1b87a98261
## 主要更新 - ✨ 更新所有依赖到最新稳定版本 - 📝 添加详细的项目文档和模型推荐 - 🔧 配置 VSCode Cloud Studio 预览功能 - 🐛 修复 PyTorch API 弃用警告 ## 依赖更新 - diffusers: 0.27.2 → 0.35.2 - gradio: 4.21.0 → 5.46.0 - peft: 0.7.1 → 0.18.0 - Pillow: 9.5.0 → 11.3.0 - fastapi: 0.108.0 → 0.116.2 ## 新增文件 - CLAUDE.md - 项目架构和开发指南 - UPGRADE_NOTES.md - 详细的升级说明 - .vscode/preview.yml - 预览配置 - .vscode/LAUNCH_GUIDE.md - 启动指南 - .gitignore - 更新的忽略规则 ## 代码修复 - 修复 iopaint/model/ldm.py 中的 torch.cuda.amp.autocast() 弃用警告 ## 文档更新 - README.md - 添加模型推荐和使用指南 - 完整的项目源码（iopaint/） - Web 前端源码（web_app/） 🤖 Generated with Claude Code
87 lines
2.5 KiB
YAML
87 lines
2.5 KiB
YAML
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
|
|
|
|
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: 2560
|
|
num_classes: sequential
|
|
use_checkpoint: True
|
|
in_channels: 4
|
|
out_channels: 4
|
|
model_channels: 384
|
|
attention_resolutions: [4, 2]
|
|
num_res_blocks: 2
|
|
channel_mult: [1, 2, 4, 4]
|
|
num_head_channels: 64
|
|
use_linear_in_transformer: True
|
|
transformer_depth: 4
|
|
context_dim: [1280, 1280, 1280, 1280]
|
|
spatial_transformer_attn_type: softmax-xformers
|
|
|
|
conditioner_config:
|
|
target: sgm.modules.GeneralConditioner
|
|
params:
|
|
emb_models:
|
|
- is_trainable: False
|
|
input_key: txt
|
|
target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
|
|
params:
|
|
arch: ViT-bigG-14
|
|
version: laion2b_s39b_b160k
|
|
legacy: False
|
|
freeze: True
|
|
layer: penultimate
|
|
always_return_pooled: True
|
|
|
|
- is_trainable: False
|
|
input_key: original_size_as_tuple
|
|
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
|
|
params:
|
|
outdim: 256
|
|
|
|
- is_trainable: False
|
|
input_key: crop_coords_top_left
|
|
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
|
|
params:
|
|
outdim: 256
|
|
|
|
- is_trainable: False
|
|
input_key: aesthetic_score
|
|
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
|
|
params:
|
|
outdim: 256
|
|
|
|
first_stage_config:
|
|
target: sgm.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
|