End of training
Browse files- README.md +4 -4
- checkpoint-180000/optimizer.bin +3 -0
- checkpoint-180000/random_states_0.pkl +3 -0
- checkpoint-180000/scaler.pt +3 -0
- checkpoint-180000/scheduler.bin +3 -0
- checkpoint-180000/unet/config.json +65 -0
- checkpoint-180000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-190000/optimizer.bin +3 -0
- checkpoint-190000/random_states_0.pkl +3 -0
- checkpoint-190000/scaler.pt +3 -0
- checkpoint-190000/scheduler.bin +3 -0
- checkpoint-190000/unet/config.json +65 -0
- checkpoint-190000/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-200000/optimizer.bin +3 -0
- checkpoint-200000/random_states_0.pkl +3 -0
- checkpoint-200000/scaler.pt +3 -0
- checkpoint-200000/scheduler.bin +3 -0
- checkpoint-200000/unet/config.json +65 -0
- checkpoint-200000/unet/diffusion_pytorch_model.bin +3 -0
- unet/config.json +1 -1
- unet/diffusion_pytorch_model.bin +1 -1
- val_imgs_grid.png +0 -0
README.md
CHANGED
@@ -14,7 +14,7 @@ inference: true
|
|
14 |
|
15 |
# Text-to-image finetuning - iamkaikai/amazing-logos
|
16 |
|
17 |
-
This pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **iamkaikai/amazing_logos_v2** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Simple elegant logo for Digital Art, D A
|
18 |
|
19 |
![val_imgs_grid](./val_imgs_grid.png)
|
20 |
|
@@ -28,7 +28,7 @@ from diffusers import DiffusionPipeline
|
|
28 |
import torch
|
29 |
|
30 |
pipeline = DiffusionPipeline.from_pretrained("iamkaikai/amazing-logos", torch_dtype=torch.float16)
|
31 |
-
prompt = "Simple elegant logo for Digital Art, D A
|
32 |
image = pipeline(prompt).images[0]
|
33 |
image.save("my_image.png")
|
34 |
```
|
@@ -37,7 +37,7 @@ image.save("my_image.png")
|
|
37 |
|
38 |
These are the key hyperparameters used during training:
|
39 |
|
40 |
-
* Epochs:
|
41 |
* Learning rate: 1e-07
|
42 |
* Batch size: 1
|
43 |
* Gradient accumulation steps: 1
|
@@ -45,4 +45,4 @@ These are the key hyperparameters used during training:
|
|
45 |
* Mixed-precision: fp16
|
46 |
|
47 |
|
48 |
-
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/iam-kai-kai/text2image-fine-tune/runs/
|
|
|
14 |
|
15 |
# Text-to-image finetuning - iamkaikai/amazing-logos
|
16 |
|
17 |
+
This pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **iamkaikai/amazing_logos_v2** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Simple elegant logo for Digital Art, D A Square Symmetrical, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white']:
|
18 |
|
19 |
![val_imgs_grid](./val_imgs_grid.png)
|
20 |
|
|
|
28 |
import torch
|
29 |
|
30 |
pipeline = DiffusionPipeline.from_pretrained("iamkaikai/amazing-logos", torch_dtype=torch.float16)
|
31 |
+
prompt = "Simple elegant logo for Digital Art, D A Square Symmetrical, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white"
|
32 |
image = pipeline(prompt).images[0]
|
33 |
image.save("my_image.png")
|
34 |
```
|
|
|
37 |
|
38 |
These are the key hyperparameters used during training:
|
39 |
|
40 |
+
* Epochs: 20
|
41 |
* Learning rate: 1e-07
|
42 |
* Batch size: 1
|
43 |
* Gradient accumulation steps: 1
|
|
|
45 |
* Mixed-precision: fp16
|
46 |
|
47 |
|
48 |
+
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/iam-kai-kai/text2image-fine-tune/runs/36y6uxai).
|
checkpoint-180000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20cd3b60296ac1573be0a03d887d637d29c74b890fde5036dc5bfc6636f7592c
|
3 |
+
size 6876749715
|
checkpoint-180000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b30e6a37947da7d9ff95cca35c6c8020144b478959c47203f32a705692e0f57d
|
3 |
+
size 14727
|
checkpoint-180000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f9fed2405de7a826c01209d4198713c7cebcc07e1118b45c1dccf76ecba501a
|
3 |
+
size 557
|
checkpoint-180000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdb9c50e3f617962e448eb62a15f8655a19c6f84da04aeccebcb187b73e66997
|
3 |
+
size 563
|
checkpoint-180000/unet/config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.19.0.dev0",
|
4 |
+
"_name_or_path": "sd/amazing-logos/checkpoint-170000",
|
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": 8,
|
10 |
+
"block_out_channels": [
|
11 |
+
320,
|
12 |
+
640,
|
13 |
+
1280,
|
14 |
+
1280
|
15 |
+
],
|
16 |
+
"center_input_sample": false,
|
17 |
+
"class_embed_type": null,
|
18 |
+
"class_embeddings_concat": false,
|
19 |
+
"conv_in_kernel": 3,
|
20 |
+
"conv_out_kernel": 3,
|
21 |
+
"cross_attention_dim": 768,
|
22 |
+
"cross_attention_norm": null,
|
23 |
+
"down_block_types": [
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"DownBlock2D"
|
28 |
+
],
|
29 |
+
"downsample_padding": 1,
|
30 |
+
"dual_cross_attention": false,
|
31 |
+
"encoder_hid_dim": null,
|
32 |
+
"encoder_hid_dim_type": null,
|
33 |
+
"flip_sin_to_cos": true,
|
34 |
+
"freq_shift": 0,
|
35 |
+
"in_channels": 4,
|
36 |
+
"layers_per_block": 2,
|
37 |
+
"mid_block_only_cross_attention": null,
|
38 |
+
"mid_block_scale_factor": 1,
|
39 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
40 |
+
"norm_eps": 1e-05,
|
41 |
+
"norm_num_groups": 32,
|
42 |
+
"num_attention_heads": null,
|
43 |
+
"num_class_embeds": null,
|
44 |
+
"only_cross_attention": false,
|
45 |
+
"out_channels": 4,
|
46 |
+
"projection_class_embeddings_input_dim": null,
|
47 |
+
"resnet_out_scale_factor": 1.0,
|
48 |
+
"resnet_skip_time_act": false,
|
49 |
+
"resnet_time_scale_shift": "default",
|
50 |
+
"sample_size": 64,
|
51 |
+
"time_cond_proj_dim": null,
|
52 |
+
"time_embedding_act_fn": null,
|
53 |
+
"time_embedding_dim": null,
|
54 |
+
"time_embedding_type": "positional",
|
55 |
+
"timestep_post_act": null,
|
56 |
+
"transformer_layers_per_block": 1,
|
57 |
+
"up_block_types": [
|
58 |
+
"UpBlock2D",
|
59 |
+
"CrossAttnUpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"use_linear_projection": false
|
65 |
+
}
|
checkpoint-180000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82bbd085e5419de58b7f6f94f97f984a0de9f88cc23f51a3352fa20d3ae2cdf0
|
3 |
+
size 3438375973
|
checkpoint-190000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a0b28d3d2c35728fc9f81689eaadce4680baca071c451c258f0a0b6be5d53c6
|
3 |
+
size 6876749715
|
checkpoint-190000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a42031f184e84b774772af8660aed89c9dc5ff024c213239aa3f9cada867bc7c
|
3 |
+
size 14727
|
checkpoint-190000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:683abfa33cba48623e6472d3f6aabb85bf6f5a1eb903d3b09aee381155413306
|
3 |
+
size 557
|
checkpoint-190000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0eadaa696a5b8bbff2e405c79aa47f6a48a0f2a831e3d867368cdaa72c6a531
|
3 |
+
size 563
|
checkpoint-190000/unet/config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.19.0.dev0",
|
4 |
+
"_name_or_path": "sd/amazing-logos/checkpoint-170000",
|
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": 8,
|
10 |
+
"block_out_channels": [
|
11 |
+
320,
|
12 |
+
640,
|
13 |
+
1280,
|
14 |
+
1280
|
15 |
+
],
|
16 |
+
"center_input_sample": false,
|
17 |
+
"class_embed_type": null,
|
18 |
+
"class_embeddings_concat": false,
|
19 |
+
"conv_in_kernel": 3,
|
20 |
+
"conv_out_kernel": 3,
|
21 |
+
"cross_attention_dim": 768,
|
22 |
+
"cross_attention_norm": null,
|
23 |
+
"down_block_types": [
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"DownBlock2D"
|
28 |
+
],
|
29 |
+
"downsample_padding": 1,
|
30 |
+
"dual_cross_attention": false,
|
31 |
+
"encoder_hid_dim": null,
|
32 |
+
"encoder_hid_dim_type": null,
|
33 |
+
"flip_sin_to_cos": true,
|
34 |
+
"freq_shift": 0,
|
35 |
+
"in_channels": 4,
|
36 |
+
"layers_per_block": 2,
|
37 |
+
"mid_block_only_cross_attention": null,
|
38 |
+
"mid_block_scale_factor": 1,
|
39 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
40 |
+
"norm_eps": 1e-05,
|
41 |
+
"norm_num_groups": 32,
|
42 |
+
"num_attention_heads": null,
|
43 |
+
"num_class_embeds": null,
|
44 |
+
"only_cross_attention": false,
|
45 |
+
"out_channels": 4,
|
46 |
+
"projection_class_embeddings_input_dim": null,
|
47 |
+
"resnet_out_scale_factor": 1.0,
|
48 |
+
"resnet_skip_time_act": false,
|
49 |
+
"resnet_time_scale_shift": "default",
|
50 |
+
"sample_size": 64,
|
51 |
+
"time_cond_proj_dim": null,
|
52 |
+
"time_embedding_act_fn": null,
|
53 |
+
"time_embedding_dim": null,
|
54 |
+
"time_embedding_type": "positional",
|
55 |
+
"timestep_post_act": null,
|
56 |
+
"transformer_layers_per_block": 1,
|
57 |
+
"up_block_types": [
|
58 |
+
"UpBlock2D",
|
59 |
+
"CrossAttnUpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"use_linear_projection": false
|
65 |
+
}
|
checkpoint-190000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5865be199d1a3ec874c4ec7ef1d5f37ccaa77194b9282f871db63e7749ee28f9
|
3 |
+
size 3438375973
|
checkpoint-200000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e0f6b6cca6896c05a6b4db2ea18f0a60ff3c4de267f7099f2cbc3699764b123
|
3 |
+
size 6876749715
|
checkpoint-200000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39241517f2b3846f5a74ecee1f5a7564bd693a4bffde292acfc9dc47cafe39d6
|
3 |
+
size 14727
|
checkpoint-200000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee1a1cbe6cc1ed4df82b374a0d8fe34599aaab7a21d256d665b65a66381d5db9
|
3 |
+
size 557
|
checkpoint-200000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c475c304063c153cd9000fcf4289337306b2b7100b4446d41891fddd3ac538e6
|
3 |
+
size 563
|
checkpoint-200000/unet/config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.19.0.dev0",
|
4 |
+
"_name_or_path": "sd/amazing-logos/checkpoint-170000",
|
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": 8,
|
10 |
+
"block_out_channels": [
|
11 |
+
320,
|
12 |
+
640,
|
13 |
+
1280,
|
14 |
+
1280
|
15 |
+
],
|
16 |
+
"center_input_sample": false,
|
17 |
+
"class_embed_type": null,
|
18 |
+
"class_embeddings_concat": false,
|
19 |
+
"conv_in_kernel": 3,
|
20 |
+
"conv_out_kernel": 3,
|
21 |
+
"cross_attention_dim": 768,
|
22 |
+
"cross_attention_norm": null,
|
23 |
+
"down_block_types": [
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"DownBlock2D"
|
28 |
+
],
|
29 |
+
"downsample_padding": 1,
|
30 |
+
"dual_cross_attention": false,
|
31 |
+
"encoder_hid_dim": null,
|
32 |
+
"encoder_hid_dim_type": null,
|
33 |
+
"flip_sin_to_cos": true,
|
34 |
+
"freq_shift": 0,
|
35 |
+
"in_channels": 4,
|
36 |
+
"layers_per_block": 2,
|
37 |
+
"mid_block_only_cross_attention": null,
|
38 |
+
"mid_block_scale_factor": 1,
|
39 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
40 |
+
"norm_eps": 1e-05,
|
41 |
+
"norm_num_groups": 32,
|
42 |
+
"num_attention_heads": null,
|
43 |
+
"num_class_embeds": null,
|
44 |
+
"only_cross_attention": false,
|
45 |
+
"out_channels": 4,
|
46 |
+
"projection_class_embeddings_input_dim": null,
|
47 |
+
"resnet_out_scale_factor": 1.0,
|
48 |
+
"resnet_skip_time_act": false,
|
49 |
+
"resnet_time_scale_shift": "default",
|
50 |
+
"sample_size": 64,
|
51 |
+
"time_cond_proj_dim": null,
|
52 |
+
"time_embedding_act_fn": null,
|
53 |
+
"time_embedding_dim": null,
|
54 |
+
"time_embedding_type": "positional",
|
55 |
+
"timestep_post_act": null,
|
56 |
+
"transformer_layers_per_block": 1,
|
57 |
+
"up_block_types": [
|
58 |
+
"UpBlock2D",
|
59 |
+
"CrossAttnUpBlock2D",
|
60 |
+
"CrossAttnUpBlock2D",
|
61 |
+
"CrossAttnUpBlock2D"
|
62 |
+
],
|
63 |
+
"upcast_attention": false,
|
64 |
+
"use_linear_projection": false
|
65 |
+
}
|
checkpoint-200000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23ea808f289636a1588377adfda89539352e73ce3fb383bfefd2d98b1352ae4a
|
3 |
+
size 3438375973
|
unet/config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
"_diffusers_version": "0.19.0.dev0",
|
4 |
-
"_name_or_path": "sd/amazing-logos/checkpoint-
|
5 |
"act_fn": "silu",
|
6 |
"addition_embed_type": null,
|
7 |
"addition_embed_type_num_heads": 64,
|
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
"_diffusers_version": "0.19.0.dev0",
|
4 |
+
"_name_or_path": "sd/amazing-logos/checkpoint-170000",
|
5 |
"act_fn": "silu",
|
6 |
"addition_embed_type": null,
|
7 |
"addition_embed_type_num_heads": 64,
|
unet/diffusion_pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3438375973
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23ea808f289636a1588377adfda89539352e73ce3fb383bfefd2d98b1352ae4a
|
3 |
size 3438375973
|
val_imgs_grid.png
CHANGED