bongbongbong
commited on
Commit
•
9b46ab4
1
Parent(s):
80ac3a5
End of training
Browse files- README.md +43 -0
- image_0.png +0 -0
- image_1.png +0 -0
- image_2.png +0 -0
- image_3.png +0 -0
- logs/text2image-fine-tune/1726582576.6716561/events.out.tfevents.1726582576.8c9f9911d24f.6308.1 +3 -0
- logs/text2image-fine-tune/1726582576.687166/hparams.yml +50 -0
- logs/text2image-fine-tune/1726584396.7526689/events.out.tfevents.1726584396.f41229a69832.2341.1 +3 -0
- logs/text2image-fine-tune/1726584396.7835157/hparams.yml +50 -0
- logs/text2image-fine-tune/1726585965.1546402/events.out.tfevents.1726585965.f41229a69832.9180.1 +3 -0
- logs/text2image-fine-tune/1726585965.1635497/hparams.yml +50 -0
- logs/text2image-fine-tune/events.out.tfevents.1726582576.8c9f9911d24f.6308.0 +3 -0
- logs/text2image-fine-tune/events.out.tfevents.1726584396.f41229a69832.2341.0 +3 -0
- logs/text2image-fine-tune/events.out.tfevents.1726585965.f41229a69832.9180.0 +3 -0
- pytorch_lora_weights.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: sd-legacy/stable-diffusion-v1-5
|
3 |
+
library_name: diffusers
|
4 |
+
license: creativeml-openrail-m
|
5 |
+
tags:
|
6 |
+
- stable-diffusion
|
7 |
+
- stable-diffusion-diffusers
|
8 |
+
- text-to-image
|
9 |
+
- diffusers
|
10 |
+
- diffusers-training
|
11 |
+
- lora
|
12 |
+
inference: true
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
|
19 |
+
# LoRA text2image fine-tuning - bongbongbong/LoRA_Output
|
20 |
+
These are LoRA adaption weights for sd-legacy/stable-diffusion-v1-5. The weights were fine-tuned on the lambdalabs/naruto-blip-captions dataset. You can find some example images in the following.
|
21 |
+
|
22 |
+
![img_0](./image_0.png)
|
23 |
+
![img_1](./image_1.png)
|
24 |
+
![img_2](./image_2.png)
|
25 |
+
![img_3](./image_3.png)
|
26 |
+
|
27 |
+
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
#### How to use
|
32 |
+
|
33 |
+
```python
|
34 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
35 |
+
```
|
36 |
+
|
37 |
+
#### Limitations and bias
|
38 |
+
|
39 |
+
[TODO: provide examples of latent issues and potential remediations]
|
40 |
+
|
41 |
+
## Training details
|
42 |
+
|
43 |
+
[TODO: describe the data used to train the model]
|
image_0.png
ADDED
image_1.png
ADDED
image_2.png
ADDED
image_3.png
ADDED
logs/text2image-fine-tune/1726582576.6716561/events.out.tfevents.1726582576.8c9f9911d24f.6308.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:920d081a9e563e41da1f812143823dcc2a1a22ce38d37a0d88109f668512a744
|
3 |
+
size 2257
|
logs/text2image-fine-tune/1726582576.687166/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 |
+
cache_dir: null
|
7 |
+
caption_column: text
|
8 |
+
center_crop: true
|
9 |
+
checkpointing_steps: 500
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 4
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: lambdalabs/naruto-blip-captions
|
14 |
+
enable_xformers_memory_efficient_attention: false
|
15 |
+
gradient_accumulation_steps: 4
|
16 |
+
gradient_checkpointing: false
|
17 |
+
hub_model_id: null
|
18 |
+
hub_token: null
|
19 |
+
image_column: image
|
20 |
+
learning_rate: 0.0001
|
21 |
+
local_rank: -1
|
22 |
+
logging_dir: logs
|
23 |
+
lr_scheduler: cosine
|
24 |
+
lr_warmup_steps: 0
|
25 |
+
max_grad_norm: 1.0
|
26 |
+
max_train_samples: null
|
27 |
+
max_train_steps: 2000
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 7
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: /content/drive/MyDrive/LoRA_Output
|
33 |
+
prediction_type: null
|
34 |
+
pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
|
35 |
+
push_to_hub: false
|
36 |
+
random_flip: true
|
37 |
+
rank: 4
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 512
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
scale_lr: false
|
43 |
+
seed: 1337
|
44 |
+
snr_gamma: null
|
45 |
+
train_batch_size: 1
|
46 |
+
train_data_dir: null
|
47 |
+
use_8bit_adam: false
|
48 |
+
validation_epochs: 1
|
49 |
+
validation_prompt: A naruto with blue eyes.
|
50 |
+
variant: null
|
logs/text2image-fine-tune/1726584396.7526689/events.out.tfevents.1726584396.f41229a69832.2341.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a885c5f7ad1620468b1e35e435df061f014c25df5f3b3c8f958a2b1c7692fe16
|
3 |
+
size 2257
|
logs/text2image-fine-tune/1726584396.7835157/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 |
+
cache_dir: null
|
7 |
+
caption_column: text
|
8 |
+
center_crop: true
|
9 |
+
checkpointing_steps: 500
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 4
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: lambdalabs/naruto-blip-captions
|
14 |
+
enable_xformers_memory_efficient_attention: false
|
15 |
+
gradient_accumulation_steps: 4
|
16 |
+
gradient_checkpointing: false
|
17 |
+
hub_model_id: null
|
18 |
+
hub_token: null
|
19 |
+
image_column: image
|
20 |
+
learning_rate: 0.0001
|
21 |
+
local_rank: -1
|
22 |
+
logging_dir: logs
|
23 |
+
lr_scheduler: cosine
|
24 |
+
lr_warmup_steps: 0
|
25 |
+
max_grad_norm: 1.0
|
26 |
+
max_train_samples: null
|
27 |
+
max_train_steps: 2000
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 7
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: /content/drive/MyDrive/LoRA_Output
|
33 |
+
prediction_type: null
|
34 |
+
pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
|
35 |
+
push_to_hub: true
|
36 |
+
random_flip: true
|
37 |
+
rank: 4
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 512
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
scale_lr: false
|
43 |
+
seed: 1337
|
44 |
+
snr_gamma: null
|
45 |
+
train_batch_size: 1
|
46 |
+
train_data_dir: null
|
47 |
+
use_8bit_adam: false
|
48 |
+
validation_epochs: 1
|
49 |
+
validation_prompt: A naruto with blue eyes.
|
50 |
+
variant: null
|
logs/text2image-fine-tune/1726585965.1546402/events.out.tfevents.1726585965.f41229a69832.9180.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4dce0ab5fec21119bd98f7513d8a84b9960f94b8d70cd5adf877ce8bd94e944
|
3 |
+
size 2258
|
logs/text2image-fine-tune/1726585965.1635497/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 |
+
cache_dir: null
|
7 |
+
caption_column: text
|
8 |
+
center_crop: true
|
9 |
+
checkpointing_steps: 500
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 4
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: lambdalabs/naruto-blip-captions
|
14 |
+
enable_xformers_memory_efficient_attention: false
|
15 |
+
gradient_accumulation_steps: 4
|
16 |
+
gradient_checkpointing: false
|
17 |
+
hub_model_id: null
|
18 |
+
hub_token: null
|
19 |
+
image_column: image
|
20 |
+
learning_rate: 0.0001
|
21 |
+
local_rank: -1
|
22 |
+
logging_dir: logs
|
23 |
+
lr_scheduler: cosine
|
24 |
+
lr_warmup_steps: 0
|
25 |
+
max_grad_norm: 1.0
|
26 |
+
max_train_samples: null
|
27 |
+
max_train_steps: 100
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 1
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: /content/drive/MyDrive/LoRA_Output
|
33 |
+
prediction_type: null
|
34 |
+
pretrained_model_name_or_path: sd-legacy/stable-diffusion-v1-5
|
35 |
+
push_to_hub: true
|
36 |
+
random_flip: true
|
37 |
+
rank: 4
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 512
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
scale_lr: false
|
43 |
+
seed: 1337
|
44 |
+
snr_gamma: null
|
45 |
+
train_batch_size: 1
|
46 |
+
train_data_dir: null
|
47 |
+
use_8bit_adam: false
|
48 |
+
validation_epochs: 1
|
49 |
+
validation_prompt: A naruto with blue eyes.
|
50 |
+
variant: null
|
logs/text2image-fine-tune/events.out.tfevents.1726582576.8c9f9911d24f.6308.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:868d139173ed972c831e726cd30fc1b71a93a44b7054e5da46636c3927fac9e0
|
3 |
+
size 88
|
logs/text2image-fine-tune/events.out.tfevents.1726584396.f41229a69832.2341.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d9d78be4b3b3bb62f2f4e37448de43c713dde86fcb3cc5178738f28fcd93c3a
|
3 |
+
size 14955
|
logs/text2image-fine-tune/events.out.tfevents.1726585965.f41229a69832.9180.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bbe967f0392784648bc1049f2f115b3d3cc927a3adf5c6e8011c46f833eb15e
|
3 |
+
size 3135643
|
pytorch_lora_weights.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f84dc09c73be5204fa12779f9c12e7177d183148e0a6c20686bda669b0f3e97
|
3 |
+
size 3226184
|