End of training
Browse files- README.md +45 -0
- checkpoint-14000/controlnet/config.json +56 -0
- checkpoint-14000/controlnet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-14000/optimizer.bin +3 -0
- checkpoint-14000/random_states_0.pkl +3 -0
- checkpoint-14000/scheduler.bin +3 -0
- checkpoint-16000/controlnet/config.json +56 -0
- checkpoint-16000/controlnet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-16000/optimizer.bin +3 -0
- checkpoint-16000/random_states_0.pkl +3 -0
- checkpoint-16000/scheduler.bin +3 -0
- checkpoint-18000/controlnet/config.json +56 -0
- checkpoint-18000/controlnet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-18000/optimizer.bin +3 -0
- checkpoint-18000/random_states_0.pkl +3 -0
- checkpoint-18000/scheduler.bin +3 -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
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_re10k_hard
|
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:
|
25 |
+
![images_0)](./images_0.png)
|
26 |
+
prompt:
|
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]
|
checkpoint-14000/controlnet/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 |
+
}
|
checkpoint-14000/controlnet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07d54a0cf4bc7d98cf6f4fd135b021b950e818969db8b099f7a9be5637eef57f
|
3 |
+
size 1456953560
|
checkpoint-14000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3365440f426508dbf95fd065f12ccf4584662d91e9ef8c4ede27af84fa374db5
|
3 |
+
size 2914111182
|
checkpoint-14000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d7d63fddce4b13a429215d9a76e8cdcb54eda0980830807bfb820e622fbd4f9
|
3 |
+
size 14408
|
checkpoint-14000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa4a0f1fa06292b5a9a54766daad921823eef17727d6cfa4c287c5f219e32a09
|
3 |
+
size 1000
|
checkpoint-16000/controlnet/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 |
+
}
|
checkpoint-16000/controlnet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dd5a0ee5644670437cb0ec474ffaab6afefcd123787ea8c3114eaf4001a7660
|
3 |
+
size 1456953560
|
checkpoint-16000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24cfe2fc17cd5bdfbeb2cd2fba59981eb35297695ba2f6f95d540cddeb93f4da
|
3 |
+
size 2914111182
|
checkpoint-16000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00133f09143cd649b51d3632a33a3b7507757889f405d8c32ad49280b107ae2a
|
3 |
+
size 14408
|
checkpoint-16000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e0406192bb92774ca7be2870d7ac8a8c8a2b174d7913a1181cf529a1bb97ddd
|
3 |
+
size 1000
|
checkpoint-18000/controlnet/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 |
+
}
|
checkpoint-18000/controlnet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fa9dcdbe764d3333383a58f04573774f03d14cd3d557abfd7a364df5167bd32
|
3 |
+
size 1456953560
|
checkpoint-18000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d455dc47ede9bab08abba567dbde1350beebd86d7cb2137e3ad0054f700675da
|
3 |
+
size 2914111182
|
checkpoint-18000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8e98cac843bba32353c52e4bb96946979b5c28ca7fb44a99739fb125e05bc70
|
3 |
+
size 14408
|
checkpoint-18000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fe725b604972c0e9d60b03e205bae01f58e846e975aab7973ca09cc3caf8446
|
3 |
+
size 1000
|
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
4 |
+
"_name_or_path": "diffusion_re10k_hard/checkpoint-18000",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": null,
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": null,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20,
|
13 |
+
20
|
14 |
+
],
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280,
|
19 |
+
1280
|
20 |
+
],
|
21 |
+
"class_embed_type": null,
|
22 |
+
"conditioning_channels": 3,
|
23 |
+
"conditioning_embedding_out_channels": [
|
24 |
+
16,
|
25 |
+
32,
|
26 |
+
96,
|
27 |
+
256
|
28 |
+
],
|
29 |
+
"controlnet_conditioning_channel_order": "rgb",
|
30 |
+
"cross_attention_dim": 1024,
|
31 |
+
"down_block_types": [
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"CrossAttnDownBlock2D",
|
34 |
+
"CrossAttnDownBlock2D",
|
35 |
+
"DownBlock2D"
|
36 |
+
],
|
37 |
+
"downsample_padding": 1,
|
38 |
+
"encoder_hid_dim": null,
|
39 |
+
"encoder_hid_dim_type": null,
|
40 |
+
"flip_sin_to_cos": true,
|
41 |
+
"freq_shift": 0,
|
42 |
+
"global_pool_conditions": false,
|
43 |
+
"in_channels": 4,
|
44 |
+
"layers_per_block": 2,
|
45 |
+
"mid_block_scale_factor": 1,
|
46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_attention_heads": null,
|
50 |
+
"num_class_embeds": null,
|
51 |
+
"only_cross_attention": false,
|
52 |
+
"projection_class_embeddings_input_dim": null,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"transformer_layers_per_block": 1,
|
55 |
+
"upcast_attention": false,
|
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 sha256:3fa9dcdbe764d3333383a58f04573774f03d14cd3d557abfd7a364df5167bd32
|
3 |
+
size 1456953560
|
image_control.png
ADDED
![]() |
images_0.png
ADDED
![]() |
images_1.png
ADDED
![]() |