instruct first commit

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

+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

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

+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

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

+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

stable_diffusion/models/ldm/bsr_sr/config.yaml

+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

stable_diffusion/models/ldm/celeba256/config.yaml

+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

stable_diffusion/models/ldm/cin256/config.yaml

+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

stable_diffusion/models/ldm/ffhq256/config.yaml

+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

stable_diffusion/models/ldm/inpainting_big/config.yaml

+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__

stable_diffusion/models/ldm/layout2img-openimages256/config.yaml

+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

stable_diffusion/models/ldm/lsun_beds256/config.yaml

+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

stable_diffusion/models/ldm/lsun_churches256/config.yaml

+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

stable_diffusion/models/ldm/semantic_synthesis256/config.yaml

+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: 64
+    channels: 3
+    concat_mode: true
+    cond_stage_trainable: true
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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
+        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

stable_diffusion/models/ldm/semantic_synthesis512/config.yaml

+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

stable_diffusion/models/ldm/text2img256/config.yaml

+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

stable_diffusion/notebook_helpers.py

+from torchvision.datasets.utils import download_url
+from ldm.util import instantiate_from_config
+import torch
+import os
+# todo ?
+from google.colab import files
+from IPython.display import Image as ipyimg
+import ipywidgets as widgets
+from PIL import Image
+from numpy import asarray
+from einops import rearrange, repeat
+import torch, torchvision
+from ldm.models.diffusion.ddim import DDIMSampler
+from ldm.util import ismap
+import time
+from omegaconf import OmegaConf
+
+
+def download_models(mode):
+
+    if mode == "superresolution":
+        # this is the small bsr light model
+        url_conf = 'https://heibox.uni-heidelberg.de/f/31a76b13ea27482981b4/?dl=1'
+        url_ckpt = 'https://heibox.uni-heidelberg.de/f/578df07c8fc04ffbadf3/?dl=1'
+
+        path_conf = 'logs/diffusion/superresolution_bsr/configs/project.yaml'
+        path_ckpt = 'logs/diffusion/superresolution_bsr/checkpoints/last.ckpt'
+
+        download_url(url_conf, path_conf)
+        download_url(url_ckpt, path_ckpt)
+
+        path_conf = path_conf + '/?dl=1' # fix it
+        path_ckpt = path_ckpt + '/?dl=1' # fix it
+        return path_conf, path_ckpt
+
+    else:
+        raise NotImplementedError
+
+
+def load_model_from_config(config, ckpt):
+    print(f"Loading model from {ckpt}")
+    pl_sd = torch.load(ckpt, map_location="cpu")
+    global_step = pl_sd["global_step"]
+    sd = pl_sd["state_dict"]
+    model = instantiate_from_config(config.model)
+    m, u = model.load_state_dict(sd, strict=False)
+    model.cuda()
+    model.eval()
+    return {"model": model}, global_step
+
+
+def get_model(mode):
+    path_conf, path_ckpt = download_models(mode)
+    config = OmegaConf.load(path_conf)
+    model, step = load_model_from_config(config, path_ckpt)
+    return model
+
+
+def get_custom_cond(mode):
+    dest = "data/example_conditioning"
+
+    if mode == "superresolution":
+        uploaded_img = files.upload()
+        filename = next(iter(uploaded_img))
+        name, filetype = filename.split(".") # todo assumes just one dot in name !
+        os.rename(f"{filename}", f"{dest}/{mode}/custom_{name}.{filetype}")
+
+    elif mode == "text_conditional":
+        w = widgets.Text(value='A cake with cream!', disabled=True)
+        display(w)
+
+        with open(f"{dest}/{mode}/custom_{w.value[:20]}.txt", 'w') as f:
+            f.write(w.value)
+
+    elif mode == "class_conditional":
+        w = widgets.IntSlider(min=0, max=1000)
+        display(w)
+        with open(f"{dest}/{mode}/custom.txt", 'w') as f:
+            f.write(w.value)
+
+    else:
+        raise NotImplementedError(f"cond not implemented for mode{mode}")
+
+
+def get_cond_options(mode):
+    path = "data/example_conditioning"
+    path = os.path.join(path, mode)
+    onlyfiles = [f for f in sorted(os.listdir(path))]
+    return path, onlyfiles
+
+
+def select_cond_path(mode):
+    path = "data/example_conditioning"  # todo
+    path = os.path.join(path, mode)
+    onlyfiles = [f for f in sorted(os.listdir(path))]
+
+    selected = widgets.RadioButtons(
+        options=onlyfiles,
+        description='Select conditioning:',
+        disabled=False
+    )
+    display(selected)
+    selected_path = os.path.join(path, selected.value)
+    return selected_path
+
+
+def get_cond(mode, selected_path):
+    example = dict()
+    if mode == "superresolution":
+        up_f = 4
+        visualize_cond_img(selected_path)
+
+        c = Image.open(selected_path)
+        c = torch.unsqueeze(torchvision.transforms.ToTensor()(c), 0)
+        c_up = torchvision.transforms.functional.resize(c, size=[up_f * c.shape[2], up_f * c.shape[3]], antialias=True)
+        c_up = rearrange(c_up, '1 c h w -> 1 h w c')
+        c = rearrange(c, '1 c h w -> 1 h w c')
+        c = 2. * c - 1.
+
+        c = c.to(torch.device("cuda"))
+        example["LR_image"] = c
+        example["image"] = c_up
+
+    return example
+
+
+def visualize_cond_img(path):
+    display(ipyimg(filename=path))
+
+
+def run(model, selected_path, task, custom_steps, resize_enabled=False, classifier_ckpt=None, global_step=None):
+
+    example = get_cond(task, selected_path)
+
+    save_intermediate_vid = False
+    n_runs = 1
+    masked = False
+    guider = None
+    ckwargs = None
+    mode = 'ddim'
+    ddim_use_x0_pred = False
+    temperature = 1.
+    eta = 1.
+    make_progrow = True
+    custom_shape = None
+
+    height, width = example["image"].shape[1:3]
+    split_input = height >= 128 and width >= 128
+
+    if split_input:
+        ks = 128
+        stride = 64
+        vqf = 4  #
+        model.split_input_params = {"ks": (ks, ks), "stride": (stride, stride),
+                                    "vqf": vqf,
+                                    "patch_distributed_vq": True,
+                                    "tie_braker": False,
+                                    "clip_max_weight": 0.5,
+                                    "clip_min_weight": 0.01,
+                                    "clip_max_tie_weight": 0.5,
+                                    "clip_min_tie_weight": 0.01}
+    else:
+        if hasattr(model, "split_input_params"):
+            delattr(model, "split_input_params")
+
+    invert_mask = False
+
+    x_T = None
+    for n in range(n_runs):
+        if custom_shape is not None:
+            x_T = torch.randn(1, custom_shape[1], custom_shape[2], custom_shape[3]).to(model.device)
+            x_T = repeat(x_T, '1 c h w -> b c h w', b=custom_shape[0])
+
+        logs = make_convolutional_sample(example, model,
+                                         mode=mode, custom_steps=custom_steps,
+                                         eta=eta, swap_mode=False , masked=masked,
+                                         invert_mask=invert_mask, quantize_x0=False,
+                                         custom_schedule=None, decode_interval=10,
+                                         resize_enabled=resize_enabled, custom_shape=custom_shape,
+                                         temperature=temperature, noise_dropout=0.,
+                                         corrector=guider, corrector_kwargs=ckwargs, x_T=x_T, save_intermediate_vid=save_intermediate_vid,
+                                         make_progrow=make_progrow,ddim_use_x0_pred=ddim_use_x0_pred
+                                         )
+    return logs
+
+
+@torch.no_grad()
+def convsample_ddim(model, cond, steps, shape, eta=1.0, callback=None, normals_sequence=None,
+                    mask=None, x0=None, quantize_x0=False, img_callback=None,
+                    temperature=1., noise_dropout=0., score_corrector=None,
+                    corrector_kwargs=None, x_T=None, log_every_t=None
+                    ):
+
+    ddim = DDIMSampler(model)
+    bs = shape[0]  # dont know where this comes from but wayne
+    shape = shape[1:]  # cut batch dim
+    print(f"Sampling with eta = {eta}; steps: {steps}")
+    samples, intermediates = ddim.sample(steps, batch_size=bs, shape=shape, conditioning=cond, callback=callback,
+                                         normals_sequence=normals_sequence, quantize_x0=quantize_x0, eta=eta,
+                                         mask=mask, x0=x0, temperature=temperature, verbose=False,
+                                         score_corrector=score_corrector,
+                                         corrector_kwargs=corrector_kwargs, x_T=x_T)
+
+    return samples, intermediates
+
+
+@torch.no_grad()
+def make_convolutional_sample(batch, model, mode="vanilla", custom_steps=None, eta=1.0, swap_mode=False, masked=False,
+                              invert_mask=True, quantize_x0=False, custom_schedule=None, decode_interval=1000,
+                              resize_enabled=False, custom_shape=None, temperature=1., noise_dropout=0., corrector=None,
+                              corrector_kwargs=None, x_T=None, save_intermediate_vid=False, make_progrow=True,ddim_use_x0_pred=False):
+    log = dict()
+
+    z, c, x, xrec, xc = model.get_input(batch, model.first_stage_key,
+                                        return_first_stage_outputs=True,
+                                        force_c_encode=not (hasattr(model, 'split_input_params')
+                                                            and model.cond_stage_key == 'coordinates_bbox'),
+                                        return_original_cond=True)
+
+    log_every_t = 1 if save_intermediate_vid else None
+
+    if custom_shape is not None:
+        z = torch.randn(custom_shape)
+        print(f"Generating {custom_shape[0]} samples of shape {custom_shape[1:]}")
+
+    z0 = None
+
+    log["input"] = x
+    log["reconstruction"] = xrec
+
+    if ismap(xc):
+        log["original_conditioning"] = model.to_rgb(xc)
+        if hasattr(model, 'cond_stage_key'):
+            log[model.cond_stage_key] = model.to_rgb(xc)
+
+    else:
+        log["original_conditioning"] = xc if xc is not None else torch.zeros_like(x)
+        if model.cond_stage_model:
+            log[model.cond_stage_key] = xc if xc is not None else torch.zeros_like(x)
+            if model.cond_stage_key =='class_label':
+                log[model.cond_stage_key] = xc[model.cond_stage_key]
+
+    with model.ema_scope("Plotting"):
+        t0 = time.time()
+        img_cb = None
+
+        sample, intermediates = convsample_ddim(model, c, steps=custom_steps, shape=z.shape,
+                                                eta=eta,
+                                                quantize_x0=quantize_x0, img_callback=img_cb, mask=None, x0=z0,
+                                                temperature=temperature, noise_dropout=noise_dropout,
+                                                score_corrector=corrector, corrector_kwargs=corrector_kwargs,
+                                                x_T=x_T, log_every_t=log_every_t)
+        t1 = time.time()
+
+        if ddim_use_x0_pred:
+            sample = intermediates['pred_x0'][-1]
+
+    x_sample = model.decode_first_stage(sample)
+
+    try:
+        x_sample_noquant = model.decode_first_stage(sample, force_not_quantize=True)
+        log["sample_noquant"] = x_sample_noquant
+        log["sample_diff"] = torch.abs(x_sample_noquant - x_sample)
+    except:
+        pass
+
+    log["sample"] = x_sample
+    log["time"] = t1 - t0
+
+    return log
\ No newline at end of file

stable_diffusion/scripts/download_first_stages.sh

+#!/bin/bash
+wget -O models/first_stage_models/kl-f4/model.zip https://ommer-lab.com/files/latent-diffusion/kl-f4.zip
+wget -O models/first_stage_models/kl-f8/model.zip https://ommer-lab.com/files/latent-diffusion/kl-f8.zip
+wget -O models/first_stage_models/kl-f16/model.zip https://ommer-lab.com/files/latent-diffusion/kl-f16.zip
+wget -O models/first_stage_models/kl-f32/model.zip https://ommer-lab.com/files/latent-diffusion/kl-f32.zip
+wget -O models/first_stage_models/vq-f4/model.zip https://ommer-lab.com/files/latent-diffusion/vq-f4.zip
+wget -O models/first_stage_models/vq-f4-noattn/model.zip https://ommer-lab.com/files/latent-diffusion/vq-f4-noattn.zip
+wget -O models/first_stage_models/vq-f8/model.zip https://ommer-lab.com/files/latent-diffusion/vq-f8.zip
+wget -O models/first_stage_models/vq-f8-n256/model.zip https://ommer-lab.com/files/latent-diffusion/vq-f8-n256.zip
+wget -O models/first_stage_models/vq-f16/model.zip https://ommer-lab.com/files/latent-diffusion/vq-f16.zip
+
+
+
+cd models/first_stage_models/kl-f4
+unzip -o model.zip
+
+cd ../kl-f8
+unzip -o model.zip
+
+cd ../kl-f16
+unzip -o model.zip
+
+cd ../kl-f32
+unzip -o model.zip
+
+cd ../vq-f4
+unzip -o model.zip
+
+cd ../vq-f4-noattn
+unzip -o model.zip
+
+cd ../vq-f8
+unzip -o model.zip
+
+cd ../vq-f8-n256
+unzip -o model.zip
+
+cd ../vq-f16
+unzip -o model.zip
+
+cd ../..
\ No newline at end of file

stable_diffusion/scripts/download_models.sh

+#!/bin/bash
+wget -O models/ldm/celeba256/celeba-256.zip https://ommer-lab.com/files/latent-diffusion/celeba.zip
+wget -O models/ldm/ffhq256/ffhq-256.zip https://ommer-lab.com/files/latent-diffusion/ffhq.zip
+wget -O models/ldm/lsun_churches256/lsun_churches-256.zip https://ommer-lab.com/files/latent-diffusion/lsun_churches.zip
+wget -O models/ldm/lsun_beds256/lsun_beds-256.zip https://ommer-lab.com/files/latent-diffusion/lsun_bedrooms.zip
+wget -O models/ldm/text2img256/model.zip https://ommer-lab.com/files/latent-diffusion/text2img.zip
+wget -O models/ldm/cin256/model.zip https://ommer-lab.com/files/latent-diffusion/cin.zip
+wget -O models/ldm/semantic_synthesis512/model.zip https://ommer-lab.com/files/latent-diffusion/semantic_synthesis.zip
+wget -O models/ldm/semantic_synthesis256/model.zip https://ommer-lab.com/files/latent-diffusion/semantic_synthesis256.zip
+wget -O models/ldm/bsr_sr/model.zip https://ommer-lab.com/files/latent-diffusion/sr_bsr.zip
+wget -O models/ldm/layout2img-openimages256/model.zip https://ommer-lab.com/files/latent-diffusion/layout2img_model.zip
+wget -O models/ldm/inpainting_big/model.zip https://ommer-lab.com/files/latent-diffusion/inpainting_big.zip
+
+
+
+cd models/ldm/celeba256
+unzip -o celeba-256.zip
+
+cd ../ffhq256
+unzip -o ffhq-256.zip
+
+cd ../lsun_churches256
+unzip -o lsun_churches-256.zip
+
+cd ../lsun_beds256
+unzip -o lsun_beds-256.zip
+
+cd ../text2img256
+unzip -o model.zip
+
+cd ../cin256
+unzip -o model.zip
+
+cd ../semantic_synthesis512
+unzip -o model.zip
+
+cd ../semantic_synthesis256
+unzip -o model.zip
+
+cd ../bsr_sr
+unzip -o model.zip
+
+cd ../layout2img-openimages256
+unzip -o model.zip
+
+cd ../inpainting_big
+unzip -o model.zip
+
+cd ../..

stable_diffusion/scripts/img2img.py

+"""make variations of input image"""
+
+import argparse, os, sys, glob
+import PIL
+import torch
+import numpy as np
+from omegaconf import OmegaConf
+from PIL import Image
+from tqdm import tqdm, trange
+from itertools import islice
+from einops import rearrange, repeat
+from torchvision.utils import make_grid
+from torch import autocast
+from contextlib import nullcontext
+import time
+from pytorch_lightning import seed_everything
+
+from ldm.util import instantiate_from_config
+from ldm.models.diffusion.ddim import DDIMSampler
+from ldm.models.diffusion.plms import PLMSSampler
+
+
+def chunk(it, size):
+    it = iter(it)
+    return iter(lambda: tuple(islice(it, size)), ())
+
+
+def load_model_from_config(config, ckpt, verbose=False):
+    print(f"Loading model from {ckpt}")
+    pl_sd = torch.load(ckpt, map_location="cpu")
+    if "global_step" in pl_sd:
+        print(f"Global Step: {pl_sd['global_step']}")
+    sd = pl_sd["state_dict"]
+    model = instantiate_from_config(config.model)
+    m, u = model.load_state_dict(sd, strict=False)
+    if len(m) > 0 and verbose:
+        print("missing keys:")
+        print(m)
+    if len(u) > 0 and verbose:
+        print("unexpected keys:")
+        print(u)
+
+    model.cuda()
+    model.eval()
+    return model
+
+
+def load_img(path):
+    image = Image.open(path).convert("RGB")
+    w, h = image.size
+    print(f"loaded input image of size ({w}, {h}) from {path}")
+    w, h = map(lambda x: x - x % 32, (w, h))  # resize to integer multiple of 32
+    image = image.resize((w, h), resample=PIL.Image.LANCZOS)
+    image = np.array(image).astype(np.float32) / 255.0
+    image = image[None].transpose(0, 3, 1, 2)
+    image = torch.from_numpy(image)
+    return 2.*image - 1.
+
+
+def main():
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument(
+        "--prompt",
+        type=str,
+        nargs="?",
+        default="a painting of a virus monster playing guitar",
+        help="the prompt to render"
+    )
+
+    parser.add_argument(
+        "--init-img",
+        type=str,
+        nargs="?",
+        help="path to the input image"
+    )
+
+    parser.add_argument(
+        "--outdir",
+        type=str,
+        nargs="?",
+        help="dir to write results to",
+        default="outputs/img2img-samples"
+    )
+
+    parser.add_argument(
+        "--skip_grid",
+        action='store_true',
+        help="do not save a grid, only individual samples. Helpful when evaluating lots of samples",
+    )
+
+    parser.add_argument(
+        "--skip_save",
+        action='store_true',
+        help="do not save indiviual samples. For speed measurements.",
+    )
+
+    parser.add_argument(
+        "--ddim_steps",
+        type=int,
+        default=50,
+        help="number of ddim sampling steps",
+    )
+
+    parser.add_argument(
+        "--plms",
+        action='store_true',
+        help="use plms sampling",
+    )
+    parser.add_argument(
+        "--fixed_code",
+        action='store_true',
+        help="if enabled, uses the same starting code across all samples ",
+    )
+
+    parser.add_argument(
+        "--ddim_eta",
+        type=float,
+        default=0.0,
+        help="ddim eta (eta=0.0 corresponds to deterministic sampling",
+    )
+    parser.add_argument(
+        "--n_iter",
+        type=int,
+        default=1,
+        help="sample this often",
+    )
+    parser.add_argument(
+        "--C",
+        type=int,
+        default=4,
+        help="latent channels",
+    )
+    parser.add_argument(
+        "--f",
+        type=int,
+        default=8,
+        help="downsampling factor, most often 8 or 16",
+    )
+    parser.add_argument(
+        "--n_samples",
+        type=int,
+        default=2,
+        help="how many samples to produce for each given prompt. A.k.a batch size",
+    )
+    parser.add_argument(
+        "--n_rows",
+        type=int,
+        default=0,
+        help="rows in the grid (default: n_samples)",
+    )
+    parser.add_argument(
+        "--scale",
+        type=float,
+        default=5.0,
+        help="unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))",
+    )
+
+    parser.add_argument(
+        "--strength",
+        type=float,
+        default=0.75,
+        help="strength for noising/unnoising. 1.0 corresponds to full destruction of information in init image",
+    )
+    parser.add_argument(
+        "--from-file",
+        type=str,
+        help="if specified, load prompts from this file",
+    )
+    parser.add_argument(
+        "--config",
+        type=str,
+        default="configs/stable-diffusion/v1-inference.yaml",
+        help="path to config which constructs model",
+    )
+    parser.add_argument(
+        "--ckpt",
+        type=str,
+        default="models/ldm/stable-diffusion-v1/model.ckpt",
+        help="path to checkpoint of model",
+    )
+    parser.add_argument(
+        "--seed",
+        type=int,
+        default=42,
+        help="the seed (for reproducible sampling)",
+    )
+    parser.add_argument(
+        "--precision",
+        type=str,
+        help="evaluate at this precision",
+        choices=["full", "autocast"],
+        default="autocast"
+    )
+
+    opt = parser.parse_args()
+    seed_everything(opt.seed)
+
+    config = OmegaConf.load(f"{opt.config}")
+    model = load_model_from_config(config, f"{opt.ckpt}")
+
+    device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+    model = model.to(device)
+
+    if opt.plms:
+        raise NotImplementedError("PLMS sampler not (yet) supported")
+        sampler = PLMSSampler(model)
+    else:
+        sampler = DDIMSampler(model)
+
+    os.makedirs(opt.outdir, exist_ok=True)
+    outpath = opt.outdir
+
+    batch_size = opt.n_samples
+    n_rows = opt.n_rows if opt.n_rows > 0 else batch_size
+    if not opt.from_file:
+        prompt = opt.prompt
+        assert prompt is not None
+        data = [batch_size * [prompt]]
+
+    else:
+        print(f"reading prompts from {opt.from_file}")
+        with open(opt.from_file, "r") as f:
+            data = f.read().splitlines()
+            data = list(chunk(data, batch_size))
+
+    sample_path = os.path.join(outpath, "samples")
+    os.makedirs(sample_path, exist_ok=True)
+    base_count = len(os.listdir(sample_path))
+    grid_count = len(os.listdir(outpath)) - 1
+
+    assert os.path.isfile(opt.init_img)
+    init_image = load_img(opt.init_img).to(device)
+    init_image = repeat(init_image, '1 ... -> b ...', b=batch_size)
+    init_latent = model.get_first_stage_encoding(model.encode_first_stage(init_image))  # move to latent space
+
+    sampler.make_schedule(ddim_num_steps=opt.ddim_steps, ddim_eta=opt.ddim_eta, verbose=False)
+
+    assert 0. <= opt.strength <= 1., 'can only work with strength in [0.0, 1.0]'
+    t_enc = int(opt.strength * opt.ddim_steps)
+    print(f"target t_enc is {t_enc} steps")
+
+    precision_scope = autocast if opt.precision == "autocast" else nullcontext
+    with torch.no_grad():
+        with precision_scope("cuda"):
+            with model.ema_scope():
+                tic = time.time()
+                all_samples = list()
+                for n in trange(opt.n_iter, desc="Sampling"):
+                    for prompts in tqdm(data, desc="data"):
+                        uc = None
+                        if opt.scale != 1.0:
+                            uc = model.get_learned_conditioning(batch_size * [""])
+                        if isinstance(prompts, tuple):
+                            prompts = list(prompts)
+                        c = model.get_learned_conditioning(prompts)
+
+                        # encode (scaled latent)
+                        z_enc = sampler.stochastic_encode(init_latent, torch.tensor([t_enc]*batch_size).to(device))
+                        # decode it
+                        samples = sampler.decode(z_enc, c, t_enc, unconditional_guidance_scale=opt.scale,
+                                                 unconditional_conditioning=uc,)
+
+                        x_samples = model.decode_first_stage(samples)
+                        x_samples = torch.clamp((x_samples + 1.0) / 2.0, min=0.0, max=1.0)
+
+                        if not opt.skip_save:
+                            for x_sample in x_samples:
+                                x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
+                                Image.fromarray(x_sample.astype(np.uint8)).save(
+                                    os.path.join(sample_path, f"{base_count:05}.png"))
+                                base_count += 1
+                        all_samples.append(x_samples)
+
+                if not opt.skip_grid:
+                    # additionally, save as grid
+                    grid = torch.stack(all_samples, 0)
+                    grid = rearrange(grid, 'n b c h w -> (n b) c h w')
+                    grid = make_grid(grid, nrow=n_rows)
+
+                    # to image
+                    grid = 255. * rearrange(grid, 'c h w -> h w c').cpu().numpy()
+                    Image.fromarray(grid.astype(np.uint8)).save(os.path.join(outpath, f'grid-{grid_count:04}.png'))
+                    grid_count += 1
+
+                toc = time.time()
+
+    print(f"Your samples are ready and waiting for you here: \n{outpath} \n"
+          f" \nEnjoy.")
+
+
+if __name__ == "__main__":
+    main()

stable_diffusion/scripts/inpaint.py

+import argparse, os, sys, glob
+from omegaconf import OmegaConf
+from PIL import Image
+from tqdm import tqdm
+import numpy as np
+import torch
+from main import instantiate_from_config
+from ldm.models.diffusion.ddim import DDIMSampler
+
+
+def make_batch(image, mask, device):
+    image = np.array(Image.open(image).convert("RGB"))
+    image = image.astype(np.float32)/255.0
+    image = image[None].transpose(0,3,1,2)
+    image = torch.from_numpy(image)
+
+    mask = np.array(Image.open(mask).convert("L"))
+    mask = mask.astype(np.float32)/255.0
+    mask = mask[None,None]
+    mask[mask < 0.5] = 0
+    mask[mask >= 0.5] = 1
+    mask = torch.from_numpy(mask)
+
+    masked_image = (1-mask)*image
+
+    batch = {"image": image, "mask": mask, "masked_image": masked_image}
+    for k in batch:
+        batch[k] = batch[k].to(device=device)
+        batch[k] = batch[k]*2.0-1.0
+    return batch
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--indir",
+        type=str,
+        nargs="?",
+        help="dir containing image-mask pairs (`example.png` and `example_mask.png`)",
+    )
+    parser.add_argument(
+        "--outdir",
+        type=str,
+        nargs="?",
+        help="dir to write results to",
+    )
+    parser.add_argument(
+        "--steps",
+        type=int,
+        default=50,
+        help="number of ddim sampling steps",
+    )
+    opt = parser.parse_args()
+
+    masks = sorted(glob.glob(os.path.join(opt.indir, "*_mask.png")))
+    images = [x.replace("_mask.png", ".png") for x in masks]
+    print(f"Found {len(masks)} inputs.")
+
+    config = OmegaConf.load("models/ldm/inpainting_big/config.yaml")
+    model = instantiate_from_config(config.model)
+    model.load_state_dict(torch.load("models/ldm/inpainting_big/last.ckpt")["state_dict"],
+                          strict=False)
+
+    device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+    model = model.to(device)
+    sampler = DDIMSampler(model)
+
+    os.makedirs(opt.outdir, exist_ok=True)
+    with torch.no_grad():
+        with model.ema_scope():
+            for image, mask in tqdm(zip(images, masks)):
+                outpath = os.path.join(opt.outdir, os.path.split(image)[1])
+                batch = make_batch(image, mask, device=device)
+
+                # encode masked image and concat downsampled mask
+                c = model.cond_stage_model.encode(batch["masked_image"])
+                cc = torch.nn.functional.interpolate(batch["mask"],
+                                                     size=c.shape[-2:])
+                c = torch.cat((c, cc), dim=1)
+
+                shape = (c.shape[1]-1,)+c.shape[2:]
+                samples_ddim, _ = sampler.sample(S=opt.steps,
+                                                 conditioning=c,
+                                                 batch_size=c.shape[0],
+                                                 shape=shape,
+                                                 verbose=False)
+                x_samples_ddim = model.decode_first_stage(samples_ddim)
+
+                image = torch.clamp((batch["image"]+1.0)/2.0,
+                                    min=0.0, max=1.0)
+                mask = torch.clamp((batch["mask"]+1.0)/2.0,
+                                   min=0.0, max=1.0)
+                predicted_image = torch.clamp((x_samples_ddim+1.0)/2.0,
+                                              min=0.0, max=1.0)
+
+                inpainted = (1-mask)*image+mask*predicted_image
+                inpainted = inpainted.cpu().numpy().transpose(0,2,3,1)[0]*255
+                Image.fromarray(inpainted.astype(np.uint8)).save(outpath)

stable_diffusion/scripts/knn2img.py

+import argparse, os, sys, glob
+import clip
+import torch
+import torch.nn as nn
+import numpy as np
+from omegaconf import OmegaConf
+from PIL import Image
+from tqdm import tqdm, trange
+from itertools import islice
+from einops import rearrange, repeat
+from torchvision.utils import make_grid
+import scann
+import time
+from multiprocessing import cpu_count
+
+from ldm.util import instantiate_from_config, parallel_data_prefetch
+from ldm.models.diffusion.ddim import DDIMSampler
+from ldm.models.diffusion.plms import PLMSSampler
+from ldm.modules.encoders.modules import FrozenClipImageEmbedder, FrozenCLIPTextEmbedder
+
+DATABASES = [
+    "openimages",
+    "artbench-art_nouveau",
+    "artbench-baroque",
+    "artbench-expressionism",
+    "artbench-impressionism",
+    "artbench-post_impressionism",
+    "artbench-realism",
+    "artbench-romanticism",
+    "artbench-renaissance",
+    "artbench-surrealism",
+    "artbench-ukiyo_e",
+]
+
+
+def chunk(it, size):
+    it = iter(it)
+    return iter(lambda: tuple(islice(it, size)), ())
+
+
+def load_model_from_config(config, ckpt, verbose=False):
+    print(f"Loading model from {ckpt}")
+    pl_sd = torch.load(ckpt, map_location="cpu")
+    if "global_step" in pl_sd:
+        print(f"Global Step: {pl_sd['global_step']}")
+    sd = pl_sd["state_dict"]
+    model = instantiate_from_config(config.model)
+    m, u = model.load_state_dict(sd, strict=False)
+    if len(m) > 0 and verbose:
+        print("missing keys:")
+        print(m)
+    if len(u) > 0 and verbose:
+        print("unexpected keys:")
+        print(u)
+
+    model.cuda()
+    model.eval()
+    return model
+
+
+class Searcher(object):
+    def __init__(self, database, retriever_version='ViT-L/14'):
+        assert database in DATABASES
+        # self.database = self.load_database(database)
+        self.database_name = database
+        self.searcher_savedir = f'data/rdm/searchers/{self.database_name}'
+        self.database_path = f'data/rdm/retrieval_databases/{self.database_name}'
+        self.retriever = self.load_retriever(version=retriever_version)
+        self.database = {'embedding': [],
+                         'img_id': [],
+                         'patch_coords': []}
+        self.load_database()
+        self.load_searcher()
+
+    def train_searcher(self, k,
+                       metric='dot_product',
+                       searcher_savedir=None):
+
+        print('Start training searcher')
+        searcher = scann.scann_ops_pybind.builder(self.database['embedding'] /
+                                                  np.linalg.norm(self.database['embedding'], axis=1)[:, np.newaxis],
+                                                  k, metric)
+        self.searcher = searcher.score_brute_force().build()
+        print('Finish training searcher')
+
+        if searcher_savedir is not None:
+            print(f'Save trained searcher under "{searcher_savedir}"')
+            os.makedirs(searcher_savedir, exist_ok=True)
+            self.searcher.serialize(searcher_savedir)
+
+    def load_single_file(self, saved_embeddings):
+        compressed = np.load(saved_embeddings)
+        self.database = {key: compressed[key] for key in compressed.files}
+        print('Finished loading of clip embeddings.')
+
+    def load_multi_files(self, data_archive):
+        out_data = {key: [] for key in self.database}
+        for d in tqdm(data_archive, desc=f'Loading datapool from {len(data_archive)} individual files.'):
+            for key in d.files:
+                out_data[key].append(d[key])
+
+        return out_data
+
+    def load_database(self):
+
+        print(f'Load saved patch embedding from "{self.database_path}"')
+        file_content = glob.glob(os.path.join(self.database_path, '*.npz'))
+
+        if len(file_content) == 1:
+            self.load_single_file(file_content[0])
+        elif len(file_content) > 1:
+            data = [np.load(f) for f in file_content]
+            prefetched_data = parallel_data_prefetch(self.load_multi_files, data,
+                                                     n_proc=min(len(data), cpu_count()), target_data_type='dict')
+
+            self.database = {key: np.concatenate([od[key] for od in prefetched_data], axis=1)[0] for key in
+                             self.database}
+        else:
+            raise ValueError(f'No npz-files in specified path "{self.database_path}" is this directory existing?')
+
+        print(f'Finished loading of retrieval database of length {self.database["embedding"].shape[0]}.')
+
+    def load_retriever(self, version='ViT-L/14', ):
+        model = FrozenClipImageEmbedder(model=version)
+        if torch.cuda.is_available():
+            model.cuda()
+        model.eval()
+        return model
+
+    def load_searcher(self):
+        print(f'load searcher for database {self.database_name} from {self.searcher_savedir}')
+        self.searcher = scann.scann_ops_pybind.load_searcher(self.searcher_savedir)
+        print('Finished loading searcher.')
+
+    def search(self, x, k):
+        if self.searcher is None and self.database['embedding'].shape[0] < 2e4:
+            self.train_searcher(k)   # quickly fit searcher on the fly for small databases
+        assert self.searcher is not None, 'Cannot search with uninitialized searcher'
+        if isinstance(x, torch.Tensor):
+            x = x.detach().cpu().numpy()
+        if len(x.shape) == 3:
+            x = x[:, 0]
+        query_embeddings = x / np.linalg.norm(x, axis=1)[:, np.newaxis]
+
+        start = time.time()
+        nns, distances = self.searcher.search_batched(query_embeddings, final_num_neighbors=k)
+        end = time.time()
+
+        out_embeddings = self.database['embedding'][nns]
+        out_img_ids = self.database['img_id'][nns]
+        out_pc = self.database['patch_coords'][nns]
+
+        out = {'nn_embeddings': out_embeddings / np.linalg.norm(out_embeddings, axis=-1)[..., np.newaxis],
+               'img_ids': out_img_ids,
+               'patch_coords': out_pc,
+               'queries': x,
+               'exec_time': end - start,
+               'nns': nns,
+               'q_embeddings': query_embeddings}
+
+        return out
+
+    def __call__(self, x, n):
+        return self.search(x, n)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    # TODO: add n_neighbors and modes (text-only, text-image-retrieval, image-image retrieval etc)
+    # TODO: add 'image variation' mode when knn=0 but a single image is given instead of a text prompt?
+    parser.add_argument(
+        "--prompt",
+        type=str,
+        nargs="?",
+        default="a painting of a virus monster playing guitar",
+        help="the prompt to render"
+    )
+
+    parser.add_argument(
+        "--outdir",
+        type=str,
+        nargs="?",
+        help="dir to write results to",
+        default="outputs/txt2img-samples"
+    )
+
+    parser.add_argument(
+        "--skip_grid",
+        action='store_true',
+        help="do not save a grid, only individual samples. Helpful when evaluating lots of samples",
+    )
+
+    parser.add_argument(
+        "--ddim_steps",
+        type=int,
+        default=50,
+        help="number of ddim sampling steps",
+    )
+
+    parser.add_argument(
+        "--n_repeat",
+        type=int,
+        default=1,
+        help="number of repeats in CLIP latent space",
+    )
+
+    parser.add_argument(
+        "--plms",
+        action='store_true',
+        help="use plms sampling",
+    )
+
+    parser.add_argument(
+        "--ddim_eta",
+        type=float,
+        default=0.0,
+        help="ddim eta (eta=0.0 corresponds to deterministic sampling",
+    )
+    parser.add_argument(
+        "--n_iter",
+        type=int,
+        default=1,
+        help="sample this often",
+    )
+
+    parser.add_argument(
+        "--H",
+        type=int,
+        default=768,
+        help="image height, in pixel space",
+    )
+
+    parser.add_argument(
+        "--W",
+        type=int,
+        default=768,
+        help="image width, in pixel space",
+    )
+
+    parser.add_argument(
+        "--n_samples",
+        type=int,
+        default=3,
+        help="how many samples to produce for each given prompt. A.k.a batch size",
+    )
+
+    parser.add_argument(
+        "--n_rows",
+        type=int,
+        default=0,
+        help="rows in the grid (default: n_samples)",
+    )
+
+    parser.add_argument(
+        "--scale",
+        type=float,
+        default=5.0,
+        help="unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))",
+    )
+
+    parser.add_argument(
+        "--from-file",
+        type=str,
+        help="if specified, load prompts from this file",
+    )
+
+    parser.add_argument(
+        "--config",
+        type=str,
+        default="configs/retrieval-augmented-diffusion/768x768.yaml",
+        help="path to config which constructs model",
+    )
+
+    parser.add_argument(
+        "--ckpt",
+        type=str,
+        default="models/rdm/rdm768x768/model.ckpt",
+        help="path to checkpoint of model",
+    )
+
+    parser.add_argument(
+        "--clip_type",
+        type=str,
+        default="ViT-L/14",
+        help="which CLIP model to use for retrieval and NN encoding",
+    )
+    parser.add_argument(
+        "--database",
+        type=str,
+        default='artbench-surrealism',
+        choices=DATABASES,
+        help="The database used for the search, only applied when --use_neighbors=True",
+    )
+    parser.add_argument(
+        "--use_neighbors",
+        default=False,
+        action='store_true',
+        help="Include neighbors in addition to text prompt for conditioning",
+    )
+    parser.add_argument(
+        "--knn",
+        default=10,
+        type=int,
+        help="The number of included neighbors, only applied when --use_neighbors=True",
+    )
+
+    opt = parser.parse_args()
+
+    config = OmegaConf.load(f"{opt.config}")
+    model = load_model_from_config(config, f"{opt.ckpt}")
+
+    device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+    model = model.to(device)
+
+    clip_text_encoder = FrozenCLIPTextEmbedder(opt.clip_type).to(device)
+
+    if opt.plms:
+        sampler = PLMSSampler(model)
+    else:
+        sampler = DDIMSampler(model)
+
+    os.makedirs(opt.outdir, exist_ok=True)
+    outpath = opt.outdir
+
+    batch_size = opt.n_samples
+    n_rows = opt.n_rows if opt.n_rows > 0 else batch_size
+    if not opt.from_file:
+        prompt = opt.prompt
+        assert prompt is not None
+        data = [batch_size * [prompt]]
+
+    else:
+        print(f"reading prompts from {opt.from_file}")
+        with open(opt.from_file, "r") as f:
+            data = f.read().splitlines()
+            data = list(chunk(data, batch_size))
+
+    sample_path = os.path.join(outpath, "samples")
+    os.makedirs(sample_path, exist_ok=True)
+    base_count = len(os.listdir(sample_path))
+    grid_count = len(os.listdir(outpath)) - 1
+
+    print(f"sampling scale for cfg is {opt.scale:.2f}")
+
+    searcher = None
+    if opt.use_neighbors:
+        searcher = Searcher(opt.database)
+
+    with torch.no_grad():
+        with model.ema_scope():
+            for n in trange(opt.n_iter, desc="Sampling"):
+                all_samples = list()
+                for prompts in tqdm(data, desc="data"):
+                    print("sampling prompts:", prompts)
+                    if isinstance(prompts, tuple):
+                        prompts = list(prompts)
+                    c = clip_text_encoder.encode(prompts)
+                    uc = None
+                    if searcher is not None:
+                        nn_dict = searcher(c, opt.knn)
+                        c = torch.cat([c, torch.from_numpy(nn_dict['nn_embeddings']).cuda()], dim=1)
+                    if opt.scale != 1.0:
+                        uc = torch.zeros_like(c)
+                    if isinstance(prompts, tuple):
+                        prompts = list(prompts)
+                    shape = [16, opt.H // 16, opt.W // 16]  # note: currently hardcoded for f16 model
+                    samples_ddim, _ = sampler.sample(S=opt.ddim_steps,
+                                                     conditioning=c,
+                                                     batch_size=c.shape[0],
+                                                     shape=shape,
+                                                     verbose=False,
+                                                     unconditional_guidance_scale=opt.scale,
+                                                     unconditional_conditioning=uc,
+                                                     eta=opt.ddim_eta,
+                                                     )
+
+                    x_samples_ddim = model.decode_first_stage(samples_ddim)
+                    x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
+
+                    for x_sample in x_samples_ddim:
+                        x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
+                        Image.fromarray(x_sample.astype(np.uint8)).save(
+                            os.path.join(sample_path, f"{base_count:05}.png"))
+                        base_count += 1
+                    all_samples.append(x_samples_ddim)
+
+                if not opt.skip_grid:
+                    # additionally, save as grid
+                    grid = torch.stack(all_samples, 0)
+                    grid = rearrange(grid, 'n b c h w -> (n b) c h w')
+                    grid = make_grid(grid, nrow=n_rows)
+
+                    # to image
+                    grid = 255. * rearrange(grid, 'c h w -> h w c').cpu().numpy()
+                    Image.fromarray(grid.astype(np.uint8)).save(os.path.join(outpath, f'grid-{grid_count:04}.png'))
+                    grid_count += 1
+
+    print(f"Your samples are ready and waiting for you here: \n{outpath} \nEnjoy.")