bharadwajkg
commited on
Commit
•
7ca0deb
1
Parent(s):
e2ef5ae
End of training
Browse files- README.md +21 -0
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-2000/optimizer.bin +3 -0
- checkpoint-2000/pytorch_model.bin +3 -0
- checkpoint-2000/random_states_0.pkl +3 -0
- checkpoint-2000/scaler.pt +3 -0
- checkpoint-2000/scheduler.bin +3 -0
- checkpoint-3000/optimizer.bin +3 -0
- checkpoint-3000/pytorch_model.bin +3 -0
- checkpoint-3000/random_states_0.pkl +3 -0
- checkpoint-3000/scaler.pt +3 -0
- checkpoint-3000/scheduler.bin +3 -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/1691043322.8519316/events.out.tfevents.1691043322.7686de4f6696.203.1 +3 -0
- logs/text2image-fine-tune/1691043322.8548627/hparams.yml +53 -0
- logs/text2image-fine-tune/1691137183.464093/events.out.tfevents.1691137183.5d562fc64c89.222.1 +3 -0
- logs/text2image-fine-tune/1691137183.4675448/hparams.yml +53 -0
- logs/text2image-fine-tune/1691137273.0572374/events.out.tfevents.1691137273.5d562fc64c89.252.1 +3 -0
- logs/text2image-fine-tune/1691137273.0598068/hparams.yml +53 -0
- logs/text2image-fine-tune/events.out.tfevents.1691043322.7686de4f6696.203.0 +3 -0
- logs/text2image-fine-tune/events.out.tfevents.1691137183.5d562fc64c89.222.0 +3 -0
- logs/text2image-fine-tune/events.out.tfevents.1691137273.5d562fc64c89.252.0 +3 -0
- pytorch_lora_weights.bin +3 -0
README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
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 |
+
- lora
|
11 |
+
inference: true
|
12 |
+
---
|
13 |
+
|
14 |
+
# LoRA text2image fine-tuning - bharadwajkg/finetune-sd2-1-planogram-lora-data6
|
15 |
+
These are LoRA adaption weights for stabilityai/stable-diffusion-2-1. The weights were fine-tuned on the bharadwajkg/planogram-sd-original-data6 dataset. You can find some example images in the following.
|
16 |
+
|
17 |
+
![img_0](./image_0.png)
|
18 |
+
![img_1](./image_1.png)
|
19 |
+
![img_2](./image_2.png)
|
20 |
+
![img_3](./image_3.png)
|
21 |
+
|
checkpoint-1000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ae7482179422b926a229f0769b1a0ad04270e08a6be451c45e64195ae8a1cc7
|
3 |
+
size 6853829
|
checkpoint-1000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e5f4a3403319eb887ff589f4331467c9b26d5d32c2c5a86a646ea7d1ecc29f5
|
3 |
+
size 3417037
|
checkpoint-1000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88bbb03df9c765dea59edb7dc0de32f5ad50d321a283b56457d442883544d86b
|
3 |
+
size 14727
|
checkpoint-1000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68cff80b680ddf6e7abbef98b5f336b97f9b5963e2209307f639383870e8cc71
|
3 |
+
size 557
|
checkpoint-1000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b0e7c0031b016b4014530d122ec43cabd4876abf9f6428b84177110087b7869
|
3 |
+
size 563
|
checkpoint-2000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d36137d5d9a916cb370dbb616d06df44f801788ec2722b9f7a53834e8c52bbc
|
3 |
+
size 6853829
|
checkpoint-2000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23bc1dbd3c661fec783c79e04da623e9ea77696a7e66a1c6cce373a57f1f80fb
|
3 |
+
size 3417037
|
checkpoint-2000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f417e4f8fc9a21d5e47bf5fbc1eef0e85ca83979af3678f19b953fb496e1defd
|
3 |
+
size 14727
|
checkpoint-2000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd2de9749828adacdf103bf6e9592702bb7067a2c1df27dd62ab38c1eb8c070f
|
3 |
+
size 557
|
checkpoint-2000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99d048c90a677fd083f3b58a8f8a6bbbeda629e54c112c7166f31c819dd83f52
|
3 |
+
size 563
|
checkpoint-3000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9504cc2e74407057d13ac083fc8dccbf303c38af2a4b9fdf3669e154a7bfb8d2
|
3 |
+
size 6853829
|
checkpoint-3000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8790c19d2382b60a4e16b5ac16ae01ead61ec670a44fde4bbf00d9d89e0fd7a9
|
3 |
+
size 3417037
|
checkpoint-3000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2b33c617770813552b8f90879bc545eb6053f8f34c0ad4eeb5a9327a6094016
|
3 |
+
size 14727
|
checkpoint-3000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b63965244fa6de213b909c7f4ac6e07c292527156a0fb4f6e47061ea56e23acc
|
3 |
+
size 557
|
checkpoint-3000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ed22528225f676498e413e6018072eb211384e8dda35affcda826642659765a
|
3 |
+
size 563
|
image_0.png
ADDED
image_1.png
ADDED
image_2.png
ADDED
image_3.png
ADDED
logs/text2image-fine-tune/1691043322.8519316/events.out.tfevents.1691043322.7686de4f6696.203.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:612cfaba32e0926dcf7a91c10c5163b9d9f25a4f12d672cdbbf0c3fb7b17c4a0
|
3 |
+
size 2600
|
logs/text2image-fine-tune/1691043322.8548627/hparams.yml
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: false
|
9 |
+
checkpointing_steps: 1000
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 2
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: bharadwajkg/planogram-sd-original-data6
|
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: 5000
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 556
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: finetune-sd2-1-planogram-lora-data6
|
33 |
+
prediction_type: null
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
|
35 |
+
push_to_hub: true
|
36 |
+
random_flip: false
|
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: An image of a shelf in retail store with 5 racks. First rack on
|
50 |
+
top contains 3 yellow cornflakes boxes and 2 brown chocos boxes. Second rack contains
|
51 |
+
3 brown chocos boxes and 2 yellow cornflakes boxes. Third rack contains 5 red oats
|
52 |
+
packets. Fourth rack contains 4 blue oats packets. Fifth rack contains 4 brown chocolate
|
53 |
+
jars and 3 red ketchup bottles.
|
logs/text2image-fine-tune/1691137183.464093/events.out.tfevents.1691137183.5d562fc64c89.222.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:beacde330b89127acd8d0216b4608867aee8624faa4706935efabd575144a98f
|
3 |
+
size 2726
|
logs/text2image-fine-tune/1691137183.4675448/hparams.yml
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: false
|
9 |
+
checkpointing_steps: 1000
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 2
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: bharadwajkg/planogram-sd-original-data6
|
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: 3000
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 334
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: finetune-sd2-1-planogram-lora-data6
|
33 |
+
prediction_type: null
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
|
35 |
+
push_to_hub: true
|
36 |
+
random_flip: false
|
37 |
+
rank: 4
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 512
|
40 |
+
resume_from_checkpoint: /kaggle/working/finetune-sd2-1-planogram-lora-data6/checkpoint-2000/
|
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: An image of a shelf in retail store with 5 racks. First rack on
|
50 |
+
top contains 3 yellow cornflakes boxes and 2 brown chocos boxes. Second rack contains
|
51 |
+
3 brown chocos boxes and 2 yellow cornflakes boxes. Third rack contains 5 red oats
|
52 |
+
packets. Fourth rack contains 4 blue oats packets. Fifth rack contains 4 brown chocolate
|
53 |
+
jars and 3 red ketchup bottles.
|
logs/text2image-fine-tune/1691137273.0572374/events.out.tfevents.1691137273.5d562fc64c89.252.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26b8fbb2d0e3ff75f511f5bfced33a97da024bfd7c592907825d43cd8492ba9a
|
3 |
+
size 2664
|
logs/text2image-fine-tune/1691137273.0598068/hparams.yml
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: false
|
9 |
+
checkpointing_steps: 1000
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 2
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: bharadwajkg/planogram-sd-original-data6
|
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: 3000
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 334
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: finetune-sd2-1-planogram-lora-data6
|
33 |
+
prediction_type: null
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
|
35 |
+
push_to_hub: true
|
36 |
+
random_flip: false
|
37 |
+
rank: 4
|
38 |
+
report_to: tensorboard
|
39 |
+
resolution: 512
|
40 |
+
resume_from_checkpoint: latest
|
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: An image of a shelf in retail store with 5 racks. First rack on
|
50 |
+
top contains 3 yellow cornflakes boxes and 2 brown chocos boxes. Second rack contains
|
51 |
+
3 brown chocos boxes and 2 yellow cornflakes boxes. Third rack contains 5 red oats
|
52 |
+
packets. Fourth rack contains 4 blue oats packets. Fifth rack contains 4 brown chocolate
|
53 |
+
jars and 3 red ketchup bottles.
|
logs/text2image-fine-tune/events.out.tfevents.1691043322.7686de4f6696.203.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05488e69dd72f89d86bd0dd57791f140dcea501c6d29cb2c557cd2079b12f35c
|
3 |
+
size 1037699567
|
logs/text2image-fine-tune/events.out.tfevents.1691137183.5d562fc64c89.222.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4eb16ef02b14623ccd9cdd5904c74c88ea4ba286f2c36284685f54a414f1951
|
3 |
+
size 88
|
logs/text2image-fine-tune/events.out.tfevents.1691137273.5d562fc64c89.252.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87cf99603728533ac68ebd372ad1433f28921a9e7888167fbea802ceeb18d760
|
3 |
+
size 373355876
|
pytorch_lora_weights.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b712be60e895cdd92da787ae17aab69db5af3f81c5d9bff162f8d4fdb3165f56
|
3 |
+
size 3418843
|