End of training
Browse files- README.md +61 -0
- logs/dreambooth-lora-sd-xl/1709082916.2947295/events.out.tfevents.1709082916.f2d6fa700f9e.9485.1 +3 -0
- logs/dreambooth-lora-sd-xl/1709082916.2967541/hparams.yml +67 -0
- logs/dreambooth-lora-sd-xl/events.out.tfevents.1709082916.f2d6fa700f9e.9485.0 +3 -0
- pytorch_lora_weights.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: openrail++
|
3 |
+
library_name: diffusers
|
4 |
+
tags:
|
5 |
+
- text-to-image
|
6 |
+
- stable-diffusion-xl
|
7 |
+
- stable-diffusion-xl-diffusers
|
8 |
+
- text-to-image
|
9 |
+
- diffusers
|
10 |
+
- lora
|
11 |
+
- template:sd-lora
|
12 |
+
base_model: stabilityai/stable-diffusion-xl-base-1.0
|
13 |
+
instance_prompt: a photo of TOK dress
|
14 |
+
widget: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
|
21 |
+
# SDXL LoRA DreamBooth - juliaturc/aritzia-dress-dreambooth
|
22 |
+
|
23 |
+
<Gallery />
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
These are juliaturc/aritzia-dress-dreambooth LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
|
28 |
+
|
29 |
+
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
|
30 |
+
|
31 |
+
LoRA for the text encoder was enabled: False.
|
32 |
+
|
33 |
+
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
|
34 |
+
|
35 |
+
## Trigger words
|
36 |
+
|
37 |
+
You should use a photo of TOK dress to trigger the image generation.
|
38 |
+
|
39 |
+
## Download model
|
40 |
+
|
41 |
+
Weights for this model are available in Safetensors format.
|
42 |
+
|
43 |
+
[Download](juliaturc/aritzia-dress-dreambooth/tree/main) them in the Files & versions tab.
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
## Intended uses & limitations
|
48 |
+
|
49 |
+
#### How to use
|
50 |
+
|
51 |
+
```python
|
52 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
53 |
+
```
|
54 |
+
|
55 |
+
#### Limitations and bias
|
56 |
+
|
57 |
+
[TODO: provide examples of latent issues and potential remediations]
|
58 |
+
|
59 |
+
## Training details
|
60 |
+
|
61 |
+
[TODO: describe the data used to train the model]
|
logs/dreambooth-lora-sd-xl/1709082916.2947295/events.out.tfevents.1709082916.f2d6fa700f9e.9485.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb6efc07b054c4e7c00637051fb0b76fb92dbf43c984c8200d9e494ec39bfa91
|
3 |
+
size 3156
|
logs/dreambooth-lora-sd-xl/1709082916.2967541/hparams.yml
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
adam_beta1: 0.9
|
2 |
+
adam_beta2: 0.999
|
3 |
+
adam_epsilon: 1.0e-08
|
4 |
+
adam_weight_decay: 0.0001
|
5 |
+
adam_weight_decay_text_encoder: 0.001
|
6 |
+
allow_tf32: false
|
7 |
+
cache_dir: null
|
8 |
+
caption_column: prompt
|
9 |
+
center_crop: false
|
10 |
+
checkpointing_steps: 717
|
11 |
+
checkpoints_total_limit: null
|
12 |
+
class_data_dir: null
|
13 |
+
class_prompt: null
|
14 |
+
dataloader_num_workers: 0
|
15 |
+
dataset_config_name: null
|
16 |
+
dataset_name: juliaturc/aritzia-dress
|
17 |
+
enable_xformers_memory_efficient_attention: false
|
18 |
+
gradient_accumulation_steps: 3
|
19 |
+
gradient_checkpointing: true
|
20 |
+
hub_model_id: null
|
21 |
+
hub_token: null
|
22 |
+
image_column: image
|
23 |
+
instance_data_dir: null
|
24 |
+
instance_prompt: caption_prefix
|
25 |
+
learning_rate: 0.0001
|
26 |
+
local_rank: -1
|
27 |
+
logging_dir: logs
|
28 |
+
lr_num_cycles: 1
|
29 |
+
lr_power: 1.0
|
30 |
+
lr_scheduler: constant
|
31 |
+
lr_warmup_steps: 0
|
32 |
+
max_grad_norm: 1.0
|
33 |
+
max_train_steps: 500
|
34 |
+
mixed_precision: fp16
|
35 |
+
num_class_images: 100
|
36 |
+
num_train_epochs: 50
|
37 |
+
num_validation_images: 4
|
38 |
+
optimizer: AdamW
|
39 |
+
output_dir: aritzia_dress_LoRA
|
40 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
41 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
42 |
+
prior_generation_precision: null
|
43 |
+
prior_loss_weight: 1.0
|
44 |
+
prodigy_beta3: null
|
45 |
+
prodigy_decouple: true
|
46 |
+
prodigy_safeguard_warmup: true
|
47 |
+
prodigy_use_bias_correction: true
|
48 |
+
push_to_hub: false
|
49 |
+
random_flip: false
|
50 |
+
rank: 4
|
51 |
+
repeats: 1
|
52 |
+
report_to: tensorboard
|
53 |
+
resolution: 1024
|
54 |
+
resume_from_checkpoint: null
|
55 |
+
revision: null
|
56 |
+
sample_batch_size: 4
|
57 |
+
scale_lr: false
|
58 |
+
seed: 0
|
59 |
+
snr_gamma: 5.0
|
60 |
+
text_encoder_lr: 5.0e-06
|
61 |
+
train_batch_size: 1
|
62 |
+
train_text_encoder: false
|
63 |
+
use_8bit_adam: true
|
64 |
+
validation_epochs: 50
|
65 |
+
validation_prompt: null
|
66 |
+
variant: null
|
67 |
+
with_prior_preservation: false
|
logs/dreambooth-lora-sd-xl/events.out.tfevents.1709082916.f2d6fa700f9e.9485.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:649af4878ca39e191a82e9b509488cbcc62b3ef902c12a7624cd98b028277257
|
3 |
+
size 125314
|
pytorch_lora_weights.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e07d446ecb9decff406bd4d752c4cb2b9e94353f06c8cef92b692fab972e272c
|
3 |
+
size 23390424
|