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
71 lines
1.8 KiB
YAML
71 lines
1.8 KiB
YAML
model:
|
|
base_learning_rate: 1.0e-04
|
|
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
|
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"
|
|
image_size: 64
|
|
channels: 4
|
|
cond_stage_trainable: false # Note: different from the one we trained before
|
|
conditioning_key: crossattn
|
|
monitor: val/loss_simple_ema
|
|
scale_factor: 0.18215
|
|
use_ema: False
|
|
|
|
scheduler_config: # 10000 warmup steps
|
|
target: ldm.lr_scheduler.LambdaLinearScheduler
|
|
params:
|
|
warm_up_steps: [ 10000 ]
|
|
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
|
f_start: [ 1.e-6 ]
|
|
f_max: [ 1. ]
|
|
f_min: [ 1. ]
|
|
|
|
unet_config:
|
|
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
|
params:
|
|
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
|
|
use_checkpoint: True
|
|
legacy: False
|
|
|
|
first_stage_config:
|
|
target: ldm.models.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: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|