File size: 1,637 Bytes
2a8a75a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
model:
target: imagedream.ldm.interface.LatentDiffusionInterface
params:
linear_start: 0.00085
linear_end: 0.0120
timesteps: 1000
scale_factor: 0.18215
parameterization: "eps"
unet_config:
target: imagedream.ldm.modules.diffusionmodules.openaimodel.MultiViewUNetModel
params:
image_size: 32 # unused
in_channels: 8
out_channels: 8
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
use_checkpoint: False
legacy: False
camera_dim: 16
with_ip: True
ip_dim: 16 # ip token length
ip_mode: "local_resample"
vae_config:
target: imagedream.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
clip_config:
target: imagedream.ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
params:
freeze: True
layer: "penultimate"
ip_mode: "local_resample"
|