colomi
0eb61f3e60
包含： - hair_service_sd: 换发型/换发色算法服务 (端口 8801) - photo_service: LoRA 训练调度服务 (端口 32678) - stable-diffusion-webui: SD WebUI 推理服务 (端口 57860) - kohya_ss_home: 训练环境代码 - meidaojia: 监控测试脚本 - setup.sh: 一键部署脚本 (conda环境恢复 + 配置生成 + 完整性检查) - start_all_services.sh: 启动3个服务 - configure.ini.template: 路径模板化 (BASE_DIR自动推导) - conda_envs/py310.yml: py310 环境定义 大文件 (weights/, models/, data/, conda_envs/*.tar.gz 等) 通过 .gitignore 排除， 由网盘单独上传。
99 lines
3.2 KiB
YAML
Executable File
99 lines
3.2 KiB
YAML
Executable File
model:
|
|
target: sgm.models.diffusion.DiffusionEngine
|
|
params:
|
|
scale_factor: 0.13025
|
|
disable_first_stage_autocast: True
|
|
|
|
denoiser_config:
|
|
target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
|
|
params:
|
|
num_idx: 1000
|
|
|
|
weighting_config:
|
|
target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
|
|
scaling_config:
|
|
target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling
|
|
discretization_config:
|
|
target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
|
|
|
|
network_config:
|
|
target: sgm.modules.diffusionmodules.openaimodel.UNetModel
|
|
params:
|
|
adm_in_channels: 2816
|
|
num_classes: sequential
|
|
use_checkpoint: False
|
|
in_channels: 9
|
|
out_channels: 4
|
|
model_channels: 320
|
|
attention_resolutions: [4, 2]
|
|
num_res_blocks: 2
|
|
channel_mult: [1, 2, 4]
|
|
num_head_channels: 64
|
|
use_spatial_transformer: True
|
|
use_linear_in_transformer: True
|
|
transformer_depth: [1, 2, 10] # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
|
|
context_dim: 2048
|
|
spatial_transformer_attn_type: softmax-xformers
|
|
legacy: False
|
|
|
|
conditioner_config:
|
|
target: sgm.modules.GeneralConditioner
|
|
params:
|
|
emb_models:
|
|
# crossattn cond
|
|
- is_trainable: False
|
|
input_key: txt
|
|
target: sgm.modules.encoders.modules.FrozenCLIPEmbedder
|
|
params:
|
|
layer: hidden
|
|
layer_idx: 11
|
|
# crossattn and vector cond
|
|
- is_trainable: False
|
|
input_key: txt
|
|
target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
|
|
params:
|
|
arch: ViT-bigG-14
|
|
version: laion2b_s39b_b160k
|
|
freeze: True
|
|
layer: penultimate
|
|
always_return_pooled: True
|
|
legacy: False
|
|
# vector cond
|
|
- is_trainable: False
|
|
input_key: original_size_as_tuple
|
|
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
|
|
params:
|
|
outdim: 256 # multiplied by two
|
|
# vector cond
|
|
- is_trainable: False
|
|
input_key: crop_coords_top_left
|
|
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
|
|
params:
|
|
outdim: 256 # multiplied by two
|
|
# vector cond
|
|
- is_trainable: False
|
|
input_key: target_size_as_tuple
|
|
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
|
|
params:
|
|
outdim: 256 # multiplied by two
|
|
|
|
first_stage_config:
|
|
target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
|
|
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
|