williamberman
commited on
Commit
•
5b91a01
1
Parent(s):
5562d30
init
Browse files- checkpoint-1500/optimizer.bin +3 -0
- checkpoint-1500/random_states_0.pkl +3 -0
- checkpoint-1500/scheduler.bin +3 -0
- checkpoint-1500/text_encoder_lora_layers.bin +3 -0
- checkpoint-1500/unet/config.json +71 -0
- checkpoint-1500/unet/diffusion_pytorch_model.bin +3 -0
- checkpoint-2000/optimizer.bin +3 -0
- checkpoint-2000/random_states_0.pkl +3 -0
- checkpoint-2000/scheduler.bin +3 -0
- checkpoint-2000/text_encoder_lora_layers.bin +3 -0
- checkpoint-2000/unet/config.json +71 -0
- checkpoint-2000/unet/diffusion_pytorch_model.bin +3 -0
- text_encoder_lora_layers.bin +3 -0
- unet/config.json +71 -0
- unet/diffusion_pytorch_model.bin +3 -0
checkpoint-1500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46a832251277680c4d858d49f18376606c22b83d384a07cc917bd75c9016a147
|
3 |
+
size 2500908293
|
checkpoint-1500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:614b70acaba3a2bc49e5dc7d5ede073bae391da7d00d31aa92420ee6eaf86073
|
3 |
+
size 14663
|
checkpoint-1500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3ec4051663ac3d7a7d8a2e2bd9a3a36fe0f96e7a3ac2e0a1cf0ab87b79009c0
|
3 |
+
size 563
|
checkpoint-1500/text_encoder_lora_layers.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38515d1f15629a123281199b2757c61b88505f85885f78eab974d27b38838bb5
|
3 |
+
size 9491283
|
checkpoint-1500/unet/config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.18.0.dev0",
|
4 |
+
"_name_or_path": "DeepFloyd/IF-II-L-v1.0",
|
5 |
+
"act_fn": "gelu",
|
6 |
+
"addition_embed_type": "text",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": 64,
|
9 |
+
"block_out_channels": [
|
10 |
+
160,
|
11 |
+
320,
|
12 |
+
640,
|
13 |
+
960,
|
14 |
+
1280
|
15 |
+
],
|
16 |
+
"center_input_sample": false,
|
17 |
+
"class_embed_type": "timestep",
|
18 |
+
"class_embeddings_concat": false,
|
19 |
+
"conv_in_kernel": 3,
|
20 |
+
"conv_out_kernel": 3,
|
21 |
+
"cross_attention_dim": 1280,
|
22 |
+
"cross_attention_norm": "group_norm",
|
23 |
+
"down_block_types": [
|
24 |
+
"ResnetDownsampleBlock2D",
|
25 |
+
"ResnetDownsampleBlock2D",
|
26 |
+
"ResnetDownsampleBlock2D",
|
27 |
+
"SimpleCrossAttnDownBlock2D",
|
28 |
+
"SimpleCrossAttnDownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": 4096,
|
33 |
+
"encoder_hid_dim_type": "text_proj",
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 6,
|
37 |
+
"layers_per_block": [
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
3,
|
41 |
+
5,
|
42 |
+
5
|
43 |
+
],
|
44 |
+
"mid_block_only_cross_attention": null,
|
45 |
+
"mid_block_scale_factor": 1.4142271248762552,
|
46 |
+
"mid_block_type": "UNetMidBlock2DSimpleCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_class_embeds": null,
|
50 |
+
"only_cross_attention": false,
|
51 |
+
"out_channels": 6,
|
52 |
+
"projection_class_embeddings_input_dim": null,
|
53 |
+
"resnet_out_scale_factor": 1.4142271248762552,
|
54 |
+
"resnet_skip_time_act": true,
|
55 |
+
"resnet_time_scale_shift": "scale_shift",
|
56 |
+
"sample_size": 256,
|
57 |
+
"time_cond_proj_dim": null,
|
58 |
+
"time_embedding_act_fn": "gelu",
|
59 |
+
"time_embedding_dim": 1280,
|
60 |
+
"time_embedding_type": "positional",
|
61 |
+
"timestep_post_act": null,
|
62 |
+
"up_block_types": [
|
63 |
+
"SimpleCrossAttnUpBlock2D",
|
64 |
+
"SimpleCrossAttnUpBlock2D",
|
65 |
+
"ResnetUpsampleBlock2D",
|
66 |
+
"ResnetUpsampleBlock2D",
|
67 |
+
"ResnetUpsampleBlock2D"
|
68 |
+
],
|
69 |
+
"upcast_attention": false,
|
70 |
+
"use_linear_projection": false
|
71 |
+
}
|
checkpoint-1500/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c238d047d279769fa032aec0088326a0f0e9ad41b4dfacd11043511b3f1ec946
|
3 |
+
size 4973475331
|
checkpoint-2000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ef1c6b9339bb68857e300e3e086e0196890406db3d9acf24e36154e7491d4e8
|
3 |
+
size 2500908293
|
checkpoint-2000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5a7e92b3ef00239a6ba396d42f5644170405ad589ad093e6fc7188cae465d64
|
3 |
+
size 14663
|
checkpoint-2000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3f59dbf4ffd4f0f8df22b4c9370ea2ace9ad3479a29b1f7e7f5141bb0e1ce6c
|
3 |
+
size 563
|
checkpoint-2000/text_encoder_lora_layers.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2932f0a0019befc8b090977c37eeee363ce66a12f6639d57b09d5b5677f1be26
|
3 |
+
size 9491283
|
checkpoint-2000/unet/config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.18.0.dev0",
|
4 |
+
"_name_or_path": "DeepFloyd/IF-II-L-v1.0",
|
5 |
+
"act_fn": "gelu",
|
6 |
+
"addition_embed_type": "text",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": 64,
|
9 |
+
"block_out_channels": [
|
10 |
+
160,
|
11 |
+
320,
|
12 |
+
640,
|
13 |
+
960,
|
14 |
+
1280
|
15 |
+
],
|
16 |
+
"center_input_sample": false,
|
17 |
+
"class_embed_type": "timestep",
|
18 |
+
"class_embeddings_concat": false,
|
19 |
+
"conv_in_kernel": 3,
|
20 |
+
"conv_out_kernel": 3,
|
21 |
+
"cross_attention_dim": 1280,
|
22 |
+
"cross_attention_norm": "group_norm",
|
23 |
+
"down_block_types": [
|
24 |
+
"ResnetDownsampleBlock2D",
|
25 |
+
"ResnetDownsampleBlock2D",
|
26 |
+
"ResnetDownsampleBlock2D",
|
27 |
+
"SimpleCrossAttnDownBlock2D",
|
28 |
+
"SimpleCrossAttnDownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": 4096,
|
33 |
+
"encoder_hid_dim_type": "text_proj",
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 6,
|
37 |
+
"layers_per_block": [
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
3,
|
41 |
+
5,
|
42 |
+
5
|
43 |
+
],
|
44 |
+
"mid_block_only_cross_attention": null,
|
45 |
+
"mid_block_scale_factor": 1.4142271248762552,
|
46 |
+
"mid_block_type": "UNetMidBlock2DSimpleCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_class_embeds": null,
|
50 |
+
"only_cross_attention": false,
|
51 |
+
"out_channels": 6,
|
52 |
+
"projection_class_embeddings_input_dim": null,
|
53 |
+
"resnet_out_scale_factor": 1.4142271248762552,
|
54 |
+
"resnet_skip_time_act": true,
|
55 |
+
"resnet_time_scale_shift": "scale_shift",
|
56 |
+
"sample_size": 256,
|
57 |
+
"time_cond_proj_dim": null,
|
58 |
+
"time_embedding_act_fn": "gelu",
|
59 |
+
"time_embedding_dim": 1280,
|
60 |
+
"time_embedding_type": "positional",
|
61 |
+
"timestep_post_act": null,
|
62 |
+
"up_block_types": [
|
63 |
+
"SimpleCrossAttnUpBlock2D",
|
64 |
+
"SimpleCrossAttnUpBlock2D",
|
65 |
+
"ResnetUpsampleBlock2D",
|
66 |
+
"ResnetUpsampleBlock2D",
|
67 |
+
"ResnetUpsampleBlock2D"
|
68 |
+
],
|
69 |
+
"upcast_attention": false,
|
70 |
+
"use_linear_projection": false
|
71 |
+
}
|
checkpoint-2000/unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c78820eb0b522841a9a8017ce65cf2f91c86e13a30a62d701b0773bb94583c9a
|
3 |
+
size 4973475331
|
text_encoder_lora_layers.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2932f0a0019befc8b090977c37eeee363ce66a12f6639d57b09d5b5677f1be26
|
3 |
+
size 9491283
|
unet/config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.18.0.dev0",
|
4 |
+
"_name_or_path": "DeepFloyd/IF-II-L-v1.0",
|
5 |
+
"act_fn": "gelu",
|
6 |
+
"addition_embed_type": "text",
|
7 |
+
"addition_embed_type_num_heads": 64,
|
8 |
+
"attention_head_dim": 64,
|
9 |
+
"block_out_channels": [
|
10 |
+
160,
|
11 |
+
320,
|
12 |
+
640,
|
13 |
+
960,
|
14 |
+
1280
|
15 |
+
],
|
16 |
+
"center_input_sample": false,
|
17 |
+
"class_embed_type": "timestep",
|
18 |
+
"class_embeddings_concat": false,
|
19 |
+
"conv_in_kernel": 3,
|
20 |
+
"conv_out_kernel": 3,
|
21 |
+
"cross_attention_dim": 1280,
|
22 |
+
"cross_attention_norm": "group_norm",
|
23 |
+
"down_block_types": [
|
24 |
+
"ResnetDownsampleBlock2D",
|
25 |
+
"ResnetDownsampleBlock2D",
|
26 |
+
"ResnetDownsampleBlock2D",
|
27 |
+
"SimpleCrossAttnDownBlock2D",
|
28 |
+
"SimpleCrossAttnDownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dual_cross_attention": false,
|
32 |
+
"encoder_hid_dim": 4096,
|
33 |
+
"encoder_hid_dim_type": "text_proj",
|
34 |
+
"flip_sin_to_cos": true,
|
35 |
+
"freq_shift": 0,
|
36 |
+
"in_channels": 6,
|
37 |
+
"layers_per_block": [
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
3,
|
41 |
+
5,
|
42 |
+
5
|
43 |
+
],
|
44 |
+
"mid_block_only_cross_attention": null,
|
45 |
+
"mid_block_scale_factor": 1.4142271248762552,
|
46 |
+
"mid_block_type": "UNetMidBlock2DSimpleCrossAttn",
|
47 |
+
"norm_eps": 1e-05,
|
48 |
+
"norm_num_groups": 32,
|
49 |
+
"num_class_embeds": null,
|
50 |
+
"only_cross_attention": false,
|
51 |
+
"out_channels": 6,
|
52 |
+
"projection_class_embeddings_input_dim": null,
|
53 |
+
"resnet_out_scale_factor": 1.4142271248762552,
|
54 |
+
"resnet_skip_time_act": true,
|
55 |
+
"resnet_time_scale_shift": "scale_shift",
|
56 |
+
"sample_size": 256,
|
57 |
+
"time_cond_proj_dim": null,
|
58 |
+
"time_embedding_act_fn": "gelu",
|
59 |
+
"time_embedding_dim": 1280,
|
60 |
+
"time_embedding_type": "positional",
|
61 |
+
"timestep_post_act": null,
|
62 |
+
"up_block_types": [
|
63 |
+
"SimpleCrossAttnUpBlock2D",
|
64 |
+
"SimpleCrossAttnUpBlock2D",
|
65 |
+
"ResnetUpsampleBlock2D",
|
66 |
+
"ResnetUpsampleBlock2D",
|
67 |
+
"ResnetUpsampleBlock2D"
|
68 |
+
],
|
69 |
+
"upcast_attention": false,
|
70 |
+
"use_linear_projection": false
|
71 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c78820eb0b522841a9a8017ce65cf2f91c86e13a30a62d701b0773bb94583c9a
|
3 |
+
size 4973475331
|