juliajoanna
commited on
Commit
•
9fcad9a
1
Parent(s):
b75220c
End of training
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-10000/optimizer.bin +3 -0
- checkpoint-10000/random_states_0.pkl +3 -0
- checkpoint-10000/scheduler.bin +3 -0
- checkpoint-10000/unet/config.json +73 -0
- checkpoint-10000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-12000/optimizer.bin +3 -0
- checkpoint-12000/random_states_0.pkl +3 -0
- checkpoint-12000/scheduler.bin +3 -0
- checkpoint-12000/unet/config.json +73 -0
- checkpoint-12000/unet/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-14000/unet/config.json +73 -0
- checkpoint-14000/unet/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-2000/unet/config.json +73 -0
- checkpoint-2000/unet/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-4000/unet/config.json +73 -0
- checkpoint-4000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-6000/optimizer.bin +3 -0
- checkpoint-6000/random_states_0.pkl +3 -0
- checkpoint-6000/scheduler.bin +3 -0
- checkpoint-6000/unet/config.json +73 -0
- checkpoint-6000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-8000/optimizer.bin +3 -0
- checkpoint-8000/random_states_0.pkl +3 -0
- checkpoint-8000/scheduler.bin +3 -0
- checkpoint-8000/unet/config.json +73 -0
- checkpoint-8000/unet/diffusion_pytorch_model.safetensors +3 -0
- image_0.png +2 -2
- image_1.png +2 -2
- image_2.png +2 -2
- image_3.png +2 -2
- logs/text2image-fine-tune-sdxl/1699564389.9686658/events.out.tfevents.1699564389.4124gs01.2074770.1 +3 -0
- logs/text2image-fine-tune-sdxl/1699564389.9709973/hparams.yml +56 -0
- logs/text2image-fine-tune-sdxl/1699565455.163503/events.out.tfevents.1699565455.4124gs01.2087089.1 +3 -0
- logs/text2image-fine-tune-sdxl/1699565455.1653008/hparams.yml +56 -0
- logs/text2image-fine-tune-sdxl/1699567973.1467016/events.out.tfevents.1699567973.4124gs01.2098631.1 +3 -0
- logs/text2image-fine-tune-sdxl/1699567973.149079/hparams.yml +56 -0
- logs/text2image-fine-tune-sdxl/1699568176.5264077/events.out.tfevents.1699568176.4124gs01.2100196.1 +3 -0
- logs/text2image-fine-tune-sdxl/1699568176.5279846/hparams.yml +56 -0
- logs/text2image-fine-tune-sdxl/1699568465.8294842/events.out.tfevents.1699568465.4124gs01.2102710.1 +3 -0
- logs/text2image-fine-tune-sdxl/1699568465.831263/hparams.yml +56 -0
- logs/text2image-fine-tune-sdxl/1699568662.2018025/events.out.tfevents.1699568662.4124gs01.2103894.1 +3 -0
checkpoint-10000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f07af2d203df2dee3b0a38dd26c58e242e761f5d4dfbe2056290c1a6393d8da
|
3 |
+
size 20541173898
|
checkpoint-10000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ba2c950e31d5ae787bd33b309bed75b31a27f69a2a31590838975ecdb901bda
|
3 |
+
size 14344
|
checkpoint-10000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06effd520766ea4bf433e328069a8f372a51c114ac80e230f0948163719cd0c3
|
3 |
+
size 1000
|
checkpoint-10000/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
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 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
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 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-10000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddc1dfa6a1f19244a93d8bc20222e1565b21b93a6c17aebf9d014725cd666093
|
3 |
+
size 10270077736
|
checkpoint-12000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2d43d952867a0aa2ac4ed8894df4aece1e3f34ae08dc2fea38f7ca4931e5f9c
|
3 |
+
size 20541173898
|
checkpoint-12000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff1cb0940b2f57cb0d1c0138f848fdc49a4c74f5b6f736c91c9f30d4c9c8471a
|
3 |
+
size 14344
|
checkpoint-12000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c82973153dea5cf9a471058fa34947c8e4abee4df03cb78fc273cd87224bacd
|
3 |
+
size 1000
|
checkpoint-12000/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
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 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
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 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-12000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f305692ca43f1e3f3cc95cc4be30476d67e74998125718d0cfed7ea540a904fe
|
3 |
+
size 10270077736
|
checkpoint-14000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f974cf80e0412c32760bb0d741675b5bbe155be86bb5d70d16d06f6907666556
|
3 |
+
size 20541173898
|
checkpoint-14000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94d5ca0cbeaf96200f81c4308b03a8b3acaf8ff079f163d2a7e2a18ab4aafe6b
|
3 |
+
size 14344
|
checkpoint-14000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a5e2264ea58f688ed476502e534baeaf6cd8d0457af94d996dbb095a8afc4b6
|
3 |
+
size 1000
|
checkpoint-14000/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
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 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
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 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-14000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:134c51c9adca2e1333ef4d9ccb523d82affdf76812c00e403e218dcd43d36216
|
3 |
+
size 10270077736
|
checkpoint-2000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c1a23abdc1ff267c8c387ba5076078cf10fe9d47d1952118ff690851891c368
|
3 |
+
size 20541173898
|
checkpoint-2000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b340153cf316f759589020c57809dc7e339b22b1ebade9764040bad39bc5e545
|
3 |
+
size 14344
|
checkpoint-2000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe3d121c38ead0248622203c308e1055781ce873ae44f4c05a5cd814a3253eaa
|
3 |
+
size 1000
|
checkpoint-2000/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
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 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
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 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-2000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0791a7e599752a94ea27d880eb7bdc800ecbc8711ffc4f7997ebdf0b2add9cdd
|
3 |
+
size 10270077736
|
checkpoint-4000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdda02705041891f6c1335db24598201509c7b12ee727afc5f6492d84d460f45
|
3 |
+
size 20541173898
|
checkpoint-4000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d09d2141b68289fabb5752c9bb4d3444be5ab0f642f7102e1d651477f842d1b0
|
3 |
+
size 14344
|
checkpoint-4000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a5fd66f5bfe9a9d50b60281f0168db8f4d76c1466da8493c4f717b4ae26481e
|
3 |
+
size 1000
|
checkpoint-4000/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
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 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
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 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-4000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bb84cd0213860bee411507939148b3efd8c57b24763dd0c50f5344fbd1910f3
|
3 |
+
size 10270077736
|
checkpoint-6000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48a414cbd37d07ff45720b9df837dc48d3bd28137907d0ab0a63a44f396efc8f
|
3 |
+
size 20541173898
|
checkpoint-6000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21becebdae7c5a865032ac7a861fff20b430606e4dc2177f2797a7e09cbda5ed
|
3 |
+
size 14344
|
checkpoint-6000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e76a1617011ef7a2c519a9f92d6623728b052bf47934946089d664951319f0d4
|
3 |
+
size 1000
|
checkpoint-6000/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
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 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
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 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-6000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcb4b40f6a7dd4cc88c07c0543dae0be8ccca892b42f02ed0049ee726b34a4b5
|
3 |
+
size 10270077736
|
checkpoint-8000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e672ef1ce030b0375504f7e244a218f6dfe6aa49a9c5241ae0e8ef1f8966520
|
3 |
+
size 20541173898
|
checkpoint-8000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9374abfa48a5cc437b0b97b31448c571ae133cef810121476cd8df776f6031cc
|
3 |
+
size 14344
|
checkpoint-8000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efff19450f55a9358b76f3e5170171942761d1c5b9128683028d0c09b8a24573
|
3 |
+
size 1000
|
checkpoint-8000/unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
|
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 |
+
"attention_type": "default",
|
15 |
+
"block_out_channels": [
|
16 |
+
320,
|
17 |
+
640,
|
18 |
+
1280
|
19 |
+
],
|
20 |
+
"center_input_sample": false,
|
21 |
+
"class_embed_type": null,
|
22 |
+
"class_embeddings_concat": false,
|
23 |
+
"conv_in_kernel": 3,
|
24 |
+
"conv_out_kernel": 3,
|
25 |
+
"cross_attention_dim": 2048,
|
26 |
+
"cross_attention_norm": null,
|
27 |
+
"down_block_types": [
|
28 |
+
"DownBlock2D",
|
29 |
+
"CrossAttnDownBlock2D",
|
30 |
+
"CrossAttnDownBlock2D"
|
31 |
+
],
|
32 |
+
"downsample_padding": 1,
|
33 |
+
"dropout": 0.0,
|
34 |
+
"dual_cross_attention": false,
|
35 |
+
"encoder_hid_dim": null,
|
36 |
+
"encoder_hid_dim_type": null,
|
37 |
+
"flip_sin_to_cos": true,
|
38 |
+
"freq_shift": 0,
|
39 |
+
"in_channels": 4,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
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 |
+
"out_channels": 4,
|
50 |
+
"projection_class_embeddings_input_dim": 2816,
|
51 |
+
"resnet_out_scale_factor": 1.0,
|
52 |
+
"resnet_skip_time_act": false,
|
53 |
+
"resnet_time_scale_shift": "default",
|
54 |
+
"reverse_transformer_layers_per_block": null,
|
55 |
+
"sample_size": 128,
|
56 |
+
"time_cond_proj_dim": null,
|
57 |
+
"time_embedding_act_fn": null,
|
58 |
+
"time_embedding_dim": null,
|
59 |
+
"time_embedding_type": "positional",
|
60 |
+
"timestep_post_act": null,
|
61 |
+
"transformer_layers_per_block": [
|
62 |
+
1,
|
63 |
+
2,
|
64 |
+
10
|
65 |
+
],
|
66 |
+
"up_block_types": [
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"UpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": null,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
checkpoint-8000/unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec2e3b9d967d2d42daba32db72f9e7989d3ced2bf8cb94b539e3ad9775ddb65f
|
3 |
+
size 10270077736
|
image_0.png
CHANGED
Git LFS Details
|
Git LFS Details
|
image_1.png
CHANGED
Git LFS Details
|
Git LFS Details
|
image_2.png
CHANGED
Git LFS Details
|
Git LFS Details
|
image_3.png
CHANGED
Git LFS Details
|
Git LFS Details
|
logs/text2image-fine-tune-sdxl/1699564389.9686658/events.out.tfevents.1699564389.4124gs01.2074770.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11640e0d6f4d3282904bb65e9aa1b203671d37318b9549fe16bed2ab4990ed78
|
3 |
+
size 2773
|
logs/text2image-fine-tune-sdxl/1699564389.9709973/hparams.yml
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: true
|
9 |
+
checkpointing_steps: 2000
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: null
|
14 |
+
enable_xformers_memory_efficient_attention: true
|
15 |
+
gradient_accumulation_steps: 4
|
16 |
+
gradient_checkpointing: true
|
17 |
+
hub_model_id: null
|
18 |
+
hub_token: null
|
19 |
+
image_column: image
|
20 |
+
learning_rate: 1.0e-06
|
21 |
+
local_rank: -1
|
22 |
+
logging_dir: logs
|
23 |
+
lr_scheduler: constant
|
24 |
+
lr_warmup_steps: 0
|
25 |
+
max_grad_norm: 1.0
|
26 |
+
max_train_samples: null
|
27 |
+
max_train_steps: 0
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 0
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: sdxl-flintstones_finetuning_4
|
33 |
+
prediction_type: null
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
35 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
36 |
+
proportion_empty_prompts: 0.0
|
37 |
+
push_to_hub: true
|
38 |
+
random_flip: false
|
39 |
+
report_to: tensorboard
|
40 |
+
resolution: 1024
|
41 |
+
resume_from_checkpoint: latest
|
42 |
+
revision: null
|
43 |
+
scale_lr: false
|
44 |
+
seed: null
|
45 |
+
snr_gamma: null
|
46 |
+
timestep_bias_begin: 0
|
47 |
+
timestep_bias_end: 1000
|
48 |
+
timestep_bias_multiplier: 1.0
|
49 |
+
timestep_bias_portion: 0.25
|
50 |
+
timestep_bias_strategy: none
|
51 |
+
train_batch_size: 1
|
52 |
+
train_data_dir: fake_dataset
|
53 |
+
use_8bit_adam: false
|
54 |
+
use_ema: false
|
55 |
+
validation_epochs: 1
|
56 |
+
validation_prompt: Fred is driving a car
|
logs/text2image-fine-tune-sdxl/1699565455.163503/events.out.tfevents.1699565455.4124gs01.2087089.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fff43a7720bdbc63ab51619ba59b066e6d5cb1cb5bd5cb0343fbdac896b43fbb
|
3 |
+
size 2783
|
logs/text2image-fine-tune-sdxl/1699565455.1653008/hparams.yml
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: true
|
9 |
+
checkpointing_steps: 2000
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: null
|
14 |
+
enable_xformers_memory_efficient_attention: true
|
15 |
+
gradient_accumulation_steps: 4
|
16 |
+
gradient_checkpointing: true
|
17 |
+
hub_model_id: null
|
18 |
+
hub_token: null
|
19 |
+
image_column: image
|
20 |
+
learning_rate: 1.0e-06
|
21 |
+
local_rank: -1
|
22 |
+
logging_dir: logs
|
23 |
+
lr_scheduler: constant
|
24 |
+
lr_warmup_steps: 0
|
25 |
+
max_grad_norm: 1.0
|
26 |
+
max_train_samples: null
|
27 |
+
max_train_steps: 0
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 0
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: sdxl-flintstones_finetuning_4
|
33 |
+
prediction_type: null
|
34 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
|
35 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
36 |
+
proportion_empty_prompts: 0.0
|
37 |
+
push_to_hub: true
|
38 |
+
random_flip: false
|
39 |
+
report_to: tensorboard
|
40 |
+
resolution: 1024
|
41 |
+
resume_from_checkpoint: checkpoint-10000
|
42 |
+
revision: null
|
43 |
+
scale_lr: false
|
44 |
+
seed: null
|
45 |
+
snr_gamma: null
|
46 |
+
timestep_bias_begin: 0
|
47 |
+
timestep_bias_end: 1000
|
48 |
+
timestep_bias_multiplier: 1.0
|
49 |
+
timestep_bias_portion: 0.25
|
50 |
+
timestep_bias_strategy: none
|
51 |
+
train_batch_size: 1
|
52 |
+
train_data_dir: fake_dataset
|
53 |
+
use_8bit_adam: false
|
54 |
+
use_ema: false
|
55 |
+
validation_epochs: 1
|
56 |
+
validation_prompt: Fred is driving a car
|
logs/text2image-fine-tune-sdxl/1699567973.1467016/events.out.tfevents.1699567973.4124gs01.2098631.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22413c9ac1d77ea2d9e63581accbaa11784999c587b9c3f5a216bf2179d654f4
|
3 |
+
size 2776
|
logs/text2image-fine-tune-sdxl/1699567973.149079/hparams.yml
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: true
|
9 |
+
checkpointing_steps: 2000
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: null
|
14 |
+
enable_xformers_memory_efficient_attention: true
|
15 |
+
gradient_accumulation_steps: 4
|
16 |
+
gradient_checkpointing: true
|
17 |
+
hub_model_id: null
|
18 |
+
hub_token: null
|
19 |
+
image_column: image
|
20 |
+
learning_rate: 1.0e-06
|
21 |
+
local_rank: -1
|
22 |
+
logging_dir: logs
|
23 |
+
lr_scheduler: constant
|
24 |
+
lr_warmup_steps: 0
|
25 |
+
max_grad_norm: 1.0
|
26 |
+
max_train_samples: null
|
27 |
+
max_train_steps: 0
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 0
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: sdxl-flintstones_finetuning_4
|
33 |
+
prediction_type: null
|
34 |
+
pretrained_model_name_or_path: juliajoanna/sdxl-one_hot_encoding
|
35 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
36 |
+
proportion_empty_prompts: 0.0
|
37 |
+
push_to_hub: true
|
38 |
+
random_flip: false
|
39 |
+
report_to: tensorboard
|
40 |
+
resolution: 1024
|
41 |
+
resume_from_checkpoint: checkpoint-12000
|
42 |
+
revision: null
|
43 |
+
scale_lr: false
|
44 |
+
seed: null
|
45 |
+
snr_gamma: null
|
46 |
+
timestep_bias_begin: 0
|
47 |
+
timestep_bias_end: 1000
|
48 |
+
timestep_bias_multiplier: 1.0
|
49 |
+
timestep_bias_portion: 0.25
|
50 |
+
timestep_bias_strategy: none
|
51 |
+
train_batch_size: 1
|
52 |
+
train_data_dir: fake_dataset
|
53 |
+
use_8bit_adam: false
|
54 |
+
use_ema: false
|
55 |
+
validation_epochs: 1
|
56 |
+
validation_prompt: Fred is driving a car
|
logs/text2image-fine-tune-sdxl/1699568176.5264077/events.out.tfevents.1699568176.4124gs01.2100196.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:168a91dd2a46eef1cc2056ebdf0c7ea873a05babfbfb177ab27bf26c48b41171
|
3 |
+
size 2776
|
logs/text2image-fine-tune-sdxl/1699568176.5279846/hparams.yml
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: true
|
9 |
+
checkpointing_steps: 2000
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: null
|
14 |
+
enable_xformers_memory_efficient_attention: true
|
15 |
+
gradient_accumulation_steps: 4
|
16 |
+
gradient_checkpointing: true
|
17 |
+
hub_model_id: null
|
18 |
+
hub_token: null
|
19 |
+
image_column: image
|
20 |
+
learning_rate: 1.0e-06
|
21 |
+
local_rank: -1
|
22 |
+
logging_dir: logs
|
23 |
+
lr_scheduler: constant
|
24 |
+
lr_warmup_steps: 0
|
25 |
+
max_grad_norm: 1.0
|
26 |
+
max_train_samples: null
|
27 |
+
max_train_steps: 0
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 0
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: sdxl-flintstones_finetuning_4
|
33 |
+
prediction_type: null
|
34 |
+
pretrained_model_name_or_path: juliajoanna/sdxl-one_hot_encoding
|
35 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
36 |
+
proportion_empty_prompts: 0.0
|
37 |
+
push_to_hub: true
|
38 |
+
random_flip: false
|
39 |
+
report_to: tensorboard
|
40 |
+
resolution: 1024
|
41 |
+
resume_from_checkpoint: checkpoint-12000
|
42 |
+
revision: null
|
43 |
+
scale_lr: false
|
44 |
+
seed: null
|
45 |
+
snr_gamma: null
|
46 |
+
timestep_bias_begin: 0
|
47 |
+
timestep_bias_end: 1000
|
48 |
+
timestep_bias_multiplier: 1.0
|
49 |
+
timestep_bias_portion: 0.25
|
50 |
+
timestep_bias_strategy: none
|
51 |
+
train_batch_size: 1
|
52 |
+
train_data_dir: fake_dataset
|
53 |
+
use_8bit_adam: false
|
54 |
+
use_ema: false
|
55 |
+
validation_epochs: 1
|
56 |
+
validation_prompt: Fred is driving a car
|
logs/text2image-fine-tune-sdxl/1699568465.8294842/events.out.tfevents.1699568465.4124gs01.2102710.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9123f11470021a8b9015f7605762597a34a1a0b43c274f3b681e3d2e514e9be
|
3 |
+
size 2776
|
logs/text2image-fine-tune-sdxl/1699568465.831263/hparams.yml
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
center_crop: true
|
9 |
+
checkpointing_steps: 2000
|
10 |
+
checkpoints_total_limit: null
|
11 |
+
dataloader_num_workers: 0
|
12 |
+
dataset_config_name: null
|
13 |
+
dataset_name: null
|
14 |
+
enable_xformers_memory_efficient_attention: true
|
15 |
+
gradient_accumulation_steps: 4
|
16 |
+
gradient_checkpointing: true
|
17 |
+
hub_model_id: null
|
18 |
+
hub_token: null
|
19 |
+
image_column: image
|
20 |
+
learning_rate: 1.0e-06
|
21 |
+
local_rank: -1
|
22 |
+
logging_dir: logs
|
23 |
+
lr_scheduler: constant
|
24 |
+
lr_warmup_steps: 0
|
25 |
+
max_grad_norm: 1.0
|
26 |
+
max_train_samples: null
|
27 |
+
max_train_steps: 0
|
28 |
+
mixed_precision: null
|
29 |
+
noise_offset: 0
|
30 |
+
num_train_epochs: 0
|
31 |
+
num_validation_images: 4
|
32 |
+
output_dir: sdxl-flintstones_finetuning_4
|
33 |
+
prediction_type: null
|
34 |
+
pretrained_model_name_or_path: juliajoanna/sdxl-one_hot_encoding
|
35 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
36 |
+
proportion_empty_prompts: 0.0
|
37 |
+
push_to_hub: true
|
38 |
+
random_flip: false
|
39 |
+
report_to: tensorboard
|
40 |
+
resolution: 1024
|
41 |
+
resume_from_checkpoint: checkpoint-12000
|
42 |
+
revision: null
|
43 |
+
scale_lr: false
|
44 |
+
seed: null
|
45 |
+
snr_gamma: null
|
46 |
+
timestep_bias_begin: 0
|
47 |
+
timestep_bias_end: 1000
|
48 |
+
timestep_bias_multiplier: 1.0
|
49 |
+
timestep_bias_portion: 0.25
|
50 |
+
timestep_bias_strategy: none
|
51 |
+
train_batch_size: 1
|
52 |
+
train_data_dir: fake_dataset
|
53 |
+
use_8bit_adam: false
|
54 |
+
use_ema: false
|
55 |
+
validation_epochs: 1
|
56 |
+
validation_prompt: Fred is driving a car
|
logs/text2image-fine-tune-sdxl/1699568662.2018025/events.out.tfevents.1699568662.4124gs01.2103894.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fa4a37b5f549b77c5a394538139d15d7ac2a311ebd74bade1f2e1136208afb5
|
3 |
+
size 2776
|