End of training
Browse files- README.md +39 -0
- checkpoint-100/controlnet/config.json +57 -0
- checkpoint-100/controlnet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-100/optimizer.bin +3 -0
- checkpoint-100/random_states_0.pkl +3 -0
- checkpoint-100/scheduler.bin +3 -0
- checkpoint-1000/controlnet/config.json +58 -0
- checkpoint-1000/controlnet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-2000/controlnet/config.json +58 -0
- checkpoint-2000/controlnet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2000/optimizer.bin +3 -0
- checkpoint-2000/random_states_0.pkl +3 -0
- checkpoint-2000/scheduler.bin +3 -0
- checkpoint-3000/controlnet/config.json +58 -0
- checkpoint-3000/controlnet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3000/optimizer.bin +3 -0
- checkpoint-3000/random_states_0.pkl +3 -0
- checkpoint-3000/scheduler.bin +3 -0
- checkpoint-4000/controlnet/config.json +58 -0
- checkpoint-4000/controlnet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-4000/optimizer.bin +3 -0
- checkpoint-4000/random_states_0.pkl +3 -0
- checkpoint-4000/scheduler.bin +3 -0
- checkpoint-5000/controlnet/config.json +58 -0
- checkpoint-5000/controlnet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-5000/optimizer.bin +3 -0
- checkpoint-5000/random_states_0.pkl +3 -0
- checkpoint-5000/scheduler.bin +3 -0
- config.json +58 -0
- diffusion_pytorch_model.safetensors +3 -0
- logs/sample/1730742409.3826554/events.out.tfevents.1730742409.5ad68ea5fba8.1714.1 +3 -0
- logs/sample/1730742409.3844607/hparams.yml +54 -0
- logs/sample/1730743042.4770608/events.out.tfevents.1730743042.5ad68ea5fba8.4331.1 +3 -0
- logs/sample/1730743042.4789245/hparams.yml +54 -0
- logs/sample/events.out.tfevents.1730742409.5ad68ea5fba8.1714.0 +3 -0
- logs/sample/events.out.tfevents.1730743042.5ad68ea5fba8.4331.0 +3 -0
README.md
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: cagliostrolab/animagine-xl-3.1
|
3 |
+
library_name: diffusers
|
4 |
+
license: openrail++
|
5 |
+
tags:
|
6 |
+
- stable-diffusion-xl
|
7 |
+
- stable-diffusion-xl-diffusers
|
8 |
+
- text-to-image
|
9 |
+
- diffusers
|
10 |
+
- controlnet
|
11 |
+
- diffusers-training
|
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-watsydney/animagine-sample
|
20 |
+
|
21 |
+
These are controlnet weights trained on cagliostrolab/animagine-xl-3.1 with new type of conditioning.
|
22 |
+
|
23 |
+
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
#### How to use
|
28 |
+
|
29 |
+
```python
|
30 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
31 |
+
```
|
32 |
+
|
33 |
+
#### Limitations and bias
|
34 |
+
|
35 |
+
[TODO: provide examples of latent issues and potential remediations]
|
36 |
+
|
37 |
+
## Training details
|
38 |
+
|
39 |
+
[TODO: describe the data used to train the model]
|
checkpoint-100/controlnet/config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.30.3",
|
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": false,
|
56 |
+
"use_linear_projection": true
|
57 |
+
}
|
checkpoint-100/controlnet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:807aa29189c10660dff77a5bbfcf5cf39d60f7780199db36db36a9096e11ace7
|
3 |
+
size 2502139104
|
checkpoint-100/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc18f26892cefc917c3079f033e67f261d803f4cd1aa15be4612b61fa6b61c13
|
3 |
+
size 2544590030
|
checkpoint-100/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b49c53703760d115ae3e4531622bb568ca7b7cdbe745833a29719e7863cc1696
|
3 |
+
size 14344
|
checkpoint-100/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d860912d4bc0403250fef9b886e201db28aaa6bd91f9fa6f113746e3ff460a2c
|
3 |
+
size 1000
|
checkpoint-1000/controlnet/config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.30.3",
|
4 |
+
"_name_or_path": "./animagine-sample/checkpoint-100",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280
|
18 |
+
],
|
19 |
+
"class_embed_type": null,
|
20 |
+
"conditioning_channels": 3,
|
21 |
+
"conditioning_embedding_out_channels": [
|
22 |
+
16,
|
23 |
+
32,
|
24 |
+
96,
|
25 |
+
256
|
26 |
+
],
|
27 |
+
"controlnet_conditioning_channel_order": "rgb",
|
28 |
+
"cross_attention_dim": 2048,
|
29 |
+
"down_block_types": [
|
30 |
+
"DownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D"
|
33 |
+
],
|
34 |
+
"downsample_padding": 1,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"global_pool_conditions": false,
|
40 |
+
"in_channels": 4,
|
41 |
+
"layers_per_block": 2,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"projection_class_embeddings_input_dim": 2816,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"transformer_layers_per_block": [
|
52 |
+
1,
|
53 |
+
2,
|
54 |
+
10
|
55 |
+
],
|
56 |
+
"upcast_attention": false,
|
57 |
+
"use_linear_projection": true
|
58 |
+
}
|
checkpoint-1000/controlnet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0188908c409543ffc13fcc3ceb5a072e0dc0220226951568671923e039040975
|
3 |
+
size 5004167864
|
checkpoint-1000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a131a1ccff5c6bdcb6e3ad547a488767763faabddf7a77aaa9b794539d742d8e
|
3 |
+
size 2545717486
|
checkpoint-1000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b0044bd9ce26634295112e8625f9cb8d55a14c354863ca21d3a47dfaa9183ca
|
3 |
+
size 14344
|
checkpoint-1000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d16ae9dedf4c45ceadc467593037d83423677715e75ab402a9f44aa81de9b84
|
3 |
+
size 1000
|
checkpoint-2000/controlnet/config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.30.3",
|
4 |
+
"_name_or_path": "./animagine-sample/checkpoint-100",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280
|
18 |
+
],
|
19 |
+
"class_embed_type": null,
|
20 |
+
"conditioning_channels": 3,
|
21 |
+
"conditioning_embedding_out_channels": [
|
22 |
+
16,
|
23 |
+
32,
|
24 |
+
96,
|
25 |
+
256
|
26 |
+
],
|
27 |
+
"controlnet_conditioning_channel_order": "rgb",
|
28 |
+
"cross_attention_dim": 2048,
|
29 |
+
"down_block_types": [
|
30 |
+
"DownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D"
|
33 |
+
],
|
34 |
+
"downsample_padding": 1,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"global_pool_conditions": false,
|
40 |
+
"in_channels": 4,
|
41 |
+
"layers_per_block": 2,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"projection_class_embeddings_input_dim": 2816,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"transformer_layers_per_block": [
|
52 |
+
1,
|
53 |
+
2,
|
54 |
+
10
|
55 |
+
],
|
56 |
+
"upcast_attention": false,
|
57 |
+
"use_linear_projection": true
|
58 |
+
}
|
checkpoint-2000/controlnet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bbb157563ebe315e7b820b63a63de4cc224bf1de8f7047caf7f23f79abef6c2
|
3 |
+
size 5004167864
|
checkpoint-2000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4f24b47b6cd61160bf9a82003ce6587792b0a8145de586bc64b9312f585d937
|
3 |
+
size 2545717486
|
checkpoint-2000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fef5e416f8761df3d85397f4580b78bdf806513578b6db5f83392117b35358c
|
3 |
+
size 14344
|
checkpoint-2000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81a7fe0a2983de695c44ba167520d4ce1ca01157e36e90498bee8c9d8e4b61fc
|
3 |
+
size 1000
|
checkpoint-3000/controlnet/config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.30.3",
|
4 |
+
"_name_or_path": "./animagine-sample/checkpoint-100",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280
|
18 |
+
],
|
19 |
+
"class_embed_type": null,
|
20 |
+
"conditioning_channels": 3,
|
21 |
+
"conditioning_embedding_out_channels": [
|
22 |
+
16,
|
23 |
+
32,
|
24 |
+
96,
|
25 |
+
256
|
26 |
+
],
|
27 |
+
"controlnet_conditioning_channel_order": "rgb",
|
28 |
+
"cross_attention_dim": 2048,
|
29 |
+
"down_block_types": [
|
30 |
+
"DownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D"
|
33 |
+
],
|
34 |
+
"downsample_padding": 1,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"global_pool_conditions": false,
|
40 |
+
"in_channels": 4,
|
41 |
+
"layers_per_block": 2,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"projection_class_embeddings_input_dim": 2816,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"transformer_layers_per_block": [
|
52 |
+
1,
|
53 |
+
2,
|
54 |
+
10
|
55 |
+
],
|
56 |
+
"upcast_attention": false,
|
57 |
+
"use_linear_projection": true
|
58 |
+
}
|
checkpoint-3000/controlnet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fd69db43a3563ffd6f7fbc19e3ab9b1012d50532d7db2b3daef94b98b0ab63c
|
3 |
+
size 5004167864
|
checkpoint-3000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:881792b727a9ebb92a7289a8d371b863fcd3183234813700fa5cbf2ba67c7596
|
3 |
+
size 2545717486
|
checkpoint-3000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc4076bb91e90d3207a9e011dc333066ef6bb2dd11c1894c80484db88be5a321
|
3 |
+
size 14344
|
checkpoint-3000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a530ffa9220cf65c0729e966fdf26ce7223ed3dc88346bbe1367170da20bad4
|
3 |
+
size 1000
|
checkpoint-4000/controlnet/config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.30.3",
|
4 |
+
"_name_or_path": "./animagine-sample/checkpoint-100",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280
|
18 |
+
],
|
19 |
+
"class_embed_type": null,
|
20 |
+
"conditioning_channels": 3,
|
21 |
+
"conditioning_embedding_out_channels": [
|
22 |
+
16,
|
23 |
+
32,
|
24 |
+
96,
|
25 |
+
256
|
26 |
+
],
|
27 |
+
"controlnet_conditioning_channel_order": "rgb",
|
28 |
+
"cross_attention_dim": 2048,
|
29 |
+
"down_block_types": [
|
30 |
+
"DownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D"
|
33 |
+
],
|
34 |
+
"downsample_padding": 1,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"global_pool_conditions": false,
|
40 |
+
"in_channels": 4,
|
41 |
+
"layers_per_block": 2,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"projection_class_embeddings_input_dim": 2816,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"transformer_layers_per_block": [
|
52 |
+
1,
|
53 |
+
2,
|
54 |
+
10
|
55 |
+
],
|
56 |
+
"upcast_attention": false,
|
57 |
+
"use_linear_projection": true
|
58 |
+
}
|
checkpoint-4000/controlnet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bc3cd267dd2d94d87c855d6cb5fd1b8dc2b8cc7ebad2cba447a66dbdc986d5a
|
3 |
+
size 5004167864
|
checkpoint-4000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbe5f6249aa4c6067eef227ef92541f743600de72a80f0f09784175f3d619853
|
3 |
+
size 2545717486
|
checkpoint-4000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13cb77045ac19c18ca9d3169c0a5ee4260308c42e4808acb06305fb08b6c40b2
|
3 |
+
size 14344
|
checkpoint-4000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a27fbcb71e64da5cd3c386782ab45bb0efde0abb5d30842a94c8a599b450c90c
|
3 |
+
size 1000
|
checkpoint-5000/controlnet/config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.30.3",
|
4 |
+
"_name_or_path": "./animagine-sample/checkpoint-100",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280
|
18 |
+
],
|
19 |
+
"class_embed_type": null,
|
20 |
+
"conditioning_channels": 3,
|
21 |
+
"conditioning_embedding_out_channels": [
|
22 |
+
16,
|
23 |
+
32,
|
24 |
+
96,
|
25 |
+
256
|
26 |
+
],
|
27 |
+
"controlnet_conditioning_channel_order": "rgb",
|
28 |
+
"cross_attention_dim": 2048,
|
29 |
+
"down_block_types": [
|
30 |
+
"DownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D"
|
33 |
+
],
|
34 |
+
"downsample_padding": 1,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"global_pool_conditions": false,
|
40 |
+
"in_channels": 4,
|
41 |
+
"layers_per_block": 2,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"projection_class_embeddings_input_dim": 2816,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"transformer_layers_per_block": [
|
52 |
+
1,
|
53 |
+
2,
|
54 |
+
10
|
55 |
+
],
|
56 |
+
"upcast_attention": false,
|
57 |
+
"use_linear_projection": true
|
58 |
+
}
|
checkpoint-5000/controlnet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8227cb215733203e5aea0318a6409ff5ed5bcb5a2a63dc481ec77ba75022fd9f
|
3 |
+
size 5004167864
|
checkpoint-5000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fcc9a7d2e6cbcd5a3a60006a475286d9f88fda15628efa7a3c220b307988989
|
3 |
+
size 2545717486
|
checkpoint-5000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47520d0deaf815659439c5b5030ef027159936967534a9231afd5e9f6f9e2b7c
|
3 |
+
size 14344
|
checkpoint-5000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:920333155b08e76154b89a85170c320833074db7b84649a9cfe79fd10b6bf2d9
|
3 |
+
size 1000
|
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.30.3",
|
4 |
+
"_name_or_path": "./animagine-sample/checkpoint-100",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"addition_embed_type": "text_time",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"addition_time_embed_dim": 256,
|
9 |
+
"attention_head_dim": [
|
10 |
+
5,
|
11 |
+
10,
|
12 |
+
20
|
13 |
+
],
|
14 |
+
"block_out_channels": [
|
15 |
+
320,
|
16 |
+
640,
|
17 |
+
1280
|
18 |
+
],
|
19 |
+
"class_embed_type": null,
|
20 |
+
"conditioning_channels": 3,
|
21 |
+
"conditioning_embedding_out_channels": [
|
22 |
+
16,
|
23 |
+
32,
|
24 |
+
96,
|
25 |
+
256
|
26 |
+
],
|
27 |
+
"controlnet_conditioning_channel_order": "rgb",
|
28 |
+
"cross_attention_dim": 2048,
|
29 |
+
"down_block_types": [
|
30 |
+
"DownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D"
|
33 |
+
],
|
34 |
+
"downsample_padding": 1,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"global_pool_conditions": false,
|
40 |
+
"in_channels": 4,
|
41 |
+
"layers_per_block": 2,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"norm_eps": 1e-05,
|
45 |
+
"norm_num_groups": 32,
|
46 |
+
"num_attention_heads": null,
|
47 |
+
"num_class_embeds": null,
|
48 |
+
"only_cross_attention": false,
|
49 |
+
"projection_class_embeddings_input_dim": 2816,
|
50 |
+
"resnet_time_scale_shift": "default",
|
51 |
+
"transformer_layers_per_block": [
|
52 |
+
1,
|
53 |
+
2,
|
54 |
+
10
|
55 |
+
],
|
56 |
+
"upcast_attention": false,
|
57 |
+
"use_linear_projection": true
|
58 |
+
}
|
diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8227cb215733203e5aea0318a6409ff5ed5bcb5a2a63dc481ec77ba75022fd9f
|
3 |
+
size 5004167864
|
logs/sample/1730742409.3826554/events.out.tfevents.1730742409.5ad68ea5fba8.1714.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1ad59687761caf276f04f52346b3643d1f4e80f00803e62887555d54585ac61
|
3 |
+
size 2575
|
logs/sample/1730742409.3844607/hparams.yml
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 1000
|
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_npu_flash_attention: false
|
18 |
+
enable_xformers_memory_efficient_attention: true
|
19 |
+
gradient_accumulation_steps: 4
|
20 |
+
gradient_checkpointing: false
|
21 |
+
hub_model_id: null
|
22 |
+
hub_token: null
|
23 |
+
image_column: image
|
24 |
+
learning_rate: 1.0e-05
|
25 |
+
logging_dir: logs
|
26 |
+
lr_num_cycles: 1
|
27 |
+
lr_power: 1.0
|
28 |
+
lr_scheduler: constant
|
29 |
+
lr_warmup_steps: 500
|
30 |
+
max_grad_norm: 1.0
|
31 |
+
max_train_samples: null
|
32 |
+
max_train_steps: 50
|
33 |
+
mixed_precision: 'no'
|
34 |
+
num_train_epochs: 2
|
35 |
+
num_validation_images: 1
|
36 |
+
output_dir: ./animagine-sample
|
37 |
+
pretrained_model_name_or_path: cagliostrolab/animagine-xl-3.1
|
38 |
+
pretrained_vae_model_name_or_path: null
|
39 |
+
proportion_empty_prompts: 0
|
40 |
+
push_to_hub: false
|
41 |
+
report_to: tensorboard
|
42 |
+
resolution: 1024
|
43 |
+
resume_from_checkpoint: null
|
44 |
+
revision: null
|
45 |
+
scale_lr: false
|
46 |
+
seed: 42
|
47 |
+
set_grads_to_none: false
|
48 |
+
tokenizer_name: null
|
49 |
+
tracker_project_name: sample
|
50 |
+
train_batch_size: 1
|
51 |
+
train_data_dir: realding/11bubbletest_grayscale
|
52 |
+
use_8bit_adam: true
|
53 |
+
validation_steps: 100
|
54 |
+
variant: null
|
logs/sample/1730743042.4770608/events.out.tfevents.1730743042.5ad68ea5fba8.4331.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b9dbc7815ad48da52b29efdee069467f3b91be0a140c5263917c2e9ff2506f0
|
3 |
+
size 2575
|
logs/sample/1730743042.4789245/hparams.yml
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 100
|
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_npu_flash_attention: false
|
18 |
+
enable_xformers_memory_efficient_attention: true
|
19 |
+
gradient_accumulation_steps: 4
|
20 |
+
gradient_checkpointing: false
|
21 |
+
hub_model_id: null
|
22 |
+
hub_token: null
|
23 |
+
image_column: image
|
24 |
+
learning_rate: 1.0e-05
|
25 |
+
logging_dir: logs
|
26 |
+
lr_num_cycles: 1
|
27 |
+
lr_power: 1.0
|
28 |
+
lr_scheduler: constant
|
29 |
+
lr_warmup_steps: 500
|
30 |
+
max_grad_norm: 1.0
|
31 |
+
max_train_samples: null
|
32 |
+
max_train_steps: 150
|
33 |
+
mixed_precision: 'no'
|
34 |
+
num_train_epochs: 6
|
35 |
+
num_validation_images: 1
|
36 |
+
output_dir: ./animagine-sample
|
37 |
+
pretrained_model_name_or_path: cagliostrolab/animagine-xl-3.1
|
38 |
+
pretrained_vae_model_name_or_path: null
|
39 |
+
proportion_empty_prompts: 0
|
40 |
+
push_to_hub: false
|
41 |
+
report_to: tensorboard
|
42 |
+
resolution: 1024
|
43 |
+
resume_from_checkpoint: null
|
44 |
+
revision: null
|
45 |
+
scale_lr: false
|
46 |
+
seed: 42
|
47 |
+
set_grads_to_none: false
|
48 |
+
tokenizer_name: null
|
49 |
+
tracker_project_name: sample
|
50 |
+
train_batch_size: 1
|
51 |
+
train_data_dir: realding/11bubbletest_grayscale
|
52 |
+
use_8bit_adam: true
|
53 |
+
validation_steps: 100
|
54 |
+
variant: null
|
logs/sample/events.out.tfevents.1730742409.5ad68ea5fba8.1714.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d73a1221a8e376ee19d40c2b41fc686d69be11afe47bd5394b7dde69bd1fa281
|
3 |
+
size 16312
|
logs/sample/events.out.tfevents.1730743042.5ad68ea5fba8.4331.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e8a9bd871c15125a2efcdef49a51dbbc82d815c34f76655223362a67006e21a
|
3 |
+
size 48630
|