65 lines
1.8 KiB
YAML
65 lines
1.8 KiB
YAML
|
model:
|
||
|
|
base_learning_rate: 1.0e-04
|
||
|
|
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
||
|
|
params:
|
||
|
|
linear_start: 0.001
|
||
|
|
linear_end: 0.015
|
||
|
|
num_timesteps_cond: 1
|
||
|
|
log_every_t: 200
|
||
|
|
timesteps: 1000
|
||
|
|
first_stage_key: "jpg"
|
||
|
|
cond_stage_key: "txt"
|
||
|
|
image_size: 48
|
||
|
|
channels: 16
|
||
|
|
cond_stage_trainable: false
|
||
|
|
conditioning_key: crossattn
|
||
|
|
monitor: val/loss_simple_ema
|
||
|
|
scale_factor: 0.22765929 # magic number
|
||
|
|
|
||
|
|
scheduler_config: # 10000 warmup steps
|
||
|
|
target: ldm.lr_scheduler.LambdaLinearScheduler
|
||
|
|
params:
|
||
|
|
warm_up_steps: [ 10000 ]
|
||
|
|
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
||
|
|
f_start: [ 1.e-6 ]
|
||
|
|
f_max: [ 1. ]
|
||
|
|
f_min: [ 1. ]
|
||
|
|
|
||
|
|
unet_config:
|
||
|
|
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
||
|
|
params:
|
||
|
|
image_size: 48
|
||
|
|
in_channels: 16
|
||
|
|
out_channels: 16
|
||
|
|
model_channels: 320
|
||
|
|
attention_resolutions: [ 4, 2, 1 ]
|
||
|
|
num_res_blocks: 2
|
||
|
|
channel_mult: [ 1, 2, 4, 4 ]
|
||
|
|
num_heads: 8
|
||
|
|
use_spatial_transformer: True
|
||
|
|
transformer_depth: 1
|
||
|
|
context_dim: 768
|
||
|
|
use_checkpoint: True
|
||
|
|
legacy: False
|
||
|
|
|
||
|
|
first_stage_config:
|
||
|
|
target: ldm.models.autoencoder.AutoencoderKL
|
||
|
|
params:
|
||
|
|
embed_dim: 16
|
||
|
|
monitor: val/rec_loss
|
||
|
|
ddconfig:
|
||
|
|
double_z: True
|
||
|
|
z_channels: 16
|
||
|
|
resolution: 256
|
||
|
|
in_channels: 3
|
||
|
|
out_ch: 3
|
||
|
|
ch: 128
|
||
|
|
ch_mult: [ 1,1,2,2,4 ] # num_down = len(ch_mult)-1
|
||
|
|
num_res_blocks: 2
|
||
|
|
attn_resolutions: [ 16 ]
|
||
|
|
dropout: 0.0
|
||
|
|
lossconfig:
|
||
|
|
target: torch.nn.Identity
|
||
|
|
|
||
|
|
cond_stage_config:
|
||
|
|
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|