feature: add "shuffle" control mode
Image is generated from elements of control image. similar to style transferpull/316/head
parent
750d4f7ea8
commit
476a81a967
Binary file not shown.
After Width: | Height: | Size: 34 KiB |
Binary file not shown.
After Width: | Height: | Size: 34 KiB |
@ -0,0 +1,80 @@
|
||||
model:
|
||||
target: imaginairy.modules.cldm.ControlLDM
|
||||
params:
|
||||
linear_start: 0.00085
|
||||
linear_end: 0.0120
|
||||
num_timesteps_cond: 1
|
||||
log_every_t: 200
|
||||
timesteps: 1000
|
||||
first_stage_key: "image"
|
||||
cond_stage_key: "txt"
|
||||
control_key: "hint"
|
||||
image_size: 64
|
||||
channels: 4
|
||||
cond_stage_trainable: false
|
||||
conditioning_key: crossattn
|
||||
monitor: val/loss_simple_ema
|
||||
scale_factor: 0.18215
|
||||
use_ema: False
|
||||
only_mid_control: False
|
||||
global_average_pooling: True
|
||||
|
||||
unet_config:
|
||||
target: imaginairy.modules.cldm.ControlledUnetModel
|
||||
params:
|
||||
use_checkpoint: True
|
||||
image_size: 32 # unused
|
||||
in_channels: 4
|
||||
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
|
||||
|
||||
control_stage_config:
|
||||
target: imaginairy.modules.cldm.ControlNet
|
||||
params:
|
||||
image_size: 32 # unused
|
||||
in_channels: 4
|
||||
hint_channels: 3
|
||||
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
|
Binary file not shown.
After Width: | Height: | Size: 565 KiB |
Loading…
Reference in New Issue