stable-diffusion-paperspace/lfs/latent-diffusion/project.yaml

81 lines
1.9 KiB
YAML

model:
base_learning_rate: 1.0e-06
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.0015
linear_end: 0.0155
log_every_t: 100
timesteps: 1000
loss_type: l2
first_stage_key: image
cond_stage_key: LR_image
image_size: 64
channels: 3
concat_mode: true
cond_stage_trainable: false
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
image_size: 64
in_channels: 6
out_channels: 3
model_channels: 160
attention_resolutions:
- 16
- 8
num_res_blocks: 2
channel_mult:
- 1
- 2
- 2
- 4
num_head_channels: 32
first_stage_config:
target: ldm.models.autoencoder.VQModelInterface
params:
embed_dim: 3
n_embed: 8192
monitor: val/rec_loss
ddconfig:
double_z: false
z_channels: 3
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Module # todo
cond_stage_config:
target: torch.nn.Identity
data:
target: cutlit.DataModuleFromConfig
params:
batch_size: 64
wrap: false
num_workers: 12
train:
target: ldm.data.openimages.SuperresOpenImagesAdvancedTrain
params:
size: 256
degradation: bsrgan_light
downscale_f: 4
min_crop_f: 0.5
max_crop_f: 1.0
random_crop: true
validation:
target: ldm.data.openimages.SuperresOpenImagesAdvancedValidation
params:
size: 256
degradation: bsrgan_light
downscale_f: 4
min_crop_f: 0.5
max_crop_f: 1.0
random_crop: true