Upload 24 files
Browse files- Base11/Canny.safetensors +3 -0
- Base11/Canny.yaml +79 -0
- Base11/Depth.safetensors +3 -0
- Base11/Depth.yaml +79 -0
- Base11/Inpaint.safetensors +3 -0
- Base11/Inpaint.yaml +79 -0
- Base11/Lineart-anime.safetensors +3 -0
- Base11/Lineart-anime.yaml +79 -0
- Base11/Lineart.safetensors +3 -0
- Base11/Lineart.yaml +79 -0
- Base11/Mlsd.safetensors +3 -0
- Base11/Mlsd.yaml +79 -0
- Base11/Normalbae.safetensors +3 -0
- Base11/Normalbae.yaml +79 -0
- Base11/Openpose.safetensors +3 -0
- Base11/Openpose.yaml +79 -0
- Base11/Scribble.safetensors +3 -0
- Base11/Scribble.yaml +79 -0
- Base11/Seg.safetensors +3 -0
- Base11/Seg.yaml +79 -0
- Base11/T2-color.pth +3 -0
- Base11/T2-color.yaml +6 -0
- Base11/T2-style.pth +3 -0
- Base11/T2-style.yaml +8 -0
Base11/Canny.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8932b66e15aae835b3490dbf989f56c253104cee08a88bf21283762f557c9f10
|
3 |
+
size 722601100
|
Base11/Canny.yaml
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: cldm.cldm.ControlLDM
|
3 |
+
params:
|
4 |
+
linear_start: 0.00085
|
5 |
+
linear_end: 0.0120
|
6 |
+
num_timesteps_cond: 1
|
7 |
+
log_every_t: 200
|
8 |
+
timesteps: 1000
|
9 |
+
first_stage_key: "jpg"
|
10 |
+
cond_stage_key: "txt"
|
11 |
+
control_key: "hint"
|
12 |
+
image_size: 64
|
13 |
+
channels: 4
|
14 |
+
cond_stage_trainable: false
|
15 |
+
conditioning_key: crossattn
|
16 |
+
monitor: val/loss_simple_ema
|
17 |
+
scale_factor: 0.18215
|
18 |
+
use_ema: False
|
19 |
+
only_mid_control: False
|
20 |
+
|
21 |
+
control_stage_config:
|
22 |
+
target: cldm.cldm.ControlNet
|
23 |
+
params:
|
24 |
+
image_size: 32 # unused
|
25 |
+
in_channels: 4
|
26 |
+
hint_channels: 3
|
27 |
+
model_channels: 320
|
28 |
+
attention_resolutions: [ 4, 2, 1 ]
|
29 |
+
num_res_blocks: 2
|
30 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
31 |
+
num_heads: 8
|
32 |
+
use_spatial_transformer: True
|
33 |
+
transformer_depth: 1
|
34 |
+
context_dim: 768
|
35 |
+
use_checkpoint: True
|
36 |
+
legacy: False
|
37 |
+
|
38 |
+
unet_config:
|
39 |
+
target: cldm.cldm.ControlledUnetModel
|
40 |
+
params:
|
41 |
+
image_size: 32 # unused
|
42 |
+
in_channels: 4
|
43 |
+
out_channels: 4
|
44 |
+
model_channels: 320
|
45 |
+
attention_resolutions: [ 4, 2, 1 ]
|
46 |
+
num_res_blocks: 2
|
47 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
48 |
+
num_heads: 8
|
49 |
+
use_spatial_transformer: True
|
50 |
+
transformer_depth: 1
|
51 |
+
context_dim: 768
|
52 |
+
use_checkpoint: True
|
53 |
+
legacy: False
|
54 |
+
|
55 |
+
first_stage_config:
|
56 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
57 |
+
params:
|
58 |
+
embed_dim: 4
|
59 |
+
monitor: val/rec_loss
|
60 |
+
ddconfig:
|
61 |
+
double_z: true
|
62 |
+
z_channels: 4
|
63 |
+
resolution: 256
|
64 |
+
in_channels: 3
|
65 |
+
out_ch: 3
|
66 |
+
ch: 128
|
67 |
+
ch_mult:
|
68 |
+
- 1
|
69 |
+
- 2
|
70 |
+
- 4
|
71 |
+
- 4
|
72 |
+
num_res_blocks: 2
|
73 |
+
attn_resolutions: []
|
74 |
+
dropout: 0.0
|
75 |
+
lossconfig:
|
76 |
+
target: torch.nn.Identity
|
77 |
+
|
78 |
+
cond_stage_config:
|
79 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
Base11/Depth.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bab8043519c0f563853459c1e4f4e93445a87cef1dcdfa3e1e70115b3c83553
|
3 |
+
size 722601100
|
Base11/Depth.yaml
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: cldm.cldm.ControlLDM
|
3 |
+
params:
|
4 |
+
linear_start: 0.00085
|
5 |
+
linear_end: 0.0120
|
6 |
+
num_timesteps_cond: 1
|
7 |
+
log_every_t: 200
|
8 |
+
timesteps: 1000
|
9 |
+
first_stage_key: "jpg"
|
10 |
+
cond_stage_key: "txt"
|
11 |
+
control_key: "hint"
|
12 |
+
image_size: 64
|
13 |
+
channels: 4
|
14 |
+
cond_stage_trainable: false
|
15 |
+
conditioning_key: crossattn
|
16 |
+
monitor: val/loss_simple_ema
|
17 |
+
scale_factor: 0.18215
|
18 |
+
use_ema: False
|
19 |
+
only_mid_control: False
|
20 |
+
|
21 |
+
control_stage_config:
|
22 |
+
target: cldm.cldm.ControlNet
|
23 |
+
params:
|
24 |
+
image_size: 32 # unused
|
25 |
+
in_channels: 4
|
26 |
+
hint_channels: 3
|
27 |
+
model_channels: 320
|
28 |
+
attention_resolutions: [ 4, 2, 1 ]
|
29 |
+
num_res_blocks: 2
|
30 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
31 |
+
num_heads: 8
|
32 |
+
use_spatial_transformer: True
|
33 |
+
transformer_depth: 1
|
34 |
+
context_dim: 768
|
35 |
+
use_checkpoint: True
|
36 |
+
legacy: False
|
37 |
+
|
38 |
+
unet_config:
|
39 |
+
target: cldm.cldm.ControlledUnetModel
|
40 |
+
params:
|
41 |
+
image_size: 32 # unused
|
42 |
+
in_channels: 4
|
43 |
+
out_channels: 4
|
44 |
+
model_channels: 320
|
45 |
+
attention_resolutions: [ 4, 2, 1 ]
|
46 |
+
num_res_blocks: 2
|
47 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
48 |
+
num_heads: 8
|
49 |
+
use_spatial_transformer: True
|
50 |
+
transformer_depth: 1
|
51 |
+
context_dim: 768
|
52 |
+
use_checkpoint: True
|
53 |
+
legacy: False
|
54 |
+
|
55 |
+
first_stage_config:
|
56 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
57 |
+
params:
|
58 |
+
embed_dim: 4
|
59 |
+
monitor: val/rec_loss
|
60 |
+
ddconfig:
|
61 |
+
double_z: true
|
62 |
+
z_channels: 4
|
63 |
+
resolution: 256
|
64 |
+
in_channels: 3
|
65 |
+
out_ch: 3
|
66 |
+
ch: 128
|
67 |
+
ch_mult:
|
68 |
+
- 1
|
69 |
+
- 2
|
70 |
+
- 4
|
71 |
+
- 4
|
72 |
+
num_res_blocks: 2
|
73 |
+
attn_resolutions: []
|
74 |
+
dropout: 0.0
|
75 |
+
lossconfig:
|
76 |
+
target: torch.nn.Identity
|
77 |
+
|
78 |
+
cond_stage_config:
|
79 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
Base11/Inpaint.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:677a4fe351edecd40cd0d7cc210a8686b59d4e55207317f12319ef746a7a5a89
|
3 |
+
size 722601100
|
Base11/Inpaint.yaml
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: cldm.cldm.ControlLDM
|
3 |
+
params:
|
4 |
+
linear_start: 0.00085
|
5 |
+
linear_end: 0.0120
|
6 |
+
num_timesteps_cond: 1
|
7 |
+
log_every_t: 200
|
8 |
+
timesteps: 1000
|
9 |
+
first_stage_key: "jpg"
|
10 |
+
cond_stage_key: "txt"
|
11 |
+
control_key: "hint"
|
12 |
+
image_size: 64
|
13 |
+
channels: 4
|
14 |
+
cond_stage_trainable: false
|
15 |
+
conditioning_key: crossattn
|
16 |
+
monitor: val/loss_simple_ema
|
17 |
+
scale_factor: 0.18215
|
18 |
+
use_ema: False
|
19 |
+
only_mid_control: False
|
20 |
+
|
21 |
+
control_stage_config:
|
22 |
+
target: cldm.cldm.ControlNet
|
23 |
+
params:
|
24 |
+
image_size: 32 # unused
|
25 |
+
in_channels: 4
|
26 |
+
hint_channels: 3
|
27 |
+
model_channels: 320
|
28 |
+
attention_resolutions: [ 4, 2, 1 ]
|
29 |
+
num_res_blocks: 2
|
30 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
31 |
+
num_heads: 8
|
32 |
+
use_spatial_transformer: True
|
33 |
+
transformer_depth: 1
|
34 |
+
context_dim: 768
|
35 |
+
use_checkpoint: True
|
36 |
+
legacy: False
|
37 |
+
|
38 |
+
unet_config:
|
39 |
+
target: cldm.cldm.ControlledUnetModel
|
40 |
+
params:
|
41 |
+
image_size: 32 # unused
|
42 |
+
in_channels: 4
|
43 |
+
out_channels: 4
|
44 |
+
model_channels: 320
|
45 |
+
attention_resolutions: [ 4, 2, 1 ]
|
46 |
+
num_res_blocks: 2
|
47 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
48 |
+
num_heads: 8
|
49 |
+
use_spatial_transformer: True
|
50 |
+
transformer_depth: 1
|
51 |
+
context_dim: 768
|
52 |
+
use_checkpoint: True
|
53 |
+
legacy: False
|
54 |
+
|
55 |
+
first_stage_config:
|
56 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
57 |
+
params:
|
58 |
+
embed_dim: 4
|
59 |
+
monitor: val/rec_loss
|
60 |
+
ddconfig:
|
61 |
+
double_z: true
|
62 |
+
z_channels: 4
|
63 |
+
resolution: 256
|
64 |
+
in_channels: 3
|
65 |
+
out_ch: 3
|
66 |
+
ch: 128
|
67 |
+
ch_mult:
|
68 |
+
- 1
|
69 |
+
- 2
|
70 |
+
- 4
|
71 |
+
- 4
|
72 |
+
num_res_blocks: 2
|
73 |
+
attn_resolutions: []
|
74 |
+
dropout: 0.0
|
75 |
+
lossconfig:
|
76 |
+
target: torch.nn.Identity
|
77 |
+
|
78 |
+
cond_stage_config:
|
79 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
Base11/Lineart-anime.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:067bf845109afdd1049bd9553d44faed1ad53691bd6b5ac9ee31c87466ef7c27
|
3 |
+
size 722601100
|
Base11/Lineart-anime.yaml
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: cldm.cldm.ControlLDM
|
3 |
+
params:
|
4 |
+
linear_start: 0.00085
|
5 |
+
linear_end: 0.0120
|
6 |
+
num_timesteps_cond: 1
|
7 |
+
log_every_t: 200
|
8 |
+
timesteps: 1000
|
9 |
+
first_stage_key: "jpg"
|
10 |
+
cond_stage_key: "txt"
|
11 |
+
control_key: "hint"
|
12 |
+
image_size: 64
|
13 |
+
channels: 4
|
14 |
+
cond_stage_trainable: false
|
15 |
+
conditioning_key: crossattn
|
16 |
+
monitor: val/loss_simple_ema
|
17 |
+
scale_factor: 0.18215
|
18 |
+
use_ema: False
|
19 |
+
only_mid_control: False
|
20 |
+
|
21 |
+
control_stage_config:
|
22 |
+
target: cldm.cldm.ControlNet
|
23 |
+
params:
|
24 |
+
image_size: 32 # unused
|
25 |
+
in_channels: 4
|
26 |
+
hint_channels: 3
|
27 |
+
model_channels: 320
|
28 |
+
attention_resolutions: [ 4, 2, 1 ]
|
29 |
+
num_res_blocks: 2
|
30 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
31 |
+
num_heads: 8
|
32 |
+
use_spatial_transformer: True
|
33 |
+
transformer_depth: 1
|
34 |
+
context_dim: 768
|
35 |
+
use_checkpoint: True
|
36 |
+
legacy: False
|
37 |
+
|
38 |
+
unet_config:
|
39 |
+
target: cldm.cldm.ControlledUnetModel
|
40 |
+
params:
|
41 |
+
image_size: 32 # unused
|
42 |
+
in_channels: 4
|
43 |
+
out_channels: 4
|
44 |
+
model_channels: 320
|
45 |
+
attention_resolutions: [ 4, 2, 1 ]
|
46 |
+
num_res_blocks: 2
|
47 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
48 |
+
num_heads: 8
|
49 |
+
use_spatial_transformer: True
|
50 |
+
transformer_depth: 1
|
51 |
+
context_dim: 768
|
52 |
+
use_checkpoint: True
|
53 |
+
legacy: False
|
54 |
+
|
55 |
+
first_stage_config:
|
56 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
57 |
+
params:
|
58 |
+
embed_dim: 4
|
59 |
+
monitor: val/rec_loss
|
60 |
+
ddconfig:
|
61 |
+
double_z: true
|
62 |
+
z_channels: 4
|
63 |
+
resolution: 256
|
64 |
+
in_channels: 3
|
65 |
+
out_ch: 3
|
66 |
+
ch: 128
|
67 |
+
ch_mult:
|
68 |
+
- 1
|
69 |
+
- 2
|
70 |
+
- 4
|
71 |
+
- 4
|
72 |
+
num_res_blocks: 2
|
73 |
+
attn_resolutions: []
|
74 |
+
dropout: 0.0
|
75 |
+
lossconfig:
|
76 |
+
target: torch.nn.Identity
|
77 |
+
|
78 |
+
cond_stage_config:
|
79 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
Base11/Lineart.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10559106d1bb8196298b7a81565ede9279295d2b2df15165b9dbe189994def56
|
3 |
+
size 722601100
|
Base11/Lineart.yaml
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: cldm.cldm.ControlLDM
|
3 |
+
params:
|
4 |
+
linear_start: 0.00085
|
5 |
+
linear_end: 0.0120
|
6 |
+
num_timesteps_cond: 1
|
7 |
+
log_every_t: 200
|
8 |
+
timesteps: 1000
|
9 |
+
first_stage_key: "jpg"
|
10 |
+
cond_stage_key: "txt"
|
11 |
+
control_key: "hint"
|
12 |
+
image_size: 64
|
13 |
+
channels: 4
|
14 |
+
cond_stage_trainable: false
|
15 |
+
conditioning_key: crossattn
|
16 |
+
monitor: val/loss_simple_ema
|
17 |
+
scale_factor: 0.18215
|
18 |
+
use_ema: False
|
19 |
+
only_mid_control: False
|
20 |
+
|
21 |
+
control_stage_config:
|
22 |
+
target: cldm.cldm.ControlNet
|
23 |
+
params:
|
24 |
+
image_size: 32 # unused
|
25 |
+
in_channels: 4
|
26 |
+
hint_channels: 3
|
27 |
+
model_channels: 320
|
28 |
+
attention_resolutions: [ 4, 2, 1 ]
|
29 |
+
num_res_blocks: 2
|
30 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
31 |
+
num_heads: 8
|
32 |
+
use_spatial_transformer: True
|
33 |
+
transformer_depth: 1
|
34 |
+
context_dim: 768
|
35 |
+
use_checkpoint: True
|
36 |
+
legacy: False
|
37 |
+
|
38 |
+
unet_config:
|
39 |
+
target: cldm.cldm.ControlledUnetModel
|
40 |
+
params:
|
41 |
+
image_size: 32 # unused
|
42 |
+
in_channels: 4
|
43 |
+
out_channels: 4
|
44 |
+
model_channels: 320
|
45 |
+
attention_resolutions: [ 4, 2, 1 ]
|
46 |
+
num_res_blocks: 2
|
47 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
48 |
+
num_heads: 8
|
49 |
+
use_spatial_transformer: True
|
50 |
+
transformer_depth: 1
|
51 |
+
context_dim: 768
|
52 |
+
use_checkpoint: True
|
53 |
+
legacy: False
|
54 |
+
|
55 |
+
first_stage_config:
|
56 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
57 |
+
params:
|
58 |
+
embed_dim: 4
|
59 |
+
monitor: val/rec_loss
|
60 |
+
ddconfig:
|
61 |
+
double_z: true
|
62 |
+
z_channels: 4
|
63 |
+
resolution: 256
|
64 |
+
in_channels: 3
|
65 |
+
out_ch: 3
|
66 |
+
ch: 128
|
67 |
+
ch_mult:
|
68 |
+
- 1
|
69 |
+
- 2
|
70 |
+
- 4
|
71 |
+
- 4
|
72 |
+
num_res_blocks: 2
|
73 |
+
attn_resolutions: []
|
74 |
+
dropout: 0.0
|
75 |
+
lossconfig:
|
76 |
+
target: torch.nn.Identity
|
77 |
+
|
78 |
+
cond_stage_config:
|
79 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
Base11/Mlsd.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d689682fcc9341581b788524ab813cda789acdbc16bdbecbd1b9d2221e119b7
|
3 |
+
size 722601100
|
Base11/Mlsd.yaml
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: cldm.cldm.ControlLDM
|
3 |
+
params:
|
4 |
+
linear_start: 0.00085
|
5 |
+
linear_end: 0.0120
|
6 |
+
num_timesteps_cond: 1
|
7 |
+
log_every_t: 200
|
8 |
+
timesteps: 1000
|
9 |
+
first_stage_key: "jpg"
|
10 |
+
cond_stage_key: "txt"
|
11 |
+
control_key: "hint"
|
12 |
+
image_size: 64
|
13 |
+
channels: 4
|
14 |
+
cond_stage_trainable: false
|
15 |
+
conditioning_key: crossattn
|
16 |
+
monitor: val/loss_simple_ema
|
17 |
+
scale_factor: 0.18215
|
18 |
+
use_ema: False
|
19 |
+
only_mid_control: False
|
20 |
+
|
21 |
+
control_stage_config:
|
22 |
+
target: cldm.cldm.ControlNet
|
23 |
+
params:
|
24 |
+
image_size: 32 # unused
|
25 |
+
in_channels: 4
|
26 |
+
hint_channels: 3
|
27 |
+
model_channels: 320
|
28 |
+
attention_resolutions: [ 4, 2, 1 ]
|
29 |
+
num_res_blocks: 2
|
30 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
31 |
+
num_heads: 8
|
32 |
+
use_spatial_transformer: True
|
33 |
+
transformer_depth: 1
|
34 |
+
context_dim: 768
|
35 |
+
use_checkpoint: True
|
36 |
+
legacy: False
|
37 |
+
|
38 |
+
unet_config:
|
39 |
+
target: cldm.cldm.ControlledUnetModel
|
40 |
+
params:
|
41 |
+
image_size: 32 # unused
|
42 |
+
in_channels: 4
|
43 |
+
out_channels: 4
|
44 |
+
model_channels: 320
|
45 |
+
attention_resolutions: [ 4, 2, 1 ]
|
46 |
+
num_res_blocks: 2
|
47 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
48 |
+
num_heads: 8
|
49 |
+
use_spatial_transformer: True
|
50 |
+
transformer_depth: 1
|
51 |
+
context_dim: 768
|
52 |
+
use_checkpoint: True
|
53 |
+
legacy: False
|
54 |
+
|
55 |
+
first_stage_config:
|
56 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
57 |
+
params:
|
58 |
+
embed_dim: 4
|
59 |
+
monitor: val/rec_loss
|
60 |
+
ddconfig:
|
61 |
+
double_z: true
|
62 |
+
z_channels: 4
|
63 |
+
resolution: 256
|
64 |
+
in_channels: 3
|
65 |
+
out_ch: 3
|
66 |
+
ch: 128
|
67 |
+
ch_mult:
|
68 |
+
- 1
|
69 |
+
- 2
|
70 |
+
- 4
|
71 |
+
- 4
|
72 |
+
num_res_blocks: 2
|
73 |
+
attn_resolutions: []
|
74 |
+
dropout: 0.0
|
75 |
+
lossconfig:
|
76 |
+
target: torch.nn.Identity
|
77 |
+
|
78 |
+
cond_stage_config:
|
79 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
Base11/Normalbae.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79864bfc3a1df58ed35bd92fc8dd1e4d7b85cac424cc427b9049ddc7647cceec
|
3 |
+
size 722601100
|
Base11/Normalbae.yaml
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: cldm.cldm.ControlLDM
|
3 |
+
params:
|
4 |
+
linear_start: 0.00085
|
5 |
+
linear_end: 0.0120
|
6 |
+
num_timesteps_cond: 1
|
7 |
+
log_every_t: 200
|
8 |
+
timesteps: 1000
|
9 |
+
first_stage_key: "jpg"
|
10 |
+
cond_stage_key: "txt"
|
11 |
+
control_key: "hint"
|
12 |
+
image_size: 64
|
13 |
+
channels: 4
|
14 |
+
cond_stage_trainable: false
|
15 |
+
conditioning_key: crossattn
|
16 |
+
monitor: val/loss_simple_ema
|
17 |
+
scale_factor: 0.18215
|
18 |
+
use_ema: False
|
19 |
+
only_mid_control: False
|
20 |
+
|
21 |
+
control_stage_config:
|
22 |
+
target: cldm.cldm.ControlNet
|
23 |
+
params:
|
24 |
+
image_size: 32 # unused
|
25 |
+
in_channels: 4
|
26 |
+
hint_channels: 3
|
27 |
+
model_channels: 320
|
28 |
+
attention_resolutions: [ 4, 2, 1 ]
|
29 |
+
num_res_blocks: 2
|
30 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
31 |
+
num_heads: 8
|
32 |
+
use_spatial_transformer: True
|
33 |
+
transformer_depth: 1
|
34 |
+
context_dim: 768
|
35 |
+
use_checkpoint: True
|
36 |
+
legacy: False
|
37 |
+
|
38 |
+
unet_config:
|
39 |
+
target: cldm.cldm.ControlledUnetModel
|
40 |
+
params:
|
41 |
+
image_size: 32 # unused
|
42 |
+
in_channels: 4
|
43 |
+
out_channels: 4
|
44 |
+
model_channels: 320
|
45 |
+
attention_resolutions: [ 4, 2, 1 ]
|
46 |
+
num_res_blocks: 2
|
47 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
48 |
+
num_heads: 8
|
49 |
+
use_spatial_transformer: True
|
50 |
+
transformer_depth: 1
|
51 |
+
context_dim: 768
|
52 |
+
use_checkpoint: True
|
53 |
+
legacy: False
|
54 |
+
|
55 |
+
first_stage_config:
|
56 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
57 |
+
params:
|
58 |
+
embed_dim: 4
|
59 |
+
monitor: val/rec_loss
|
60 |
+
ddconfig:
|
61 |
+
double_z: true
|
62 |
+
z_channels: 4
|
63 |
+
resolution: 256
|
64 |
+
in_channels: 3
|
65 |
+
out_ch: 3
|
66 |
+
ch: 128
|
67 |
+
ch_mult:
|
68 |
+
- 1
|
69 |
+
- 2
|
70 |
+
- 4
|
71 |
+
- 4
|
72 |
+
num_res_blocks: 2
|
73 |
+
attn_resolutions: []
|
74 |
+
dropout: 0.0
|
75 |
+
lossconfig:
|
76 |
+
target: torch.nn.Identity
|
77 |
+
|
78 |
+
cond_stage_config:
|
79 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
Base11/Openpose.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4003c1da17b0e4ba444e02140e1c0d83bb24b79e4dcfd613c3a554d38f0f89c7
|
3 |
+
size 722601100
|
Base11/Openpose.yaml
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: cldm.cldm.ControlLDM
|
3 |
+
params:
|
4 |
+
linear_start: 0.00085
|
5 |
+
linear_end: 0.0120
|
6 |
+
num_timesteps_cond: 1
|
7 |
+
log_every_t: 200
|
8 |
+
timesteps: 1000
|
9 |
+
first_stage_key: "jpg"
|
10 |
+
cond_stage_key: "txt"
|
11 |
+
control_key: "hint"
|
12 |
+
image_size: 64
|
13 |
+
channels: 4
|
14 |
+
cond_stage_trainable: false
|
15 |
+
conditioning_key: crossattn
|
16 |
+
monitor: val/loss_simple_ema
|
17 |
+
scale_factor: 0.18215
|
18 |
+
use_ema: False
|
19 |
+
only_mid_control: False
|
20 |
+
|
21 |
+
control_stage_config:
|
22 |
+
target: cldm.cldm.ControlNet
|
23 |
+
params:
|
24 |
+
image_size: 32 # unused
|
25 |
+
in_channels: 4
|
26 |
+
hint_channels: 3
|
27 |
+
model_channels: 320
|
28 |
+
attention_resolutions: [ 4, 2, 1 ]
|
29 |
+
num_res_blocks: 2
|
30 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
31 |
+
num_heads: 8
|
32 |
+
use_spatial_transformer: True
|
33 |
+
transformer_depth: 1
|
34 |
+
context_dim: 768
|
35 |
+
use_checkpoint: True
|
36 |
+
legacy: False
|
37 |
+
|
38 |
+
unet_config:
|
39 |
+
target: cldm.cldm.ControlledUnetModel
|
40 |
+
params:
|
41 |
+
image_size: 32 # unused
|
42 |
+
in_channels: 4
|
43 |
+
out_channels: 4
|
44 |
+
model_channels: 320
|
45 |
+
attention_resolutions: [ 4, 2, 1 ]
|
46 |
+
num_res_blocks: 2
|
47 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
48 |
+
num_heads: 8
|
49 |
+
use_spatial_transformer: True
|
50 |
+
transformer_depth: 1
|
51 |
+
context_dim: 768
|
52 |
+
use_checkpoint: True
|
53 |
+
legacy: False
|
54 |
+
|
55 |
+
first_stage_config:
|
56 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
57 |
+
params:
|
58 |
+
embed_dim: 4
|
59 |
+
monitor: val/rec_loss
|
60 |
+
ddconfig:
|
61 |
+
double_z: true
|
62 |
+
z_channels: 4
|
63 |
+
resolution: 256
|
64 |
+
in_channels: 3
|
65 |
+
out_ch: 3
|
66 |
+
ch: 128
|
67 |
+
ch_mult:
|
68 |
+
- 1
|
69 |
+
- 2
|
70 |
+
- 4
|
71 |
+
- 4
|
72 |
+
num_res_blocks: 2
|
73 |
+
attn_resolutions: []
|
74 |
+
dropout: 0.0
|
75 |
+
lossconfig:
|
76 |
+
target: torch.nn.Identity
|
77 |
+
|
78 |
+
cond_stage_config:
|
79 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
Base11/Scribble.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99edfd25b54c18c0ab19fba8c5618f741aac1f8c3101e7fa62cce925ad87ae68
|
3 |
+
size 722601100
|
Base11/Scribble.yaml
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: cldm.cldm.ControlLDM
|
3 |
+
params:
|
4 |
+
linear_start: 0.00085
|
5 |
+
linear_end: 0.0120
|
6 |
+
num_timesteps_cond: 1
|
7 |
+
log_every_t: 200
|
8 |
+
timesteps: 1000
|
9 |
+
first_stage_key: "jpg"
|
10 |
+
cond_stage_key: "txt"
|
11 |
+
control_key: "hint"
|
12 |
+
image_size: 64
|
13 |
+
channels: 4
|
14 |
+
cond_stage_trainable: false
|
15 |
+
conditioning_key: crossattn
|
16 |
+
monitor: val/loss_simple_ema
|
17 |
+
scale_factor: 0.18215
|
18 |
+
use_ema: False
|
19 |
+
only_mid_control: False
|
20 |
+
|
21 |
+
control_stage_config:
|
22 |
+
target: cldm.cldm.ControlNet
|
23 |
+
params:
|
24 |
+
image_size: 32 # unused
|
25 |
+
in_channels: 4
|
26 |
+
hint_channels: 3
|
27 |
+
model_channels: 320
|
28 |
+
attention_resolutions: [ 4, 2, 1 ]
|
29 |
+
num_res_blocks: 2
|
30 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
31 |
+
num_heads: 8
|
32 |
+
use_spatial_transformer: True
|
33 |
+
transformer_depth: 1
|
34 |
+
context_dim: 768
|
35 |
+
use_checkpoint: True
|
36 |
+
legacy: False
|
37 |
+
|
38 |
+
unet_config:
|
39 |
+
target: cldm.cldm.ControlledUnetModel
|
40 |
+
params:
|
41 |
+
image_size: 32 # unused
|
42 |
+
in_channels: 4
|
43 |
+
out_channels: 4
|
44 |
+
model_channels: 320
|
45 |
+
attention_resolutions: [ 4, 2, 1 ]
|
46 |
+
num_res_blocks: 2
|
47 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
48 |
+
num_heads: 8
|
49 |
+
use_spatial_transformer: True
|
50 |
+
transformer_depth: 1
|
51 |
+
context_dim: 768
|
52 |
+
use_checkpoint: True
|
53 |
+
legacy: False
|
54 |
+
|
55 |
+
first_stage_config:
|
56 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
57 |
+
params:
|
58 |
+
embed_dim: 4
|
59 |
+
monitor: val/rec_loss
|
60 |
+
ddconfig:
|
61 |
+
double_z: true
|
62 |
+
z_channels: 4
|
63 |
+
resolution: 256
|
64 |
+
in_channels: 3
|
65 |
+
out_ch: 3
|
66 |
+
ch: 128
|
67 |
+
ch_mult:
|
68 |
+
- 1
|
69 |
+
- 2
|
70 |
+
- 4
|
71 |
+
- 4
|
72 |
+
num_res_blocks: 2
|
73 |
+
attn_resolutions: []
|
74 |
+
dropout: 0.0
|
75 |
+
lossconfig:
|
76 |
+
target: torch.nn.Identity
|
77 |
+
|
78 |
+
cond_stage_config:
|
79 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
Base11/Seg.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acd4dd3df2da2f1f2b9dd00f4504cc0d98b20afb608e25f1789a95c0ccdba14a
|
3 |
+
size 722601100
|
Base11/Seg.yaml
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: cldm.cldm.ControlLDM
|
3 |
+
params:
|
4 |
+
linear_start: 0.00085
|
5 |
+
linear_end: 0.0120
|
6 |
+
num_timesteps_cond: 1
|
7 |
+
log_every_t: 200
|
8 |
+
timesteps: 1000
|
9 |
+
first_stage_key: "jpg"
|
10 |
+
cond_stage_key: "txt"
|
11 |
+
control_key: "hint"
|
12 |
+
image_size: 64
|
13 |
+
channels: 4
|
14 |
+
cond_stage_trainable: false
|
15 |
+
conditioning_key: crossattn
|
16 |
+
monitor: val/loss_simple_ema
|
17 |
+
scale_factor: 0.18215
|
18 |
+
use_ema: False
|
19 |
+
only_mid_control: False
|
20 |
+
|
21 |
+
control_stage_config:
|
22 |
+
target: cldm.cldm.ControlNet
|
23 |
+
params:
|
24 |
+
image_size: 32 # unused
|
25 |
+
in_channels: 4
|
26 |
+
hint_channels: 3
|
27 |
+
model_channels: 320
|
28 |
+
attention_resolutions: [ 4, 2, 1 ]
|
29 |
+
num_res_blocks: 2
|
30 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
31 |
+
num_heads: 8
|
32 |
+
use_spatial_transformer: True
|
33 |
+
transformer_depth: 1
|
34 |
+
context_dim: 768
|
35 |
+
use_checkpoint: True
|
36 |
+
legacy: False
|
37 |
+
|
38 |
+
unet_config:
|
39 |
+
target: cldm.cldm.ControlledUnetModel
|
40 |
+
params:
|
41 |
+
image_size: 32 # unused
|
42 |
+
in_channels: 4
|
43 |
+
out_channels: 4
|
44 |
+
model_channels: 320
|
45 |
+
attention_resolutions: [ 4, 2, 1 ]
|
46 |
+
num_res_blocks: 2
|
47 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
48 |
+
num_heads: 8
|
49 |
+
use_spatial_transformer: True
|
50 |
+
transformer_depth: 1
|
51 |
+
context_dim: 768
|
52 |
+
use_checkpoint: True
|
53 |
+
legacy: False
|
54 |
+
|
55 |
+
first_stage_config:
|
56 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
57 |
+
params:
|
58 |
+
embed_dim: 4
|
59 |
+
monitor: val/rec_loss
|
60 |
+
ddconfig:
|
61 |
+
double_z: true
|
62 |
+
z_channels: 4
|
63 |
+
resolution: 256
|
64 |
+
in_channels: 3
|
65 |
+
out_ch: 3
|
66 |
+
ch: 128
|
67 |
+
ch_mult:
|
68 |
+
- 1
|
69 |
+
- 2
|
70 |
+
- 4
|
71 |
+
- 4
|
72 |
+
num_res_blocks: 2
|
73 |
+
attn_resolutions: []
|
74 |
+
dropout: 0.0
|
75 |
+
lossconfig:
|
76 |
+
target: torch.nn.Identity
|
77 |
+
|
78 |
+
cond_stage_config:
|
79 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
Base11/T2-color.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ea46a3d2f26023179a8daccb2259a198e992044570d2f9bd18e412d479fd591
|
3 |
+
size 74780341
|
Base11/T2-color.yaml
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: scripts.adapter.Adapter_light
|
3 |
+
params:
|
4 |
+
channels: [320, 640, 1280, 1280]
|
5 |
+
nums_rb: 4
|
6 |
+
cin: 192
|
Base11/T2-style.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b41febaddb32c4338272b9ad78b7d2b2584749ca5750d6b1d972766eb2fb731b
|
3 |
+
size 154363687
|
Base11/T2-style.yaml
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: scripts.adapter.StyleAdapter
|
3 |
+
params:
|
4 |
+
width: 1024
|
5 |
+
context_dim: 768
|
6 |
+
num_head: 8
|
7 |
+
n_layes: 3
|
8 |
+
num_token: 8
|