wehub-resource-sync
cddb07a176
docs / deploy (push) Has been cancelled
docs / changes (push) Has been cancelled
docs / check-and-build (push) Has been cancelled
build container image / cpu (push) Has been cancelled
build container image / cuda (push) Has been cancelled
build container image / rocm (push) Has been cancelled
frontend checks / frontend-checks (push) Has been cancelled
frontend tests / frontend-tests (push) Has been cancelled
lfs checks / lfs-check (push) Has been cancelled
python checks / python-checks (push) Has been cancelled
python tests / py3.12: macos-default (push) Has been cancelled
python tests / py3.11: windows-cpu (push) Has been cancelled
python tests / py3.12: windows-cpu (push) Has been cancelled
python tests / py3.11: linux-cpu (push) Has been cancelled
typegen checks / typegen-checks (push) Has been cancelled
uv lock checks / uv-lock-checks (push) Has been cancelled
openapi checks / openapi-checks (push) Has been cancelled
python tests / py3.11: macos-default (push) Has been cancelled
python tests / py3.12: linux-cpu (push) Has been cancelled
86 lines
2.2 KiB
YAML
86 lines
2.2 KiB
YAML
model:
|
|
target: cldm.cldm.ControlLDM
|
|
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"
|
|
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
|
|
|
|
control_stage_config:
|
|
target: cldm.cldm.ControlNet
|
|
params:
|
|
use_checkpoint: True
|
|
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_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
|
|
|
|
unet_config:
|
|
target: cldm.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_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"
|