End of training
Browse files- README.md +45 -0
- config.json +56 -0
- diffusion_pytorch_model.safetensors +3 -0
- image_control.png +0 -0
- images_0.png +0 -0
- images_1.png +0 -0
- logs/controlnet/1713953565.2126503/events.out.tfevents.1713953565.ip-10-192-12-106.93171.1 +3 -0
- logs/controlnet/1713953565.2142987/hparams.yml +50 -0
- logs/controlnet/1713958121.0405383/events.out.tfevents.1713958121.ip-10-192-12-106.259641.1 +3 -0
- logs/controlnet/1713958121.0423748/hparams.yml +50 -0
- logs/controlnet/events.out.tfevents.1713953565.ip-10-192-12-106.93171.0 +3 -0
- logs/controlnet/events.out.tfevents.1713958121.ip-10-192-12-106.259641.0 +3 -0
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- controlnet
|
10 |
+
- diffusers-training
|
11 |
+
base_model: stabilityai/stable-diffusion-2-1-base
|
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 |
+
# controlnet-Wouter01/diffusion_model_out
|
20 |
+
|
21 |
+
These are controlnet weights trained on stabilityai/stable-diffusion-2-1-base with new type of conditioning.
|
22 |
+
You can find some example images below.
|
23 |
+
|
24 |
+
prompt: The same image but fixing small physical and illumination inconsistencies
|
25 |
+
![images_0)](./images_0.png)
|
26 |
+
prompt: The same image but fixing small physical and illumination inconsistencies
|
27 |
+
![images_1)](./images_1.png)
|
28 |
+
|
29 |
+
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
#### How to use
|
34 |
+
|
35 |
+
```python
|
36 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
37 |
+
```
|
38 |
+
|
39 |
+
#### Limitations and bias
|
40 |
+
|
41 |
+
[TODO: provide examples of latent issues and potential remediations]
|
42 |
+
|
43 |
+
## Training details
|
44 |
+
|
45 |
+
[TODO: describe the data used to train the model]
|
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_embed_type": null,
|
6 |
+
"addition_embed_type_num_heads": 64,
|
7 |
+
"addition_time_embed_dim": null,
|
8 |
+
"attention_head_dim": [
|
9 |
+
5,
|
10 |
+
10,
|
11 |
+
20,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"class_embed_type": null,
|
21 |
+
"conditioning_channels": 3,
|
22 |
+
"conditioning_embedding_out_channels": [
|
23 |
+
16,
|
24 |
+
32,
|
25 |
+
96,
|
26 |
+
256
|
27 |
+
],
|
28 |
+
"controlnet_conditioning_channel_order": "rgb",
|
29 |
+
"cross_attention_dim": 1024,
|
30 |
+
"down_block_types": [
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"CrossAttnDownBlock2D",
|
34 |
+
"DownBlock2D"
|
35 |
+
],
|
36 |
+
"downsample_padding": 1,
|
37 |
+
"encoder_hid_dim": null,
|
38 |
+
"encoder_hid_dim_type": null,
|
39 |
+
"flip_sin_to_cos": true,
|
40 |
+
"freq_shift": 0,
|
41 |
+
"global_pool_conditions": false,
|
42 |
+
"in_channels": 4,
|
43 |
+
"layers_per_block": 2,
|
44 |
+
"mid_block_scale_factor": 1,
|
45 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
46 |
+
"norm_eps": 1e-05,
|
47 |
+
"norm_num_groups": 32,
|
48 |
+
"num_attention_heads": null,
|
49 |
+
"num_class_embeds": null,
|
50 |
+
"only_cross_attention": false,
|
51 |
+
"projection_class_embeddings_input_dim": null,
|
52 |
+
"resnet_time_scale_shift": "default",
|
53 |
+
"transformer_layers_per_block": 1,
|
54 |
+
"upcast_attention": false,
|
55 |
+
"use_linear_projection": true
|
56 |
+
}
|
diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8ceac44167a93906173e9ac4430c45cb73b37fc5c81781480371296f88c01ef
|
3 |
+
size 1456953560
|
image_control.png
ADDED
![]() |
images_0.png
ADDED
![]() |
images_1.png
ADDED
![]() |
logs/controlnet/1713953565.2126503/events.out.tfevents.1713953565.ip-10-192-12-106.93171.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb751f240285d7c1b1ac4c6be0124fcd0630da8988200cd8d533f32434d1949a
|
3 |
+
size 2308
|
logs/controlnet/1713953565.2142987/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: prompt
|
8 |
+
checkpointing_steps: 5000
|
9 |
+
checkpoints_total_limit: null
|
10 |
+
conditioning_image_column: conditioning_image
|
11 |
+
controlnet_model_name_or_path: null
|
12 |
+
dataloader_num_workers: 0
|
13 |
+
dataset_config_name: null
|
14 |
+
dataset_name: Wouter01/re10ksmalltest
|
15 |
+
enable_xformers_memory_efficient_attention: true
|
16 |
+
gradient_accumulation_steps: 1
|
17 |
+
gradient_checkpointing: false
|
18 |
+
hub_model_id: null
|
19 |
+
hub_token: null
|
20 |
+
image_column: ground_truth_image
|
21 |
+
learning_rate: 1.0e-05
|
22 |
+
logging_dir: logs
|
23 |
+
lr_num_cycles: 1
|
24 |
+
lr_power: 1.0
|
25 |
+
lr_scheduler: constant
|
26 |
+
lr_warmup_steps: 500
|
27 |
+
max_grad_norm: 1.0
|
28 |
+
max_train_samples: null
|
29 |
+
max_train_steps: 2127
|
30 |
+
mixed_precision: null
|
31 |
+
num_train_epochs: 3
|
32 |
+
num_validation_images: 4
|
33 |
+
output_dir: diffusion_model_out
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1-base
|
35 |
+
proportion_empty_prompts: 0
|
36 |
+
push_to_hub: true
|
37 |
+
report_to: tensorboard
|
38 |
+
resolution: 256
|
39 |
+
resume_from_checkpoint: null
|
40 |
+
revision: null
|
41 |
+
scale_lr: false
|
42 |
+
seed: null
|
43 |
+
set_grads_to_none: false
|
44 |
+
tokenizer_name: null
|
45 |
+
tracker_project_name: controlnet
|
46 |
+
train_batch_size: 4
|
47 |
+
train_data_dir: null
|
48 |
+
use_8bit_adam: false
|
49 |
+
validation_steps: 5000
|
50 |
+
variant: null
|
logs/controlnet/1713958121.0405383/events.out.tfevents.1713958121.ip-10-192-12-106.259641.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:835006e59fb858639857b879a4964e210b8efa280d0ee52694211080be4755fe
|
3 |
+
size 2308
|
logs/controlnet/1713958121.0423748/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: prompt
|
8 |
+
checkpointing_steps: 5000
|
9 |
+
checkpoints_total_limit: null
|
10 |
+
conditioning_image_column: conditioning_image
|
11 |
+
controlnet_model_name_or_path: null
|
12 |
+
dataloader_num_workers: 0
|
13 |
+
dataset_config_name: null
|
14 |
+
dataset_name: Wouter01/re10ksmalltest
|
15 |
+
enable_xformers_memory_efficient_attention: true
|
16 |
+
gradient_accumulation_steps: 1
|
17 |
+
gradient_checkpointing: false
|
18 |
+
hub_model_id: null
|
19 |
+
hub_token: null
|
20 |
+
image_column: ground_truth_image
|
21 |
+
learning_rate: 1.0e-05
|
22 |
+
logging_dir: logs
|
23 |
+
lr_num_cycles: 1
|
24 |
+
lr_power: 1.0
|
25 |
+
lr_scheduler: constant
|
26 |
+
lr_warmup_steps: 500
|
27 |
+
max_grad_norm: 1.0
|
28 |
+
max_train_samples: null
|
29 |
+
max_train_steps: 2127
|
30 |
+
mixed_precision: null
|
31 |
+
num_train_epochs: 3
|
32 |
+
num_validation_images: 4
|
33 |
+
output_dir: diffusion_model_out
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1-base
|
35 |
+
proportion_empty_prompts: 0
|
36 |
+
push_to_hub: true
|
37 |
+
report_to: tensorboard
|
38 |
+
resolution: 256
|
39 |
+
resume_from_checkpoint: null
|
40 |
+
revision: null
|
41 |
+
scale_lr: false
|
42 |
+
seed: null
|
43 |
+
set_grads_to_none: false
|
44 |
+
tokenizer_name: null
|
45 |
+
tracker_project_name: controlnet
|
46 |
+
train_batch_size: 4
|
47 |
+
train_data_dir: null
|
48 |
+
use_8bit_adam: false
|
49 |
+
validation_steps: 5000
|
50 |
+
variant: null
|
logs/controlnet/events.out.tfevents.1713953565.ip-10-192-12-106.93171.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e28ef2ecfb2bc8291770d93678956c4a6e13144984e69f28aaba2364255ad90a
|
3 |
+
size 178502
|
logs/controlnet/events.out.tfevents.1713958121.ip-10-192-12-106.259641.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcf9ef4703ae19bc548de68d1e25bc213f4e0e8d1ad640a5eadc1c3ff95eb4c0
|
3 |
+
size 1073580
|