commit
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- cldm_v15.yaml +0 -79
- cldm_v21.yaml +0 -85
- control_sd15_canny.yaml +0 -79
- control_sd15_depth.yaml +0 -79
- control_sd15_hed.yaml +0 -79
- control_sd15_mlsd.yaml +0 -79
- control_sd15_normal.yaml +0 -79
- control_sd15_openpose.yaml +0 -79
- control_sd15_scribble.yaml +0 -79
- control_sd15_seg.yaml +0 -79
- control_v11e_sd15_ip2p.yaml +0 -79
- control_v11e_sd15_ip2p_fp16.yaml +0 -79
- control_v11e_sd15_shuffle.yaml +0 -80
- control_v11e_sd15_shuffle_fp16.yaml +0 -80
- control_v11f1e_sd15_tile.yaml +0 -79
- control_v11f1e_sd15_tile_fp16.yaml +0 -79
- control_v11f1p_sd15_depth.yaml +0 -79
- control_v11f1p_sd15_depth_fp16.yaml +0 -79
- control_v11p_sd15_canny.yaml +0 -79
- control_v11p_sd15_canny_fp16.yaml +0 -79
- control_v11p_sd15_inpaint.yaml +0 -79
- control_v11p_sd15_inpaint_fp16.yaml +0 -79
- control_v11p_sd15_lineart.yaml +0 -79
- control_v11p_sd15_lineart_fp16.yaml +0 -79
- control_v11p_sd15_mlsd.yaml +0 -79
- control_v11p_sd15_mlsd_fp16.yaml +0 -79
- control_v11p_sd15_normalbae.yaml +0 -79
- control_v11p_sd15_normalbae_fp16.yaml +0 -79
- control_v11p_sd15_openpose.yaml +0 -79
- control_v11p_sd15_openpose_fp16.yaml +0 -79
- control_v11p_sd15_scribble.yaml +0 -79
- control_v11p_sd15_scribble_fp16.yaml +0 -79
- control_v11p_sd15_seg.yaml +0 -79
- control_v11p_sd15_seg_fp16.yaml +0 -79
- control_v11p_sd15_softedge.yaml +0 -79
- control_v11p_sd15_softedge_fp16.yaml +0 -79
- control_v11p_sd15s2_lineart_anime.yaml +0 -79
- control_v11p_sd15s2_lineart_anime_fp16.yaml +0 -79
- control_v1p_sd15_qrcode_monster.yaml +0 -80
- image_adapter_v14.yaml +0 -9
- sketch_adapter_v14.yaml +0 -9
- t2iadapter_canny_sd14v1.yaml +0 -9
- t2iadapter_canny_sd15v2.yaml +0 -9
- t2iadapter_color_sd14v1.yaml +0 -6
- t2iadapter_depth_sd14v1.yaml +0 -9
- t2iadapter_depth_sd15v2.yaml +0 -9
- t2iadapter_keypose_sd14v1.yaml +0 -9
- t2iadapter_openpose_sd14v1.yaml +0 -9
- t2iadapter_seg_sd14v1.yaml +0 -9
- t2iadapter_sketch_sd14v1.yaml +0 -9
cldm_v15.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
cldm_v21.yaml
DELETED
@@ -1,85 +0,0 @@
|
|
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 |
-
use_checkpoint: True
|
25 |
-
image_size: 32 # unused
|
26 |
-
in_channels: 4
|
27 |
-
hint_channels: 3
|
28 |
-
model_channels: 320
|
29 |
-
attention_resolutions: [ 4, 2, 1 ]
|
30 |
-
num_res_blocks: 2
|
31 |
-
channel_mult: [ 1, 2, 4, 4 ]
|
32 |
-
num_head_channels: 64 # need to fix for flash-attn
|
33 |
-
use_spatial_transformer: True
|
34 |
-
use_linear_in_transformer: True
|
35 |
-
transformer_depth: 1
|
36 |
-
context_dim: 1024
|
37 |
-
legacy: False
|
38 |
-
|
39 |
-
unet_config:
|
40 |
-
target: cldm.cldm.ControlledUnetModel
|
41 |
-
params:
|
42 |
-
use_checkpoint: True
|
43 |
-
image_size: 32 # unused
|
44 |
-
in_channels: 4
|
45 |
-
out_channels: 4
|
46 |
-
model_channels: 320
|
47 |
-
attention_resolutions: [ 4, 2, 1 ]
|
48 |
-
num_res_blocks: 2
|
49 |
-
channel_mult: [ 1, 2, 4, 4 ]
|
50 |
-
num_head_channels: 64 # need to fix for flash-attn
|
51 |
-
use_spatial_transformer: True
|
52 |
-
use_linear_in_transformer: True
|
53 |
-
transformer_depth: 1
|
54 |
-
context_dim: 1024
|
55 |
-
legacy: False
|
56 |
-
|
57 |
-
first_stage_config:
|
58 |
-
target: ldm.models.autoencoder.AutoencoderKL
|
59 |
-
params:
|
60 |
-
embed_dim: 4
|
61 |
-
monitor: val/rec_loss
|
62 |
-
ddconfig:
|
63 |
-
#attn_type: "vanilla-xformers"
|
64 |
-
double_z: true
|
65 |
-
z_channels: 4
|
66 |
-
resolution: 256
|
67 |
-
in_channels: 3
|
68 |
-
out_ch: 3
|
69 |
-
ch: 128
|
70 |
-
ch_mult:
|
71 |
-
- 1
|
72 |
-
- 2
|
73 |
-
- 4
|
74 |
-
- 4
|
75 |
-
num_res_blocks: 2
|
76 |
-
attn_resolutions: []
|
77 |
-
dropout: 0.0
|
78 |
-
lossconfig:
|
79 |
-
target: torch.nn.Identity
|
80 |
-
|
81 |
-
cond_stage_config:
|
82 |
-
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
|
83 |
-
params:
|
84 |
-
freeze: True
|
85 |
-
layer: "penultimate"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_sd15_canny.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_sd15_depth.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_sd15_hed.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_sd15_mlsd.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_sd15_normal.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_sd15_openpose.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_sd15_scribble.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_sd15_seg.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11e_sd15_ip2p.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11e_sd15_ip2p_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11e_sd15_shuffle.yaml
DELETED
@@ -1,80 +0,0 @@
|
|
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 |
-
global_average_pooling: True
|
21 |
-
|
22 |
-
control_stage_config:
|
23 |
-
target: cldm.cldm.ControlNet
|
24 |
-
params:
|
25 |
-
image_size: 32 # unused
|
26 |
-
in_channels: 4
|
27 |
-
hint_channels: 3
|
28 |
-
model_channels: 320
|
29 |
-
attention_resolutions: [ 4, 2, 1 ]
|
30 |
-
num_res_blocks: 2
|
31 |
-
channel_mult: [ 1, 2, 4, 4 ]
|
32 |
-
num_heads: 8
|
33 |
-
use_spatial_transformer: True
|
34 |
-
transformer_depth: 1
|
35 |
-
context_dim: 768
|
36 |
-
use_checkpoint: True
|
37 |
-
legacy: False
|
38 |
-
|
39 |
-
unet_config:
|
40 |
-
target: cldm.cldm.ControlledUnetModel
|
41 |
-
params:
|
42 |
-
image_size: 32 # unused
|
43 |
-
in_channels: 4
|
44 |
-
out_channels: 4
|
45 |
-
model_channels: 320
|
46 |
-
attention_resolutions: [ 4, 2, 1 ]
|
47 |
-
num_res_blocks: 2
|
48 |
-
channel_mult: [ 1, 2, 4, 4 ]
|
49 |
-
num_heads: 8
|
50 |
-
use_spatial_transformer: True
|
51 |
-
transformer_depth: 1
|
52 |
-
context_dim: 768
|
53 |
-
use_checkpoint: True
|
54 |
-
legacy: False
|
55 |
-
|
56 |
-
first_stage_config:
|
57 |
-
target: ldm.models.autoencoder.AutoencoderKL
|
58 |
-
params:
|
59 |
-
embed_dim: 4
|
60 |
-
monitor: val/rec_loss
|
61 |
-
ddconfig:
|
62 |
-
double_z: true
|
63 |
-
z_channels: 4
|
64 |
-
resolution: 256
|
65 |
-
in_channels: 3
|
66 |
-
out_ch: 3
|
67 |
-
ch: 128
|
68 |
-
ch_mult:
|
69 |
-
- 1
|
70 |
-
- 2
|
71 |
-
- 4
|
72 |
-
- 4
|
73 |
-
num_res_blocks: 2
|
74 |
-
attn_resolutions: []
|
75 |
-
dropout: 0.0
|
76 |
-
lossconfig:
|
77 |
-
target: torch.nn.Identity
|
78 |
-
|
79 |
-
cond_stage_config:
|
80 |
-
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11e_sd15_shuffle_fp16.yaml
DELETED
@@ -1,80 +0,0 @@
|
|
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 |
-
global_average_pooling: True
|
21 |
-
|
22 |
-
control_stage_config:
|
23 |
-
target: cldm.cldm.ControlNet
|
24 |
-
params:
|
25 |
-
image_size: 32 # unused
|
26 |
-
in_channels: 4
|
27 |
-
hint_channels: 3
|
28 |
-
model_channels: 320
|
29 |
-
attention_resolutions: [ 4, 2, 1 ]
|
30 |
-
num_res_blocks: 2
|
31 |
-
channel_mult: [ 1, 2, 4, 4 ]
|
32 |
-
num_heads: 8
|
33 |
-
use_spatial_transformer: True
|
34 |
-
transformer_depth: 1
|
35 |
-
context_dim: 768
|
36 |
-
use_checkpoint: True
|
37 |
-
legacy: False
|
38 |
-
|
39 |
-
unet_config:
|
40 |
-
target: cldm.cldm.ControlledUnetModel
|
41 |
-
params:
|
42 |
-
image_size: 32 # unused
|
43 |
-
in_channels: 4
|
44 |
-
out_channels: 4
|
45 |
-
model_channels: 320
|
46 |
-
attention_resolutions: [ 4, 2, 1 ]
|
47 |
-
num_res_blocks: 2
|
48 |
-
channel_mult: [ 1, 2, 4, 4 ]
|
49 |
-
num_heads: 8
|
50 |
-
use_spatial_transformer: True
|
51 |
-
transformer_depth: 1
|
52 |
-
context_dim: 768
|
53 |
-
use_checkpoint: True
|
54 |
-
legacy: False
|
55 |
-
|
56 |
-
first_stage_config:
|
57 |
-
target: ldm.models.autoencoder.AutoencoderKL
|
58 |
-
params:
|
59 |
-
embed_dim: 4
|
60 |
-
monitor: val/rec_loss
|
61 |
-
ddconfig:
|
62 |
-
double_z: true
|
63 |
-
z_channels: 4
|
64 |
-
resolution: 256
|
65 |
-
in_channels: 3
|
66 |
-
out_ch: 3
|
67 |
-
ch: 128
|
68 |
-
ch_mult:
|
69 |
-
- 1
|
70 |
-
- 2
|
71 |
-
- 4
|
72 |
-
- 4
|
73 |
-
num_res_blocks: 2
|
74 |
-
attn_resolutions: []
|
75 |
-
dropout: 0.0
|
76 |
-
lossconfig:
|
77 |
-
target: torch.nn.Identity
|
78 |
-
|
79 |
-
cond_stage_config:
|
80 |
-
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11f1e_sd15_tile.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11f1e_sd15_tile_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11f1p_sd15_depth.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11f1p_sd15_depth_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_canny.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_canny_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_inpaint.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_inpaint_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_lineart.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_lineart_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_mlsd.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_mlsd_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_normalbae.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_normalbae_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_openpose.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_openpose_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_scribble.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_scribble_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_seg.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_seg_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_softedge.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15_softedge_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15s2_lineart_anime.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v11p_sd15s2_lineart_anime_fp16.yaml
DELETED
@@ -1,79 +0,0 @@
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
control_v1p_sd15_qrcode_monster.yaml
DELETED
@@ -1,80 +0,0 @@
|
|
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
|
80 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
image_adapter_v14.yaml
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
target: tencentarc.t21_adapter
|
3 |
-
params:
|
4 |
-
channels: [320, 640, 1280, 1280]
|
5 |
-
nums_rb: 2
|
6 |
-
ksize: 1
|
7 |
-
sk: true
|
8 |
-
cin: 192
|
9 |
-
use_conv: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
sketch_adapter_v14.yaml
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
target: tencentarc.t21_adapter
|
3 |
-
params:
|
4 |
-
channels: [320, 640, 1280, 1280]
|
5 |
-
nums_rb: 2
|
6 |
-
ksize: 1
|
7 |
-
sk: true
|
8 |
-
cin: 64
|
9 |
-
use_conv: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t2iadapter_canny_sd14v1.yaml
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
target: tencentarc.t21_adapter
|
3 |
-
params:
|
4 |
-
channels: [320, 640, 1280, 1280]
|
5 |
-
nums_rb: 2
|
6 |
-
ksize: 1
|
7 |
-
sk: true
|
8 |
-
cin: 64
|
9 |
-
use_conv: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t2iadapter_canny_sd15v2.yaml
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
target: tencentarc.t21_adapter
|
3 |
-
params:
|
4 |
-
channels: [320, 640, 1280, 1280]
|
5 |
-
nums_rb: 2
|
6 |
-
ksize: 1
|
7 |
-
sk: true
|
8 |
-
cin: 64
|
9 |
-
use_conv: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t2iadapter_color_sd14v1.yaml
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
target: scripts.adapter.Adapter_light
|
3 |
-
params:
|
4 |
-
channels: [320, 640, 1280, 1280]
|
5 |
-
nums_rb: 4
|
6 |
-
cin: 192
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t2iadapter_depth_sd14v1.yaml
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
target: tencentarc.t21_adapter
|
3 |
-
params:
|
4 |
-
channels: [320, 640, 1280, 1280]
|
5 |
-
nums_rb: 2
|
6 |
-
ksize: 1
|
7 |
-
sk: true
|
8 |
-
cin: 192
|
9 |
-
use_conv: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t2iadapter_depth_sd15v2.yaml
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
target: tencentarc.t21_adapter
|
3 |
-
params:
|
4 |
-
channels: [320, 640, 1280, 1280]
|
5 |
-
nums_rb: 2
|
6 |
-
ksize: 1
|
7 |
-
sk: true
|
8 |
-
cin: 192
|
9 |
-
use_conv: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t2iadapter_keypose_sd14v1.yaml
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
target: tencentarc.t21_adapter
|
3 |
-
params:
|
4 |
-
channels: [320, 640, 1280, 1280]
|
5 |
-
nums_rb: 2
|
6 |
-
ksize: 1
|
7 |
-
sk: true
|
8 |
-
cin: 192
|
9 |
-
use_conv: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t2iadapter_openpose_sd14v1.yaml
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
target: tencentarc.t21_adapter
|
3 |
-
params:
|
4 |
-
channels: [320, 640, 1280, 1280]
|
5 |
-
nums_rb: 2
|
6 |
-
ksize: 1
|
7 |
-
sk: true
|
8 |
-
cin: 192
|
9 |
-
use_conv: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t2iadapter_seg_sd14v1.yaml
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
target: tencentarc.t21_adapter
|
3 |
-
params:
|
4 |
-
channels: [320, 640, 1280, 1280]
|
5 |
-
nums_rb: 2
|
6 |
-
ksize: 1
|
7 |
-
sk: true
|
8 |
-
cin: 192
|
9 |
-
use_conv: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
t2iadapter_sketch_sd14v1.yaml
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
target: tencentarc.t21_adapter
|
3 |
-
params:
|
4 |
-
channels: [320, 640, 1280, 1280]
|
5 |
-
nums_rb: 2
|
6 |
-
ksize: 1
|
7 |
-
sk: true
|
8 |
-
cin: 64
|
9 |
-
use_conv: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|