add code

models/first_stage_models/kl-f16/config.yaml

@@ -0,0 +1,44 @@
+model:
+  base_learning_rate: 4.5e-06
+  target: ldm.models.autoencoder.AutoencoderKL
+  params:
+    monitor: val/rec_loss
+    embed_dim: 16
+    lossconfig:
+      target: ldm.modules.losses.LPIPSWithDiscriminator
+      params:
+        disc_start: 50001
+        kl_weight: 1.0e-06
+        disc_weight: 0.5
+    ddconfig:
+      double_z: true
+      z_channels: 16
+      resolution: 256
+      in_channels: 3
+      out_ch: 3
+      ch: 128
+      ch_mult:
+      - 1
+      - 1
+      - 2
+      - 2
+      - 4
+      num_res_blocks: 2
+      attn_resolutions:
+      - 16
+      dropout: 0.0
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 6
+    wrap: true
+    train:
+      target: ldm.data.openimages.FullOpenImagesTrain
+      params:
+        size: 384
+        crop_size: 256
+    validation:
+      target: ldm.data.openimages.FullOpenImagesValidation
+      params:
+        size: 384
+        crop_size: 256

models/first_stage_models/kl-f32/config.yaml

@@ -0,0 +1,46 @@
+model:
+  base_learning_rate: 4.5e-06
+  target: ldm.models.autoencoder.AutoencoderKL
+  params:
+    monitor: val/rec_loss
+    embed_dim: 64
+    lossconfig:
+      target: ldm.modules.losses.LPIPSWithDiscriminator
+      params:
+        disc_start: 50001
+        kl_weight: 1.0e-06
+        disc_weight: 0.5
+    ddconfig:
+      double_z: true
+      z_channels: 64
+      resolution: 256
+      in_channels: 3
+      out_ch: 3
+      ch: 128
+      ch_mult:
+      - 1
+      - 1
+      - 2
+      - 2
+      - 4
+      - 4
+      num_res_blocks: 2
+      attn_resolutions:
+      - 16
+      - 8
+      dropout: 0.0
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 6
+    wrap: true
+    train:
+      target: ldm.data.openimages.FullOpenImagesTrain
+      params:
+        size: 384
+        crop_size: 256
+    validation:
+      target: ldm.data.openimages.FullOpenImagesValidation
+      params:
+        size: 384
+        crop_size: 256

models/first_stage_models/kl-f4/config.yaml

@@ -0,0 +1,41 @@
+model:
+  base_learning_rate: 4.5e-06
+  target: ldm.models.autoencoder.AutoencoderKL
+  params:
+    monitor: val/rec_loss
+    embed_dim: 3
+    lossconfig:
+      target: ldm.modules.losses.LPIPSWithDiscriminator
+      params:
+        disc_start: 50001
+        kl_weight: 1.0e-06
+        disc_weight: 0.5
+    ddconfig:
+      double_z: true
+      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
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 10
+    wrap: true
+    train:
+      target: ldm.data.openimages.FullOpenImagesTrain
+      params:
+        size: 384
+        crop_size: 256
+    validation:
+      target: ldm.data.openimages.FullOpenImagesValidation
+      params:
+        size: 384
+        crop_size: 256

models/first_stage_models/kl-f8/config.yaml

@@ -0,0 +1,42 @@
+model:
+  base_learning_rate: 4.5e-06
+  target: ldm.models.autoencoder.AutoencoderKL
+  params:
+    monitor: val/rec_loss
+    embed_dim: 4
+    lossconfig:
+      target: ldm.modules.losses.LPIPSWithDiscriminator
+      params:
+        disc_start: 50001
+        kl_weight: 1.0e-06
+        disc_weight: 0.5
+    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
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 4
+    wrap: true
+    train:
+      target: ldm.data.openimages.FullOpenImagesTrain
+      params:
+        size: 384
+        crop_size: 256
+    validation:
+      target: ldm.data.openimages.FullOpenImagesValidation
+      params:
+        size: 384
+        crop_size: 256

models/first_stage_models/vq-f16/config.yaml

@@ -0,0 +1,49 @@
+model:
+  base_learning_rate: 4.5e-06
+  target: ldm.models.autoencoder.VQModel
+  params:
+    embed_dim: 8
+    n_embed: 16384
+    ddconfig:
+      double_z: false
+      z_channels: 8
+      resolution: 256
+      in_channels: 3
+      out_ch: 3
+      ch: 128
+      ch_mult:
+      - 1
+      - 1
+      - 2
+      - 2
+      - 4
+      num_res_blocks: 2
+      attn_resolutions:
+      - 16
+      dropout: 0.0
+    lossconfig:
+      target: taming.modules.losses.vqperceptual.VQLPIPSWithDiscriminator
+      params:
+        disc_conditional: false
+        disc_in_channels: 3
+        disc_start: 250001
+        disc_weight: 0.75
+        disc_num_layers: 2
+        codebook_weight: 1.0
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 14
+    num_workers: 20
+    wrap: true
+    train:
+      target: ldm.data.openimages.FullOpenImagesTrain
+      params:
+        size: 384
+        crop_size: 256
+    validation:
+      target: ldm.data.openimages.FullOpenImagesValidation
+      params:
+        size: 384
+        crop_size: 256

models/first_stage_models/vq-f4-noattn/config.yaml

@@ -0,0 +1,46 @@
+model:
+  base_learning_rate: 4.5e-06
+  target: ldm.models.autoencoder.VQModel
+  params:
+    embed_dim: 3
+    n_embed: 8192
+    monitor: val/rec_loss
+
+    ddconfig:
+      attn_type: none
+      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: taming.modules.losses.vqperceptual.VQLPIPSWithDiscriminator
+      params:
+        disc_conditional: false
+        disc_in_channels: 3
+        disc_start: 11
+        disc_weight: 0.75
+        codebook_weight: 1.0
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 8
+    num_workers: 12
+    wrap: true
+    train:
+      target: ldm.data.openimages.FullOpenImagesTrain
+      params:
+        crop_size: 256
+    validation:
+      target: ldm.data.openimages.FullOpenImagesValidation
+      params:
+        crop_size: 256

models/first_stage_models/vq-f4/config.yaml

@@ -0,0 +1,45 @@
+model:
+  base_learning_rate: 4.5e-06
+  target: ldm.models.autoencoder.VQModel
+  params:
+    embed_dim: 3
+    n_embed: 8192
+    monitor: val/rec_loss
+
+    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: taming.modules.losses.vqperceptual.VQLPIPSWithDiscriminator
+      params:
+        disc_conditional: false
+        disc_in_channels: 3
+        disc_start: 0
+        disc_weight: 0.75
+        codebook_weight: 1.0
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 8
+    num_workers: 16
+    wrap: true
+    train:
+      target: ldm.data.openimages.FullOpenImagesTrain
+      params:
+        crop_size: 256
+    validation:
+      target: ldm.data.openimages.FullOpenImagesValidation
+      params:
+        crop_size: 256

models/first_stage_models/vq-f8-n256/config.yaml

@@ -0,0 +1,48 @@
+model:
+  base_learning_rate: 4.5e-06
+  target: ldm.models.autoencoder.VQModel
+  params:
+    embed_dim: 4
+    n_embed: 256
+    monitor: val/rec_loss
+    ddconfig:
+      double_z: false
+      z_channels: 4
+      resolution: 256
+      in_channels: 3
+      out_ch: 3
+      ch: 128
+      ch_mult:
+      - 1
+      - 2
+      - 2
+      - 4
+      num_res_blocks: 2
+      attn_resolutions:
+      - 32
+      dropout: 0.0
+    lossconfig:
+      target: taming.modules.losses.vqperceptual.VQLPIPSWithDiscriminator
+      params:
+        disc_conditional: false
+        disc_in_channels: 3
+        disc_start: 250001
+        disc_weight: 0.75
+        codebook_weight: 1.0
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 10
+    num_workers: 20
+    wrap: true
+    train:
+      target: ldm.data.openimages.FullOpenImagesTrain
+      params:
+        size: 384
+        crop_size: 256
+    validation:
+      target: ldm.data.openimages.FullOpenImagesValidation
+      params:
+        size: 384
+        crop_size: 256

models/first_stage_models/vq-f8/config.yaml

@@ -0,0 +1,48 @@
+model:
+  base_learning_rate: 4.5e-06
+  target: ldm.models.autoencoder.VQModel
+  params:
+    embed_dim: 4
+    n_embed: 16384
+    monitor: val/rec_loss
+    ddconfig:
+      double_z: false
+      z_channels: 4
+      resolution: 256
+      in_channels: 3
+      out_ch: 3
+      ch: 128
+      ch_mult:
+      - 1
+      - 2
+      - 2
+      - 4
+      num_res_blocks: 2
+      attn_resolutions:
+      - 32
+      dropout: 0.0
+    lossconfig:
+      target: taming.modules.losses.vqperceptual.VQLPIPSWithDiscriminator
+      params:
+        disc_conditional: false
+        disc_in_channels: 3
+        disc_num_layers: 2
+        disc_start: 1
+        disc_weight: 0.6
+        codebook_weight: 1.0
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 10
+    num_workers: 20
+    wrap: true
+    train:
+      target: ldm.data.openimages.FullOpenImagesTrain
+      params:
+        size: 384
+        crop_size: 256
+    validation:
+      target: ldm.data.openimages.FullOpenImagesValidation
+      params:
+        size: 384
+        crop_size: 256

models/ldm/bsr_sr/config.yaml

@@ -0,0 +1,80 @@
+model:
+  base_learning_rate: 1.0e-06
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.0015
+    linear_end: 0.0155
+    log_every_t: 100
+    timesteps: 1000
+    loss_type: l2
+    first_stage_key: image
+    cond_stage_key: LR_image
+    image_size: 64
+    channels: 3
+    concat_mode: true
+    cond_stage_trainable: false
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        in_channels: 6
+        out_channels: 3
+        model_channels: 160
+        attention_resolutions:
+        - 16
+        - 8
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 2
+        - 4
+        num_head_channels: 32
+    first_stage_config:
+      target: ldm.models.autoencoder.VQModelInterface
+      params:
+        embed_dim: 3
+        n_embed: 8192
+        monitor: val/rec_loss
+        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: torch.nn.Identity
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 64
+    wrap: false
+    num_workers: 12
+    train:
+      target: ldm.data.openimages.SuperresOpenImagesAdvancedTrain
+      params:
+        size: 256
+        degradation: bsrgan_light
+        downscale_f: 4
+        min_crop_f: 0.5
+        max_crop_f: 1.0
+        random_crop: true
+    validation:
+      target: ldm.data.openimages.SuperresOpenImagesAdvancedValidation
+      params:
+        size: 256
+        degradation: bsrgan_light
+        downscale_f: 4
+        min_crop_f: 0.5
+        max_crop_f: 1.0
+        random_crop: true

models/ldm/celeba256/config.yaml

@@ -0,0 +1,70 @@
+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: class_label
+    image_size: 64
+    channels: 3
+    cond_stage_trainable: false
+    concat_mode: false
+    monitor: val/loss
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        in_channels: 3
+        out_channels: 3
+        model_channels: 224
+        attention_resolutions:
+        - 8
+        - 4
+        - 2
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 3
+        - 4
+        num_head_channels: 32
+    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: __is_unconditional__
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 48
+    num_workers: 5
+    wrap: false
+    train:
+      target: ldm.data.faceshq.CelebAHQTrain
+      params:
+        size: 256
+    validation:
+      target: ldm.data.faceshq.CelebAHQValidation
+      params:
+        size: 256

models/ldm/cin256/config.yaml

@@ -0,0 +1,80 @@
+model:
+  base_learning_rate: 1.0e-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: class_label
+    image_size: 32
+    channels: 4
+    cond_stage_trainable: true
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32
+        in_channels: 4
+        out_channels: 4
+        model_channels: 256
+        attention_resolutions:
+        - 4
+        - 2
+        - 1
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 4
+        num_head_channels: 32
+        use_spatial_transformer: true
+        transformer_depth: 1
+        context_dim: 512
+    first_stage_config:
+      target: ldm.models.autoencoder.VQModelInterface
+      params:
+        embed_dim: 4
+        n_embed: 16384
+        ddconfig:
+          double_z: false
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 2
+          - 4
+          num_res_blocks: 2
+          attn_resolutions:
+          - 32
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.ClassEmbedder
+      params:
+        embed_dim: 512
+        key: class_label
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 64
+    num_workers: 12
+    wrap: false
+    train:
+      target: ldm.data.imagenet.ImageNetTrain
+      params:
+        config:
+          size: 256
+    validation:
+      target: ldm.data.imagenet.ImageNetValidation
+      params:
+        config:
+          size: 256

models/ldm/ffhq256/config.yaml

@@ -0,0 +1,70 @@
+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: class_label
+    image_size: 64
+    channels: 3
+    cond_stage_trainable: false
+    concat_mode: false
+    monitor: val/loss
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        in_channels: 3
+        out_channels: 3
+        model_channels: 224
+        attention_resolutions:
+        - 8
+        - 4
+        - 2
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 3
+        - 4
+        num_head_channels: 32
+    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: __is_unconditional__
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 42
+    num_workers: 5
+    wrap: false
+    train:
+      target: ldm.data.faceshq.FFHQTrain
+      params:
+        size: 256
+    validation:
+      target: ldm.data.faceshq.FFHQValidation
+      params:
+        size: 256

models/ldm/inpainting_big/config.yaml

@@ -0,0 +1,67 @@
+model:
+  base_learning_rate: 1.0e-06
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.0015
+    linear_end: 0.0205
+    log_every_t: 100
+    timesteps: 1000
+    loss_type: l1
+    first_stage_key: image
+    cond_stage_key: masked_image
+    image_size: 64
+    channels: 3
+    concat_mode: true
+    monitor: val/loss
+    scheduler_config:
+      target: ldm.lr_scheduler.LambdaWarmUpCosineScheduler
+      params:
+        verbosity_interval: 0
+        warm_up_steps: 1000
+        max_decay_steps: 50000
+        lr_start: 0.001
+        lr_max: 0.1
+        lr_min: 0.0001
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        in_channels: 7
+        out_channels: 3
+        model_channels: 256
+        attention_resolutions:
+        - 8
+        - 4
+        - 2
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 3
+        - 4
+        num_heads: 8
+        resblock_updown: true
+    first_stage_config:
+      target: ldm.models.autoencoder.VQModelInterface
+      params:
+        embed_dim: 3
+        n_embed: 8192
+        monitor: val/rec_loss
+        ddconfig:
+          attn_type: none
+          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: ldm.modules.losses.contperceptual.DummyLoss
+    cond_stage_config: __is_first_stage__

models/ldm/layout2img-openimages256/config.yaml

@@ -0,0 +1,81 @@
+model:
+  base_learning_rate: 2.0e-06
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.0015
+    linear_end: 0.0205
+    log_every_t: 100
+    timesteps: 1000
+    loss_type: l1
+    first_stage_key: image
+    cond_stage_key: coordinates_bbox
+    image_size: 64
+    channels: 3
+    conditioning_key: crossattn
+    cond_stage_trainable: true
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        in_channels: 3
+        out_channels: 3
+        model_channels: 128
+        attention_resolutions:
+        - 8
+        - 4
+        - 2
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 3
+        - 4
+        num_head_channels: 32
+        use_spatial_transformer: true
+        transformer_depth: 3
+        context_dim: 512
+    first_stage_config:
+      target: ldm.models.autoencoder.VQModelInterface
+      params:
+        embed_dim: 3
+        n_embed: 8192
+        monitor: val/rec_loss
+        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: 512
+        n_layer: 16
+        vocab_size: 8192
+        max_seq_len: 92
+        use_tokenizer: false
+    monitor: val/loss_simple_ema
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 24
+    wrap: false
+    num_workers: 10
+    train:
+      target: ldm.data.openimages.OpenImagesBBoxTrain
+      params:
+        size: 256
+    validation:
+      target: ldm.data.openimages.OpenImagesBBoxValidation
+      params:
+        size: 256

models/ldm/lsun_beds256/config.yaml

@@ -0,0 +1,70 @@
+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: class_label
+    image_size: 64
+    channels: 3
+    cond_stage_trainable: false
+    concat_mode: false
+    monitor: val/loss
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        in_channels: 3
+        out_channels: 3
+        model_channels: 224
+        attention_resolutions:
+        - 8
+        - 4
+        - 2
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 3
+        - 4
+        num_head_channels: 32
+    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: __is_unconditional__
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 48
+    num_workers: 5
+    wrap: false
+    train:
+      target: ldm.data.lsun.LSUNBedroomsTrain
+      params:
+        size: 256
+    validation:
+      target: ldm.data.lsun.LSUNBedroomsValidation
+      params:
+        size: 256

models/ldm/lsun_churches256/config.yaml

@@ -0,0 +1,92 @@
+model:
+  base_learning_rate: 5.0e-05
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.0015
+    linear_end: 0.0155
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    loss_type: l1
+    first_stage_key: image
+    cond_stage_key: image
+    image_size: 32
+    channels: 4
+    cond_stage_trainable: false
+    concat_mode: false
+    scale_by_std: true
+    monitor: val/loss_simple_ema
+    scheduler_config:
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps:
+        - 10000
+        cycle_lengths:
+        - 10000000000000
+        f_start:
+        - 1.0e-06
+        f_max:
+        - 1.0
+        f_min:
+        - 1.0
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32
+        in_channels: 4
+        out_channels: 4
+        model_channels: 192
+        attention_resolutions:
+        - 1
+        - 2
+        - 4
+        - 8
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 2
+        - 4
+        - 4
+        num_heads: 8
+        use_scale_shift_norm: true
+        resblock_updown: true
+    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: '__is_unconditional__'
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 96
+    num_workers: 5
+    wrap: false
+    train:
+      target: ldm.data.lsun.LSUNChurchesTrain
+      params:
+        size: 256
+    validation:
+      target: ldm.data.lsun.LSUNChurchesValidation
+      params:
+        size: 256

models/ldm/semantic_synthesis512/config.yaml

@@ -0,0 +1,78 @@
+model:
+  base_learning_rate: 1.0e-06
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.0015
+    linear_end: 0.0205
+    log_every_t: 100
+    timesteps: 1000
+    loss_type: l1
+    first_stage_key: image
+    cond_stage_key: segmentation
+    image_size: 128
+    channels: 3
+    concat_mode: true
+    cond_stage_trainable: true
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 128
+        in_channels: 6
+        out_channels: 3
+        model_channels: 128
+        attention_resolutions:
+        - 32
+        - 16
+        - 8
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 4
+        - 8
+        num_heads: 8
+    first_stage_config:
+      target: ldm.models.autoencoder.VQModelInterface
+      params:
+        embed_dim: 3
+        n_embed: 8192
+        monitor: val/rec_loss
+        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.SpatialRescaler
+      params:
+        n_stages: 2
+        in_channels: 182
+        out_channels: 3
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 8
+    wrap: false
+    num_workers: 10
+    train:
+      target: ldm.data.landscapes.RFWTrain
+      params:
+        size: 768
+        crop_size: 512
+        segmentation_to_float32: true
+    validation:
+      target: ldm.data.landscapes.RFWValidation
+      params:
+        size: 768
+        crop_size: 512
+        segmentation_to_float32: true

models/ldm/text2img256/config.yaml

@@ -0,0 +1,77 @@
+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