End of training
Browse files- README.md +24 -0
- config.json +57 -0
- diffusion_pytorch_model.safetensors +3 -0
- image_control.png +0 -0
- images_0.png +0 -0
- images_1.png +0 -0
- images_2.png +0 -0
- logs/sd_xl_train_controlnet/1706622252.076567/events.out.tfevents.1706622252.deeplearning03.tecgraf.puc-rio.br.376108.1 +3 -0
- logs/sd_xl_train_controlnet/1706622252.0778227/hparams.yml +53 -0
- logs/sd_xl_train_controlnet/1706622325.5507345/events.out.tfevents.1706622325.deeplearning03.tecgraf.puc-rio.br.376597.1 +3 -0
- logs/sd_xl_train_controlnet/1706622325.5521212/hparams.yml +53 -0
- logs/sd_xl_train_controlnet/1706622417.360171/events.out.tfevents.1706622417.deeplearning03.tecgraf.puc-rio.br.377308.1 +3 -0
- logs/sd_xl_train_controlnet/1706622417.361561/hparams.yml +53 -0
- logs/sd_xl_train_controlnet/events.out.tfevents.1706622252.deeplearning03.tecgraf.puc-rio.br.376108.0 +3 -0
- logs/sd_xl_train_controlnet/events.out.tfevents.1706622325.deeplearning03.tecgraf.puc-rio.br.376597.0 +3 -0
- logs/sd_xl_train_controlnet/events.out.tfevents.1706622417.deeplearning03.tecgraf.puc-rio.br.377308.0 +3 -0
README.md
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: openrail++
|
4 |
+
base_model: stabilityai/stable-diffusion-xl-base-1.0
|
5 |
+
tags:
|
6 |
+
- stable-diffusion-xl
|
7 |
+
- stable-diffusion-xl-diffusers
|
8 |
+
- text-to-image
|
9 |
+
- diffusers
|
10 |
+
- controlnet
|
11 |
+
inference: true
|
12 |
+
---
|
13 |
+
|
14 |
+
# controlnet-mdesousa/output_dir
|
15 |
+
|
16 |
+
These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with new type of conditioning.
|
17 |
+
You can find some example images below.
|
18 |
+
prompt: small rocks, medium rocks, big rocks, acoustic data, deep sea, ocean
|
19 |
+
![images_0)](./images_0.png)
|
20 |
+
prompt: small rocks, medium rocks, big rocks, acoustic data, deep sea, ocean
|
21 |
+
![images_1)](./images_1.png)
|
22 |
+
prompt: small rocks, medium rocks, big rocks, acoustic data, deep sea, ocean
|
23 |
+
![images_2)](./images_2.png)
|
24 |
+
|
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.26.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": "text_time",
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"addition_time_embed_dim": 256,
|
8 |
+
"attention_head_dim": [
|
9 |
+
5,
|
10 |
+
10,
|
11 |
+
20
|
12 |
+
],
|
13 |
+
"block_out_channels": [
|
14 |
+
320,
|
15 |
+
640,
|
16 |
+
1280
|
17 |
+
],
|
18 |
+
"class_embed_type": null,
|
19 |
+
"conditioning_channels": 3,
|
20 |
+
"conditioning_embedding_out_channels": [
|
21 |
+
16,
|
22 |
+
32,
|
23 |
+
96,
|
24 |
+
256
|
25 |
+
],
|
26 |
+
"controlnet_conditioning_channel_order": "rgb",
|
27 |
+
"cross_attention_dim": 2048,
|
28 |
+
"down_block_types": [
|
29 |
+
"DownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D"
|
32 |
+
],
|
33 |
+
"downsample_padding": 1,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"global_pool_conditions": false,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_scale_factor": 1,
|
42 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
43 |
+
"norm_eps": 1e-05,
|
44 |
+
"norm_num_groups": 32,
|
45 |
+
"num_attention_heads": null,
|
46 |
+
"num_class_embeds": null,
|
47 |
+
"only_cross_attention": false,
|
48 |
+
"projection_class_embeddings_input_dim": 2816,
|
49 |
+
"resnet_time_scale_shift": "default",
|
50 |
+
"transformer_layers_per_block": [
|
51 |
+
1,
|
52 |
+
2,
|
53 |
+
10
|
54 |
+
],
|
55 |
+
"upcast_attention": null,
|
56 |
+
"use_linear_projection": true
|
57 |
+
}
|
diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:332f63bc7e64e44757352bd39411a27d1428bbc4c4897d8ecb07a5c9b19fbe3e
|
3 |
+
size 5004167864
|
image_control.png
ADDED
images_0.png
ADDED
images_1.png
ADDED
images_2.png
ADDED
logs/sd_xl_train_controlnet/1706622252.076567/events.out.tfevents.1706622252.deeplearning03.tecgraf.puc-rio.br.376108.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64204b0f0ea86d91f6290e79076ed03d08f007a106c59f6ade05d3a3c76d8c81
|
3 |
+
size 2571
|
logs/sd_xl_train_controlnet/1706622252.0778227/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 |
+
checkpointing_steps: 500
|
9 |
+
checkpoints_total_limit: null
|
10 |
+
conditioning_image_column: conditioning_image
|
11 |
+
controlnet_model_name_or_path: null
|
12 |
+
crops_coords_top_left_h: 0
|
13 |
+
crops_coords_top_left_w: 0
|
14 |
+
dataloader_num_workers: 0
|
15 |
+
dataset_config_name: null
|
16 |
+
dataset_name: null
|
17 |
+
enable_xformers_memory_efficient_attention: false
|
18 |
+
gradient_accumulation_steps: 4
|
19 |
+
gradient_checkpointing: false
|
20 |
+
hub_model_id: null
|
21 |
+
hub_token: null
|
22 |
+
image_column: image
|
23 |
+
learning_rate: 1.0e-05
|
24 |
+
logging_dir: logs
|
25 |
+
lr_num_cycles: 1
|
26 |
+
lr_power: 1.0
|
27 |
+
lr_scheduler: constant
|
28 |
+
lr_warmup_steps: 500
|
29 |
+
max_grad_norm: 1.0
|
30 |
+
max_train_samples: null
|
31 |
+
max_train_steps: 100
|
32 |
+
mixed_precision: fp16
|
33 |
+
num_train_epochs: 5
|
34 |
+
num_validation_images: 4
|
35 |
+
output_dir: /local/diffusers/examples/controlnet/output_dir
|
36 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
37 |
+
pretrained_vae_model_name_or_path: null
|
38 |
+
proportion_empty_prompts: 0
|
39 |
+
push_to_hub: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 1024
|
42 |
+
resume_from_checkpoint: null
|
43 |
+
revision: null
|
44 |
+
scale_lr: false
|
45 |
+
seed: 42
|
46 |
+
set_grads_to_none: false
|
47 |
+
tokenizer_name: null
|
48 |
+
tracker_project_name: sd_xl_train_controlnet
|
49 |
+
train_batch_size: 4
|
50 |
+
train_data_dir: /local/diffusers/examples/controlnet/train/
|
51 |
+
use_8bit_adam: false
|
52 |
+
validation_steps: 100
|
53 |
+
variant: null
|
logs/sd_xl_train_controlnet/1706622325.5507345/events.out.tfevents.1706622325.deeplearning03.tecgraf.puc-rio.br.376597.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45ae3267f3a418b43b13c1b33d7fd05ceff982d774c64d3971080a608d1aef37
|
3 |
+
size 2571
|
logs/sd_xl_train_controlnet/1706622325.5521212/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 |
+
checkpointing_steps: 500
|
9 |
+
checkpoints_total_limit: null
|
10 |
+
conditioning_image_column: conditioning_image
|
11 |
+
controlnet_model_name_or_path: null
|
12 |
+
crops_coords_top_left_h: 0
|
13 |
+
crops_coords_top_left_w: 0
|
14 |
+
dataloader_num_workers: 0
|
15 |
+
dataset_config_name: null
|
16 |
+
dataset_name: null
|
17 |
+
enable_xformers_memory_efficient_attention: false
|
18 |
+
gradient_accumulation_steps: 4
|
19 |
+
gradient_checkpointing: false
|
20 |
+
hub_model_id: null
|
21 |
+
hub_token: null
|
22 |
+
image_column: image
|
23 |
+
learning_rate: 1.0e-05
|
24 |
+
logging_dir: logs
|
25 |
+
lr_num_cycles: 1
|
26 |
+
lr_power: 1.0
|
27 |
+
lr_scheduler: constant
|
28 |
+
lr_warmup_steps: 500
|
29 |
+
max_grad_norm: 1.0
|
30 |
+
max_train_samples: null
|
31 |
+
max_train_steps: 100
|
32 |
+
mixed_precision: fp16
|
33 |
+
num_train_epochs: 3
|
34 |
+
num_validation_images: 4
|
35 |
+
output_dir: /local/diffusers/examples/controlnet/output_dir
|
36 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
37 |
+
pretrained_vae_model_name_or_path: null
|
38 |
+
proportion_empty_prompts: 0
|
39 |
+
push_to_hub: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 1024
|
42 |
+
resume_from_checkpoint: null
|
43 |
+
revision: null
|
44 |
+
scale_lr: false
|
45 |
+
seed: 42
|
46 |
+
set_grads_to_none: false
|
47 |
+
tokenizer_name: null
|
48 |
+
tracker_project_name: sd_xl_train_controlnet
|
49 |
+
train_batch_size: 2
|
50 |
+
train_data_dir: /local/diffusers/examples/controlnet/train/
|
51 |
+
use_8bit_adam: false
|
52 |
+
validation_steps: 100
|
53 |
+
variant: null
|
logs/sd_xl_train_controlnet/1706622417.360171/events.out.tfevents.1706622417.deeplearning03.tecgraf.puc-rio.br.377308.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daaee3ceb0bfb809c79c30e0d1db30dffb329279fa89d4ea81df8538add67de4
|
3 |
+
size 2571
|
logs/sd_xl_train_controlnet/1706622417.361561/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 |
+
checkpointing_steps: 500
|
9 |
+
checkpoints_total_limit: null
|
10 |
+
conditioning_image_column: conditioning_image
|
11 |
+
controlnet_model_name_or_path: null
|
12 |
+
crops_coords_top_left_h: 0
|
13 |
+
crops_coords_top_left_w: 0
|
14 |
+
dataloader_num_workers: 0
|
15 |
+
dataset_config_name: null
|
16 |
+
dataset_name: null
|
17 |
+
enable_xformers_memory_efficient_attention: false
|
18 |
+
gradient_accumulation_steps: 4
|
19 |
+
gradient_checkpointing: false
|
20 |
+
hub_model_id: null
|
21 |
+
hub_token: null
|
22 |
+
image_column: image
|
23 |
+
learning_rate: 1.0e-05
|
24 |
+
logging_dir: logs
|
25 |
+
lr_num_cycles: 1
|
26 |
+
lr_power: 1.0
|
27 |
+
lr_scheduler: constant
|
28 |
+
lr_warmup_steps: 500
|
29 |
+
max_grad_norm: 1.0
|
30 |
+
max_train_samples: null
|
31 |
+
max_train_steps: 100
|
32 |
+
mixed_precision: fp16
|
33 |
+
num_train_epochs: 2
|
34 |
+
num_validation_images: 4
|
35 |
+
output_dir: /local/diffusers/examples/controlnet/output_dir
|
36 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
37 |
+
pretrained_vae_model_name_or_path: null
|
38 |
+
proportion_empty_prompts: 0
|
39 |
+
push_to_hub: true
|
40 |
+
report_to: tensorboard
|
41 |
+
resolution: 1024
|
42 |
+
resume_from_checkpoint: null
|
43 |
+
revision: null
|
44 |
+
scale_lr: false
|
45 |
+
seed: 42
|
46 |
+
set_grads_to_none: false
|
47 |
+
tokenizer_name: null
|
48 |
+
tracker_project_name: sd_xl_train_controlnet
|
49 |
+
train_batch_size: 1
|
50 |
+
train_data_dir: /local/diffusers/examples/controlnet/train/
|
51 |
+
use_8bit_adam: false
|
52 |
+
validation_steps: 100
|
53 |
+
variant: null
|
logs/sd_xl_train_controlnet/events.out.tfevents.1706622252.deeplearning03.tecgraf.puc-rio.br.376108.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87820c871c3588e8834e3e3c4789768179ac74bc740c85d9b75e935e9dd882de
|
3 |
+
size 88
|
logs/sd_xl_train_controlnet/events.out.tfevents.1706622325.deeplearning03.tecgraf.puc-rio.br.376597.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e1f54294fc16812e32a06b4a39e204fd5157da752af9beb96ff2b29cbea4ec6
|
3 |
+
size 166
|
logs/sd_xl_train_controlnet/events.out.tfevents.1706622417.deeplearning03.tecgraf.puc-rio.br.377308.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d18451a11d8ca03ab86423434db01329825ef16bd266bd715e5e37a6ba3608f
|
3 |
+
size 280590
|