Skip to content

Commit 5775800

Browse files
author
Ubuntu
committed
tmp commit
1 parent 69ae4b3 commit 5775800

23 files changed

+1848
-25
lines changed

‎configs/stable-diffusion/v1-finetune-object.yaml

Lines changed: 108 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,108 @@
1+
model:
2+
base_learning_rate: 5.0e-03
3+
target: ldm.models.diffusion.ddpm.LatentDiffusion
4+
params:
5+
linear_start: 0.00085
6+
linear_end: 0.0120
7+
num_timesteps_cond: 1
8+
log_every_t: 200
9+
timesteps: 1000
10+
first_stage_key: image
11+
cond_stage_key: caption
12+
image_size: 64
13+
channels: 4
14+
cond_stage_trainable: true # Note: different from the one we trained before
15+
conditioning_key: crossattn
16+
monitor: val/loss_simple_ema
17+
scale_factor: 0.18215
18+
use_ema: False
19+
embedding_reg_weight: 0.0
20+
21+
personalization_config:
22+
target: ldm.modules.embedding_manager.EmbeddingManager
23+
params:
24+
placeholder_strings: ["*"]
25+
initializer_words: ["sculpture"]
26+
per_image_tokens: false
27+
num_vectors_per_token: 1
28+
progressive_words: False
29+
30+
unet_config:
31+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
32+
params:
33+
image_size: 32 # unused
34+
in_channels: 4
35+
out_channels: 4
36+
model_channels: 320
37+
attention_resolutions: [ 4, 2, 1 ]
38+
num_res_blocks: 2
39+
channel_mult: [ 1, 2, 4, 4 ]
40+
num_heads: 8
41+
use_spatial_transformer: True
42+
transformer_depth: 1
43+
context_dim: 768
44+
use_checkpoint: True
45+
legacy: False
46+
47+
first_stage_config:
48+
target: ldm.models.autoencoder.AutoencoderKL
49+
params:
50+
embed_dim: 4
51+
monitor: val/rec_loss
52+
ddconfig:
53+
double_z: true
54+
z_channels: 4
55+
resolution: 256
56+
in_channels: 3
57+
out_ch: 3
58+
ch: 128
59+
ch_mult:
60+
- 1
61+
- 2
62+
- 4
63+
- 4
64+
num_res_blocks: 2
65+
attn_resolutions: []
66+
dropout: 0.0
67+
lossconfig:
68+
target: torch.nn.Identity
69+
70+
cond_stage_config:
71+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
72+
73+
data:
74+
target: main.DataModuleFromConfig
75+
params:
76+
batch_size: 1
77+
num_workers: 2
78+
wrap: false
79+
train:
80+
target: ldm.data.personalized.PersonalizedBase
81+
params:
82+
size: 512
83+
set: train
84+
per_image_tokens: false
85+
repeats: 100
86+
validation:
87+
target: ldm.data.personalized.PersonalizedBase
88+
params:
89+
size: 512
90+
set: val
91+
per_image_tokens: false
92+
repeats: 10
93+
94+
lightning:
95+
modelcheckpoint:
96+
params:
97+
every_n_train_steps: 500
98+
callbacks:
99+
image_logger:
100+
target: main.ImageLogger
101+
params:
102+
batch_frequency: 500
103+
max_images: 8
104+
increase_log_steps: False
105+
106+
trainer:
107+
benchmark: True
108+
max_steps: 4000

‎configs/stable-diffusion/v1-finetune-style.yaml

Lines changed: 103 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,103 @@
1+
model:
2+
base_learning_rate: 5.0e-03
3+
target: ldm.models.diffusion.ddpm.LatentDiffusion
4+
params:
5+
linear_start: 0.00085
6+
linear_end: 0.0120
7+
num_timesteps_cond: 1
8+
log_every_t: 200
9+
timesteps: 1000
10+
first_stage_key: image
11+
cond_stage_key: caption
12+
image_size: 64
13+
channels: 4
14+
cond_stage_trainable: true # Note: different from the one we trained before
15+
conditioning_key: crossattn
16+
monitor: val/loss_simple_ema
17+
scale_factor: 0.18215
18+
use_ema: False
19+
embedding_reg_weight: 0.0
20+
21+
personalization_config:
22+
target: ldm.modules.embedding_manager.EmbeddingManager
23+
params:
24+
placeholder_strings: ["*"]
25+
initializer_words: ["painting"]
26+
per_image_tokens: false
27+
num_vectors_per_token: 1
28+
29+
unet_config:
30+
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
31+
params:
32+
image_size: 32 # unused
33+
in_channels: 4
34+
out_channels: 4
35+
model_channels: 320
36+
attention_resolutions: [ 4, 2, 1 ]
37+
num_res_blocks: 2
38+
channel_mult: [ 1, 2, 4, 4 ]
39+
num_heads: 8
40+
use_spatial_transformer: True
41+
transformer_depth: 1
42+
context_dim: 768
43+
use_checkpoint: True
44+
legacy: False
45+
46+
first_stage_config:
47+
target: ldm.models.autoencoder.AutoencoderKL
48+
params:
49+
embed_dim: 4
50+
monitor: val/rec_loss
51+
ddconfig:
52+
double_z: true
53+
z_channels: 4
54+
resolution: 256
55+
in_channels: 3
56+
out_ch: 3
57+
ch: 128
58+
ch_mult:
59+
- 1
60+
- 2
61+
- 4
62+
- 4
63+
num_res_blocks: 2
64+
attn_resolutions: []
65+
dropout: 0.0
66+
lossconfig:
67+
target: torch.nn.Identity
68+
69+
cond_stage_config:
70+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
71+
72+
data:
73+
target: main.DataModuleFromConfig
74+
params:
75+
batch_size: 2
76+
num_workers: 16
77+
wrap: false
78+
train:
79+
target: ldm.data.personalized_style.PersonalizedBase
80+
params:
81+
size: 512
82+
set: train
83+
per_image_tokens: false
84+
repeats: 100
85+
validation:
86+
target: ldm.data.personalized_style.PersonalizedBase
87+
params:
88+
size: 512
89+
set: val
90+
per_image_tokens: false
91+
repeats: 10
92+
93+
lightning:
94+
callbacks:
95+
image_logger:
96+
target: main.ImageLogger
97+
params:
98+
batch_frequency: 500
99+
max_images: 8
100+
increase_log_steps: False
101+
102+
trainer:
103+
benchmark: True

‎ldm/__pycache__/util.cpython-38.pyc

5.95 KB
Binary file not shown.

‎ldm/data/__pycache__/__init__.cpython-38.pyc

162 Bytes
Binary file not shown.

‎ldm/data/__pycache__/base.cpython-38.pyc

1.24 KB
Binary file not shown.

‎ldm/models/__pycache__/autoencoder.cpython-38.pyc

13.2 KB
Binary file not shown.

‎ldm/models/diffusion/__pycache__/__init__.cpython-38.pyc

174 Bytes
Binary file not shown.

‎ldm/models/diffusion/__pycache__/ddim.cpython-38.pyc

7.01 KB
Binary file not shown.

‎ldm/models/diffusion/__pycache__/ddpm.cpython-38.pyc

45.2 KB
Binary file not shown.

0 commit comments

Comments
 (0)