kerianheYi
commited on
Commit
•
7a3a366
1
Parent(s):
1ab4f65
End of training
Browse files- README.md +3 -3
- logs/text2image-fine-tune/1701127851.6032078/events.out.tfevents.1701127851.251c89de5e85.21171.1 +3 -0
- logs/text2image-fine-tune/1701127851.6048746/hparams.yml +51 -0
- logs/text2image-fine-tune/1701127965.9765682/events.out.tfevents.1701127965.251c89de5e85.21691.1 +3 -0
- logs/text2image-fine-tune/1701127965.9782622/hparams.yml +51 -0
- logs/text2image-fine-tune/events.out.tfevents.1701127372.251c89de5e85.19106.0 +2 -2
- logs/text2image-fine-tune/events.out.tfevents.1701127851.251c89de5e85.21171.0 +3 -0
- logs/text2image-fine-tune/events.out.tfevents.1701127965.251c89de5e85.21691.0 +3 -0
- unet/diffusion_pytorch_model.safetensors +1 -1
- val_imgs_grid.png +0 -0
README.md
CHANGED
@@ -14,7 +14,7 @@ inference: true
|
|
14 |
|
15 |
# Text-to-image finetuning - kerianheYi/CS245-fine-tunedSD100
|
16 |
|
17 |
-
This pipeline was finetuned from **stabilityai/stable-diffusion-2-base** on the **jytjyt05/t_to_m2** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['
|
18 |
|
19 |
![val_imgs_grid](./val_imgs_grid.png)
|
20 |
|
@@ -28,7 +28,7 @@ from diffusers import DiffusionPipeline
|
|
28 |
import torch
|
29 |
|
30 |
pipeline = DiffusionPipeline.from_pretrained("kerianheYi/CS245-fine-tunedSD100", torch_dtype=torch.float16)
|
31 |
-
prompt = "
|
32 |
image = pipeline(prompt).images[0]
|
33 |
image.save("my_image.png")
|
34 |
```
|
@@ -37,7 +37,7 @@ image.save("my_image.png")
|
|
37 |
|
38 |
These are the key hyperparameters used during training:
|
39 |
|
40 |
-
* Epochs:
|
41 |
* Learning rate: 1e-05
|
42 |
* Batch size: 1
|
43 |
* Gradient accumulation steps: 4
|
|
|
14 |
|
15 |
# Text-to-image finetuning - kerianheYi/CS245-fine-tunedSD100
|
16 |
|
17 |
+
This pipeline was finetuned from **stabilityai/stable-diffusion-2-base** on the **jytjyt05/t_to_m2** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A classical piano solo in C-major']:
|
18 |
|
19 |
![val_imgs_grid](./val_imgs_grid.png)
|
20 |
|
|
|
28 |
import torch
|
29 |
|
30 |
pipeline = DiffusionPipeline.from_pretrained("kerianheYi/CS245-fine-tunedSD100", torch_dtype=torch.float16)
|
31 |
+
prompt = "A classical piano solo in C-major"
|
32 |
image = pipeline(prompt).images[0]
|
33 |
image.save("my_image.png")
|
34 |
```
|
|
|
37 |
|
38 |
These are the key hyperparameters used during training:
|
39 |
|
40 |
+
* Epochs: 4
|
41 |
* Learning rate: 1e-05
|
42 |
* Batch size: 1
|
43 |
* Gradient accumulation steps: 4
|
logs/text2image-fine-tune/1701127851.6032078/events.out.tfevents.1701127851.251c89de5e85.21171.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b62308495713669ca0f3501769fbe7b7a0bc588612b3d7a074683288f5f9c47
|
3 |
+
size 2271
|
logs/text2image-fine-tune/1701127851.6048746/hparams.yml
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: caption
|
8 |
+
center_crop: false
|
9 |
+
checkpointing_steps: 100000
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: jytjyt05/t_to_m2
|
14 |
+
enable_xformers_memory_efficient_attention: false
|
15 |
+
gradient_accumulation_steps: 4
|
16 |
+
gradient_checkpointing: true
|
17 |
+
hub_model_id: null
|
18 |
+
hub_token: null
|
19 |
+
image_column: image
|
20 |
+
input_perturbation: 0
|
21 |
+
learning_rate: 1.0e-05
|
22 |
+
local_rank: -1
|
23 |
+
logging_dir: logs
|
24 |
+
lr_scheduler: constant
|
25 |
+
lr_warmup_steps: 0
|
26 |
+
max_grad_norm: 1.0
|
27 |
+
max_train_samples: null
|
28 |
+
max_train_steps: 1
|
29 |
+
mixed_precision: fp16
|
30 |
+
noise_offset: 0
|
31 |
+
non_ema_revision: null
|
32 |
+
num_train_epochs: 1
|
33 |
+
output_dir: kerianheyi/CS245-fine-tunedSD100
|
34 |
+
prediction_type: null
|
35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-base
|
36 |
+
push_to_hub: true
|
37 |
+
random_flip: false
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 512
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
scale_lr: false
|
43 |
+
seed: null
|
44 |
+
snr_gamma: null
|
45 |
+
tracker_project_name: text2image-fine-tune
|
46 |
+
train_batch_size: 1
|
47 |
+
train_data_dir: null
|
48 |
+
use_8bit_adam: false
|
49 |
+
use_ema: true
|
50 |
+
validation_epochs: 5
|
51 |
+
variant: null
|
logs/text2image-fine-tune/1701127965.9765682/events.out.tfevents.1701127965.251c89de5e85.21691.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c400ab29f7f05b7dc7e3fbb61a15e95ebbcdd4999e53ac78690e882515efaecf
|
3 |
+
size 2271
|
logs/text2image-fine-tune/1701127965.9782622/hparams.yml
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: caption
|
8 |
+
center_crop: false
|
9 |
+
checkpointing_steps: 100000
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: jytjyt05/t_to_m2
|
14 |
+
enable_xformers_memory_efficient_attention: false
|
15 |
+
gradient_accumulation_steps: 4
|
16 |
+
gradient_checkpointing: true
|
17 |
+
hub_model_id: null
|
18 |
+
hub_token: null
|
19 |
+
image_column: image
|
20 |
+
input_perturbation: 0
|
21 |
+
learning_rate: 1.0e-05
|
22 |
+
local_rank: -1
|
23 |
+
logging_dir: logs
|
24 |
+
lr_scheduler: constant
|
25 |
+
lr_warmup_steps: 0
|
26 |
+
max_grad_norm: 1.0
|
27 |
+
max_train_samples: null
|
28 |
+
max_train_steps: 100
|
29 |
+
mixed_precision: fp16
|
30 |
+
noise_offset: 0
|
31 |
+
non_ema_revision: null
|
32 |
+
num_train_epochs: 4
|
33 |
+
output_dir: kerianheyi/CS245-fine-tunedSD100
|
34 |
+
prediction_type: null
|
35 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-base
|
36 |
+
push_to_hub: true
|
37 |
+
random_flip: false
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 512
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
scale_lr: false
|
43 |
+
seed: null
|
44 |
+
snr_gamma: null
|
45 |
+
tracker_project_name: text2image-fine-tune
|
46 |
+
train_batch_size: 1
|
47 |
+
train_data_dir: null
|
48 |
+
use_8bit_adam: false
|
49 |
+
use_ema: true
|
50 |
+
validation_epochs: 5
|
51 |
+
variant: null
|
logs/text2image-fine-tune/events.out.tfevents.1701127372.251c89de5e85.19106.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93f71777f8a6a3b4f747cae02a910650169b8665f4d5e381d29e36bf6c38adbb
|
3 |
+
size 345363
|
logs/text2image-fine-tune/events.out.tfevents.1701127851.251c89de5e85.21171.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65ec755a9576029528a94bac88256aee1e7a3dcbceaa9ffae2ba5adfd897e829
|
3 |
+
size 136
|
logs/text2image-fine-tune/events.out.tfevents.1701127965.251c89de5e85.21691.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb07a42cbac020ebe2628de4a5af4a885c2669d128c54548804b226f6d7eb5e9
|
3 |
+
size 284021
|
unet/diffusion_pytorch_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3463726504
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6aabe1549dc388a9b41dc2af9a695425bc30d92e6b1e0c9c19ce807c601672e5
|
3 |
size 3463726504
|
val_imgs_grid.png
CHANGED