stable-diffusion-finetune/models/first_stage_models/kl-f32/config.yaml

47 lines
929 B
YAML

model:
base_learning_rate: 4.5e-06
target: ldm.models.autoencoder.AutoencoderKL
params:
monitor: val/rec_loss
embed_dim: 64
lossconfig:
target: ldm.modules.losses.LPIPSWithDiscriminator
params:
disc_start: 50001
kl_weight: 1.0e-06
disc_weight: 0.5
ddconfig:
double_z: true
z_channels: 64
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 1
- 2
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions:
- 16
- 8
dropout: 0.0
data:
target: main.DataModuleFromConfig
params:
batch_size: 6
wrap: true
train:
target: ldm.data.openimages.FullOpenImagesTrain
params:
size: 384
crop_size: 256
validation:
target: ldm.data.openimages.FullOpenImagesValidation
params:
size: 384
crop_size: 256