
|
47 |
+
timestep_bias_begin: 0
|
48 |
+
timestep_bias_end: 1000
|
49 |
+
timestep_bias_multiplier: 1.0
|
50 |
+
timestep_bias_portion: 0.25
|
51 |
+
timestep_bias_strategy: none
|
52 |
+
train_batch_size: 1
|
53 |
+
train_data_dir: null
|
54 |
+
use_8bit_adam: false
|
55 |
+
use_ema: true
|
56 |
+
validation_epochs: 1
|
57 |
+
validation_prompt: null
|
58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/1725940292.1553288/events.out.tfevents.1725940292.datasec2.engr.uconn.edu.3163194.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e68712ad0a2d0a7cb3dd9c2692076faf75e43d59f3610470dc771e6620f77164
|
3 |
+
size 2673
|
logs/text2image-fine-tune-sdxl/1725940292.1573727/hparams.yml
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 500
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: haorandai/Vehicle_Bicycle_lr0.01_e0.1_20_with20constraints
|
14 |
+
enable_npu_flash_attention: false
|
15 |
+
enable_xformers_memory_efficient_attention: false
|
16 |
+
gradient_accumulation_steps: 4
|
17 |
+
gradient_checkpointing: true
|
18 |
+
hub_model_id: null
|
19 |
+
hub_token: null
|
20 |
+
image_column: image
|
21 |
+
learning_rate: 1.0e-05
|
22 |
+
local_rank: 0
|
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: 200
|
29 |
+
mixed_precision: fp16
|
30 |
+
noise_offset: 0
|
31 |
+
num_train_epochs: 40
|
32 |
+
num_validation_images: 4
|
33 |
+
output_dir: ./temp/.
|
34 |
+
prediction_type: null
|
35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
36 |
+
pretrained_vae_model_name_or_path: null
|
37 |
+
proportion_empty_prompts: 0
|
38 |
+
push_to_hub: true
|
39 |
+
random_flip: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 512
|
42 |
+
resume_from_checkpoint: null
|
43 |
+
revision: null
|
44 |
+
scale_lr: false
|
45 |
+
seed: null
|
46 |
+
snr_gamma: null
|
47 |
+
timestep_bias_begin: 0
|
48 |
+
timestep_bias_end: 1000
|
49 |
+
timestep_bias_multiplier: 1.0
|
50 |
+
timestep_bias_portion: 0.25
|
51 |
+
timestep_bias_strategy: none
|
52 |
+
train_batch_size: 1
|
53 |
+
train_data_dir: null
|
54 |
+
use_8bit_adam: false
|
55 |
+
use_ema: true
|
56 |
+
validation_epochs: 1
|
57 |
+
validation_prompt: null
|
58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/1725940592.6629992/events.out.tfevents.1725940592.datasec2.engr.uconn.edu.3163636.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3a7be69a6adf6c455c9a0c648e49ee600ed467111f5196fd35cd663fb670fe9
|
3 |
+
size 2673
|
logs/text2image-fine-tune-sdxl/1725940592.665023/hparams.yml
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 500
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: haorandai/Vehicle_Bicycle_lr0.01_e0.1_20_with20constraints
|
14 |
+
enable_npu_flash_attention: false
|
15 |
+
enable_xformers_memory_efficient_attention: false
|
16 |
+
gradient_accumulation_steps: 4
|
17 |
+
gradient_checkpointing: true
|
18 |
+
hub_model_id: null
|
19 |
+
hub_token: null
|
20 |
+
image_column: image
|
21 |
+
learning_rate: 1.0e-05
|
22 |
+
local_rank: 0
|
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: 200
|
29 |
+
mixed_precision: fp16
|
30 |
+
noise_offset: 0
|
31 |
+
num_train_epochs: 40
|
32 |
+
num_validation_images: 4
|
33 |
+
output_dir: ./temp/.
|
34 |
+
prediction_type: null
|
35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
36 |
+
pretrained_vae_model_name_or_path: null
|
37 |
+
proportion_empty_prompts: 0
|
38 |
+
push_to_hub: true
|
39 |
+
random_flip: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 512
|
42 |
+
resume_from_checkpoint: null
|
43 |
+
revision: null
|
44 |
+
scale_lr: false
|
45 |
+
seed: null
|
46 |
+
snr_gamma: null
|
47 |
+
timestep_bias_begin: 0
|
48 |
+
timestep_bias_end: 1000
|
49 |
+
timestep_bias_multiplier: 1.0
|
50 |
+
timestep_bias_portion: 0.25
|
51 |
+
timestep_bias_strategy: none
|
52 |
+
train_batch_size: 1
|
53 |
+
train_data_dir: null
|
54 |
+
use_8bit_adam: false
|
55 |
+
use_ema: true
|
56 |
+
validation_epochs: 1
|
57 |
+
validation_prompt: null
|
58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/1725940673.437566/events.out.tfevents.1725940673.datasec2.engr.uconn.edu.3163851.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44d7189b40af3625985568e8d9b3d730df23599891d89de1e5c83011f99a7ccc
|
3 |
+
size 2673
|
logs/text2image-fine-tune-sdxl/1725940673.438938/hparams.yml
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 500
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: haorandai/Vehicle_Bicycle_lr0.01_e0.1_20_with20constraints
|
14 |
+
enable_npu_flash_attention: false
|
15 |
+
enable_xformers_memory_efficient_attention: false
|
16 |
+
gradient_accumulation_steps: 4
|
17 |
+
gradient_checkpointing: true
|
18 |
+
hub_model_id: null
|
19 |
+
hub_token: null
|
20 |
+
image_column: image
|
21 |
+
learning_rate: 1.0e-05
|
22 |
+
local_rank: 0
|
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: 200
|
29 |
+
mixed_precision: fp16
|
30 |
+
noise_offset: 0
|
31 |
+
num_train_epochs: 40
|
32 |
+
num_validation_images: 4
|
33 |
+
output_dir: ./temp/.
|
34 |
+
prediction_type: null
|
35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
36 |
+
pretrained_vae_model_name_or_path: null
|
37 |
+
proportion_empty_prompts: 0
|
38 |
+
push_to_hub: true
|
39 |
+
random_flip: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 512
|
42 |
+
resume_from_checkpoint: null
|
43 |
+
revision: null
|
44 |
+
scale_lr: false
|
45 |
+
seed: null
|
46 |
+
snr_gamma: null
|
47 |
+
timestep_bias_begin: 0
|
48 |
+
timestep_bias_end: 1000
|
49 |
+
timestep_bias_multiplier: 1.0
|
50 |
+
timestep_bias_portion: 0.25
|
51 |
+
timestep_bias_strategy: none
|
52 |
+
train_batch_size: 1
|
53 |
+
train_data_dir: null
|
54 |
+
use_8bit_adam: false
|
55 |
+
use_ema: true
|
56 |
+
validation_epochs: 1
|
57 |
+
validation_prompt: null
|
58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/1725940759.4802158/events.out.tfevents.1725940759.datasec2.engr.uconn.edu.3164079.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86a5864abee0937ba1372355c09637e3f6f5e43a7d7e71f19cc3c31f1eb94ea5
|
3 |
+
size 2673
|
logs/text2image-fine-tune-sdxl/1725940759.4820197/hparams.yml
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 500
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: haorandai/Vehicle_Bicycle_lr0.01_e0.1_20_with20constraints
|
14 |
+
enable_npu_flash_attention: false
|
15 |
+
enable_xformers_memory_efficient_attention: false
|
16 |
+
gradient_accumulation_steps: 4
|
17 |
+
gradient_checkpointing: true
|
18 |
+
hub_model_id: null
|
19 |
+
hub_token: null
|
20 |
+
image_column: image
|
21 |
+
learning_rate: 1.0e-05
|
22 |
+
local_rank: 0
|
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: 200
|
29 |
+
mixed_precision: fp16
|
30 |
+
noise_offset: 0
|
31 |
+
num_train_epochs: 40
|
32 |
+
num_validation_images: 4
|
33 |
+
output_dir: ./temp/.
|
34 |
+
prediction_type: null
|
35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
36 |
+
pretrained_vae_model_name_or_path: null
|
37 |
+
proportion_empty_prompts: 0
|
38 |
+
push_to_hub: true
|
39 |
+
random_flip: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 512
|
42 |
+
resume_from_checkpoint: null
|
43 |
+
revision: null
|
44 |
+
scale_lr: false
|
45 |
+
seed: null
|
46 |
+
snr_gamma: null
|
47 |
+
timestep_bias_begin: 0
|
48 |
+
timestep_bias_end: 1000
|
49 |
+
timestep_bias_multiplier: 1.0
|
50 |
+
timestep_bias_portion: 0.25
|
51 |
+
timestep_bias_strategy: none
|
52 |
+
train_batch_size: 1
|
53 |
+
train_data_dir: null
|
54 |
+
use_8bit_adam: false
|
55 |
+
use_ema: true
|
56 |
+
validation_epochs: 1
|
57 |
+
validation_prompt: null
|
58 |
+
variant: null
|
logs/text2image-fine-tune-sdxl/events.out.tfevents.1725939996.datasec2.engr.uconn.edu.3162987.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97e2c55903f9f1f8b3b21600a10faf0c9ef4738e640bc0d8cc3ac551a3087a9f
|
3 |
+
size 88
|
logs/text2image-fine-tune-sdxl/events.out.tfevents.1725940292.datasec2.engr.uconn.edu.3163194.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e650f03eaf104e198d8052a7058448137443a2d50cfa269699de96e38316e88
|
3 |
+
size 88
|
logs/text2image-fine-tune-sdxl/events.out.tfevents.1725940592.datasec2.engr.uconn.edu.3163636.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f106f15ddf94b03409abd2bef0251985255f64ba463e2a2abab8cb63ebe762a
|
3 |
+
size 88
|
logs/text2image-fine-tune-sdxl/events.out.tfevents.1725940673.datasec2.engr.uconn.edu.3163851.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0597515fdeefb062ee0668b3159d766d65d1b343d78bb04d64852a1a5c7b7993
|
3 |
+
size 88
|
logs/text2image-fine-tune-sdxl/events.out.tfevents.1725940759.datasec2.engr.uconn.edu.3164079.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67ab08395a21903725130d4cca53de29f8652c287a56d995b93558566293a11f
|
3 |
+
size 9761
|
model_index.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionXLPipeline",
|
3 |
+
"_diffusers_version": "0.31.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
5 |
+
"feature_extractor": [
|
6 |
+
null,
|
7 |
+
null
|
8 |
+
],
|
9 |
+
"force_zeros_for_empty_prompt": true,
|
10 |
+
"image_encoder": [
|
11 |
+
null,
|
12 |
+
null
|
13 |
+
],
|
14 |
+
"scheduler": [
|
15 |
+
"diffusers",
|
16 |
+
"EulerDiscreteScheduler"
|
17 |
+
],
|
18 |
+
"text_encoder": [
|
19 |
+
"transformers",
|
20 |
+
"CLIPTextModel"
|
21 |
+
],
|
22 |
+
"text_encoder_2": [
|
23 |
+
"transformers",
|
24 |
+
"CLIPTextModelWithProjection"
|
25 |
+
],
|
26 |
+
"tokenizer": [
|
27 |
+
"transformers",
|
28 |
+
"CLIPTokenizer"
|
29 |
+
],
|
30 |
+
"tokenizer_2": [
|
31 |
+
"transformers",
|
32 |
+
"CLIPTokenizer"
|
33 |
+
],
|
34 |
+
"unet": [
|
35 |
+
"diffusers",
|
36 |
+
"UNet2DConditionModel"
|
37 |
+
],
|
38 |
+
"vae": [
|
39 |
+
"diffusers",
|
40 |
+
"AutoencoderKL"
|
41 |
+
]
|
42 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "EulerDiscreteScheduler",
|
3 |
+
"_diffusers_version": "0.31.0.dev0",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"clip_sample": false,
|
8 |
+
"final_sigmas_type": "zero",
|
9 |
+
"interpolation_type": "linear",
|
10 |
+
"num_train_timesteps": 1000,
|
11 |
+
"prediction_type": "epsilon",
|
12 |
+
"rescale_betas_zero_snr": false,
|
13 |
+
"sample_max_value": 1.0,
|
14 |
+
"set_alpha_to_one": false,
|
15 |
+
"sigma_max": null,
|
16 |
+
"sigma_min": null,
|
17 |
+
"skip_prk_steps": true,
|
18 |
+
"steps_offset": 1,
|
19 |
+
"timestep_spacing": "leading",
|
20 |
+
"timestep_type": "discrete",
|
21 |
+
"trained_betas": null,
|
22 |
+
"use_karras_sigmas": false
|
23 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/biw23007/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/text_encoder",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModel"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "quick_gelu",
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 768,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
|
3 |
+
size 246144152
|
text_encoder_2/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/biw23007/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/text_encoder_2",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModelWithProjection"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_size": 1280,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5120,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 20,
|
19 |
+
"num_hidden_layers": 32,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 1280,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
text_encoder_2/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
|
3 |
+
size 1389382176
|
tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"49406": {
|
5 |
+
"content": "<|startoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"49407": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"bos_token": "<|startoftext|>",
|
22 |
+
"clean_up_tokenization_spaces": true,
|
23 |
+
"do_lower_case": true,
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"errors": "replace",
|
26 |
+
"model_max_length": 77,
|
27 |
+
"pad_token": "<|endoftext|>",
|
28 |
+
"tokenizer_class": "CLIPTokenizer",
|
29 |
+
"unk_token": "<|endoftext|>"
|
30 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_2/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_2/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "!",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer_2/tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "!",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"49406": {
|
13 |
+
"content": "<|startoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"49407": {
|
21 |
+
"content": "<|endoftext|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"bos_token": "<|startoftext|>",
|
30 |
+
"clean_up_tokenization_spaces": true,
|
31 |
+
"do_lower_case": true,
|
32 |
+
"eos_token": "<|endoftext|>",
|
33 |
+
"errors": "replace",
|
34 |
+
"model_max_length": 77,
|
35 |
+
"pad_token": "!",
|
36 |
+
"tokenizer_class": "CLIPTokenizer",
|
37 |
+
"unk_token": "<|endoftext|>"
|
38 |
+
}
|
tokenizer_2/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.31.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
unet/diffusion_pytorch_model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41ff3a7391c7626d7cd861c4c2495a65e818373aac641628ad43b649bdb27621
|
3 |
+
size 9988139160
|
unet/diffusion_pytorch_model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:469a809ee4948631e50e12cfaa960d16430e186cddecf7718581dc884c613918
|
3 |
+
size 281938304
|
unet/diffusion_pytorch_model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vae/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.31.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"block_out_channels": [
|
7 |
+
128,
|
8 |
+
256,
|
9 |
+
512,
|
10 |
+
512
|
11 |
+
],
|
12 |
+
"down_block_types": [
|
13 |
+
"DownEncoderBlock2D",
|
14 |
+
"DownEncoderBlock2D",
|
15 |
+
"DownEncoderBlock2D",
|
16 |
+
"DownEncoderBlock2D"
|
17 |
+
],
|
18 |
+
"force_upcast": true,
|
19 |
+
"in_channels": 3,
|
20 |
+
"latent_channels": 4,
|
21 |
+
"latents_mean": null,
|
22 |
+
"latents_std": null,
|
23 |
+
"layers_per_block": 2,
|
24 |
+
"mid_block_add_attention": true,
|
25 |
+
"norm_num_groups": 32,
|
26 |
+
"out_channels": 3,
|
27 |
+
"sample_size": 1024,
|
28 |
+
"scaling_factor": 0.13025,
|
29 |
+
"shift_factor": null,
|
30 |
+
"up_block_types": [
|
31 |
+
"UpDecoderBlock2D",
|
32 |
+
"UpDecoderBlock2D",
|
33 |
+
"UpDecoderBlock2D",
|
34 |
+
"UpDecoderBlock2D"
|
35 |
+
],
|
36 |
+
"use_post_quant_conv": true,
|
37 |
+
"use_quant_conv": true
|
38 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68
|
3 |
+
size 167335342
|