75 lines
1.8 KiB
YAML
75 lines
1.8 KiB
YAML
|
model:
|
||
|
base_learning_rate: 5.0e-07
|
||
|
target: ldm.models.diffusion.ddpm.LatentDepth2ImageDiffusion
|
||
|
params:
|
||
|
linear_start: 0.00085
|
||
|
linear_end: 0.0120
|
||
|
num_timesteps_cond: 1
|
||
|
log_every_t: 200
|
||
|
timesteps: 1000
|
||
|
first_stage_key: "jpg"
|
||
|
cond_stage_key: "txt"
|
||
|
image_size: 64
|
||
|
channels: 4
|
||
|
cond_stage_trainable: false
|
||
|
conditioning_key: hybrid
|
||
|
scale_factor: 0.18215
|
||
|
monitor: val/loss_simple_ema
|
||
|
finetune_keys: null
|
||
|
use_ema: False
|
||
|
|
||
|
depth_stage_config:
|
||
|
target: ldm.modules.midas.api.MiDaSInference
|
||
|
params:
|
||
|
model_type: "dpt_hybrid"
|
||
|
|
||
|
unet_config:
|
||
|
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
||
|
params:
|
||
|
use_checkpoint: True
|
||
|
image_size: 32 # unused
|
||
|
in_channels: 5
|
||
|
out_channels: 4
|
||
|
model_channels: 320
|
||
|
attention_resolutions: [ 4, 2, 1 ]
|
||
|
num_res_blocks: 2
|
||
|
channel_mult: [ 1, 2, 4, 4 ]
|
||
|
num_head_channels: 64 # need to fix for flash-attn
|
||
|
use_spatial_transformer: True
|
||
|
use_linear_in_transformer: True
|
||
|
transformer_depth: 1
|
||
|
context_dim: 1024
|
||
|
legacy: False
|
||
|
|
||
|
first_stage_config:
|
||
|
target: ldm.models.autoencoder.AutoencoderKL
|
||
|
params:
|
||
|
embed_dim: 4
|
||
|
monitor: val/rec_loss
|
||
|
ddconfig:
|
||
|
#attn_type: "vanilla-xformers"
|
||
|
double_z: true
|
||
|
z_channels: 4
|
||
|
resolution: 256
|
||
|
in_channels: 3
|
||
|
out_ch: 3
|
||
|
ch: 128
|
||
|
ch_mult:
|
||
|
- 1
|
||
|
- 2
|
||
|
- 4
|
||
|
- 4
|
||
|
num_res_blocks: 2
|
||
|
attn_resolutions: [ ]
|
||
|
dropout: 0.0
|
||
|
lossconfig:
|
||
|
target: torch.nn.Identity
|
||
|
|
||
|
cond_stage_config:
|
||
|
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
|
||
|
params:
|
||
|
freeze: True
|
||
|
layer: "penultimate"
|
||
|
|
||
|
|