| 1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677 |
- model:
- base_learning_rate: 2.0e-06
- target: ldm.models.diffusion.ddpm.LatentDiffusion
- params:
- linear_start: 0.0015
- linear_end: 0.0195
- num_timesteps_cond: 1
- log_every_t: 200
- timesteps: 1000
- first_stage_key: image
- cond_stage_key: caption
- image_size: 64
- channels: 3
- cond_stage_trainable: true
- conditioning_key: crossattn
- monitor: val/loss_simple_ema
- unet_config:
- target: ldm.modules.diffusionmodules.openaimodel.UNetModel
- params:
- image_size: 64
- in_channels: 3
- out_channels: 3
- model_channels: 192
- attention_resolutions:
- - 8
- - 4
- - 2
- num_res_blocks: 2
- channel_mult:
- - 1
- - 2
- - 3
- - 5
- num_head_channels: 32
- use_spatial_transformer: true
- transformer_depth: 1
- context_dim: 640
- first_stage_config:
- target: ldm.models.autoencoder.VQModelInterface
- params:
- embed_dim: 3
- n_embed: 8192
- ddconfig:
- double_z: false
- z_channels: 3
- resolution: 256
- in_channels: 3
- out_ch: 3
- ch: 128
- ch_mult:
- - 1
- - 2
- - 4
- num_res_blocks: 2
- attn_resolutions: []
- dropout: 0.0
- lossconfig:
- target: torch.nn.Identity
- cond_stage_config:
- target: ldm.modules.encoders.modules.BERTEmbedder
- params:
- n_embed: 640
- n_layer: 32
- data:
- target: main.DataModuleFromConfig
- params:
- batch_size: 28
- num_workers: 10
- wrap: false
- train:
- target: ldm.data.previews.pytorch_dataset.PreviewsTrain
- params:
- size: 256
- validation:
- target: ldm.data.previews.pytorch_dataset.PreviewsValidation
- params:
- size: 256
|
