imaginAIry/imaginairy/configs/instruct-pix2pix.yaml

70 lines
1.8 KiB
YAML

model:
base_learning_rate: 1.0e-04
target: imaginairy.modules.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "edited"
cond_stage_key: "edit"
image_size: 16
channels: 4
cond_stage_trainable: false
conditioning_key: hybrid
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: false
scheduler_config:
target: imaginairy.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 0 ]
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1. ]
f_min: [ 1. ]
unet_config:
target: imaginairy.modules.diffusion.openaimodel.UNetModel
params:
use_checkpoint: True
image_size: 32 # unused
in_channels: 8
out_channels: 4
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
legacy: False
first_stage_config:
target: imaginairy.modules.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
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: imaginairy.modules.clip_embedders.FrozenCLIPEmbedder