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/1715894881.183883/events.out.tfevents.1715894881.00c2cf366f47.5981.1 +3 -0
- logs/text2image-fine-tune/1715894881.1855834/hparams.yml +50 -0
- logs/text2image-fine-tune/1715895143.540366/events.out.tfevents.1715895143.00c2cf366f47.7173.1 +3 -0
- logs/text2image-fine-tune/1715895143.542124/hparams.yml +50 -0
- logs/text2image-fine-tune/1715895689.6005714/events.out.tfevents.1715895689.00c2cf366f47.9493.1 +3 -0
- logs/text2image-fine-tune/1715895689.6024177/hparams.yml +50 -0
- logs/text2image-fine-tune/1715895756.1334956/events.out.tfevents.1715895756.00c2cf366f47.9847.1 +3 -0
- logs/text2image-fine-tune/1715895756.1357365/hparams.yml +50 -0
- logs/text2image-fine-tune/events.out.tfevents.1715894881.00c2cf366f47.5981.0 +3 -0
- logs/text2image-fine-tune/events.out.tfevents.1715895143.00c2cf366f47.7173.0 +3 -0
- logs/text2image-fine-tune/events.out.tfevents.1715895689.00c2cf366f47.9493.0 +3 -0
- logs/text2image-fine-tune/events.out.tfevents.1715895756.00c2cf366f47.9847.0 +3 -0
- pytorch_lora_weights.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: creativeml-openrail-m
|
3 |
+
library_name: diffusers
|
4 |
+
tags:
|
5 |
+
- stable-diffusion
|
6 |
+
- stable-diffusion-diffusers
|
7 |
+
- text-to-image
|
8 |
+
- diffusers
|
9 |
+
- diffusers-training
|
10 |
+
- lora
|
11 |
+
base_model: runwayml/stable-diffusion-v1-5
|
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 - ffkatya/naruto-lora
|
20 |
+
These are LoRA adaption weights for runwayml/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/1715894881.183883/events.out.tfevents.1715894881.00c2cf366f47.5981.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5a9493b17973cacff60591efa28ebe2955aa642930d11804e7eb68af2fc371c
|
3 |
+
size 2284
|
logs/text2image-fine-tune/1715894881.1855834/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: 8
|
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: pokemon-lora
|
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: 15000
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 50
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: /sddata/finetune/lora/pokemon
|
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: 42
|
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: Totoro
|
50 |
+
variant: null
|
logs/text2image-fine-tune/1715895143.540366/events.out.tfevents.1715895143.00c2cf366f47.7173.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:701bdd90221320eae2cc8ec112ae526c9b5e1ca4c1ab17a4181be3d910bfa792
|
3 |
+
size 2284
|
logs/text2image-fine-tune/1715895143.542124/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: 8
|
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: pokemon-lora
|
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: 15000
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 50
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: /sddata/finetune/lora/pokemon
|
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: 42
|
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: Totoro
|
50 |
+
variant: null
|
logs/text2image-fine-tune/1715895689.6005714/events.out.tfevents.1715895689.00c2cf366f47.9493.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f36d07a7ed6803201a057b6a386c849b38a29b54deb350b1a6c0f94336b2985d
|
3 |
+
size 2283
|
logs/text2image-fine-tune/1715895689.6024177/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: 8
|
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: naruto-lora
|
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: 10000
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 33
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: /sddata/finetune/lora/pokemon
|
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: 128
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
scale_lr: false
|
43 |
+
seed: 42
|
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: Totoro
|
50 |
+
variant: null
|
logs/text2image-fine-tune/1715895756.1334956/events.out.tfevents.1715895756.00c2cf366f47.9847.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b55fc82bef4de035500a80589527972e040df438ec5a0c966e9d30bcf563bac3
|
3 |
+
size 2283
|
logs/text2image-fine-tune/1715895756.1357365/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: 8
|
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: naruto-lora
|
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: 10
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 1
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: /sddata/finetune/lora/pokemon
|
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: 128
|
40 |
+
resume_from_checkpoint: null
|
41 |
+
revision: null
|
42 |
+
scale_lr: false
|
43 |
+
seed: 42
|
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: Totoro
|
50 |
+
variant: null
|
logs/text2image-fine-tune/events.out.tfevents.1715894881.00c2cf366f47.5981.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cbf824e95bcf00d0355e19cd8d302dffdd9979b954dd24b83643c7c383eda7d
|
3 |
+
size 88
|
logs/text2image-fine-tune/events.out.tfevents.1715895143.00c2cf366f47.7173.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df84a61e16f85cf9e63328ae0423afdaeebaa95c4342f17c095ad2cfbc677546
|
3 |
+
size 760
|
logs/text2image-fine-tune/events.out.tfevents.1715895689.00c2cf366f47.9493.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7114130bc512a1615671289435a3c78af11f4a8ca72a949def48b7e3ca51271a
|
3 |
+
size 1432
|
logs/text2image-fine-tune/events.out.tfevents.1715895756.00c2cf366f47.9847.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45db02f7ad63d20bdb40dff5bac19058f53a65b883fabd1447754912a5ee3a75
|
3 |
+
size 1692216
|
pytorch_lora_weights.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f20548dffc38aa3aad888499d7f8fd80fec33901549b5c6937766a8e43781d79
|
3 |
+
size 3226184
|