add files

app.py

@@ -0,0 +1,15 @@
+import streamlit as st
+import os
+os.system('pip install -e src/taming-transformers/.')
+os.system('pip install -e src/clip/.')
+os.system('pip install -e .')
+from scripts.stable_txt2img import main
+# st.title('AI Gen for SG')
+st.markdown("<h1 style='text-align: center; color: orange;'>AI Gen for SG</h1>", unsafe_allow_html=True)
+st.markdown("<h3 style='text-align: center; color: black;'>ShowLab</h3>", unsafe_allow_html=True)
+st.write('Contributors: Mike Zheng Shou, Shuning Chang, Yufei Shi, Zihan Fan, Xiangdong Zhou')
+text = st.text_input('Enter your prompt', value='', key=None)
+img = main(text)
+# st.write(text)
+if text:
+    st.image(img, caption=text)

configs/autoencoder/autoencoder_kl_16x16x16.yaml

@@ -0,0 +1,54 @@
+model:
+  base_learning_rate: 4.5e-6
+  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: 0.000001
+        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_down = len(ch_mult)-1
+      num_res_blocks: 2
+      attn_resolutions: [16]
+      dropout: 0.0
+
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 12
+    wrap: True
+    train:
+      target: ldm.data.imagenet.ImageNetSRTrain
+      params:
+        size: 256
+        degradation: pil_nearest
+    validation:
+      target: ldm.data.imagenet.ImageNetSRValidation
+      params:
+        size: 256
+        degradation: pil_nearest
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: True
+
+  trainer:
+    benchmark: True
+    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_32x32x4.yaml

@@ -0,0 +1,53 @@
+model:
+  base_learning_rate: 4.5e-6
+  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: 0.000001
+        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_down = len(ch_mult)-1
+      num_res_blocks: 2
+      attn_resolutions: [ ]
+      dropout: 0.0
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 12
+    wrap: True
+    train:
+      target: ldm.data.imagenet.ImageNetSRTrain
+      params:
+        size: 256
+        degradation: pil_nearest
+    validation:
+      target: ldm.data.imagenet.ImageNetSRValidation
+      params:
+        size: 256
+        degradation: pil_nearest
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: True
+
+  trainer:
+    benchmark: True
+    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_64x64x3.yaml

@@ -0,0 +1,54 @@
+model:
+  base_learning_rate: 4.5e-6
+  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: 0.000001
+        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_down = len(ch_mult)-1
+      num_res_blocks: 2
+      attn_resolutions: [ ]
+      dropout: 0.0
+
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 12
+    wrap: True
+    train:
+      target: ldm.data.imagenet.ImageNetSRTrain
+      params:
+        size: 256
+        degradation: pil_nearest
+    validation:
+      target: ldm.data.imagenet.ImageNetSRValidation
+      params:
+        size: 256
+        degradation: pil_nearest
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: True
+
+  trainer:
+    benchmark: True
+    accumulate_grad_batches: 2

configs/autoencoder/autoencoder_kl_8x8x64.yaml

@@ -0,0 +1,53 @@
+model:
+  base_learning_rate: 4.5e-6
+  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: 0.000001
+        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_down = len(ch_mult)-1
+      num_res_blocks: 2
+      attn_resolutions: [16,8]
+      dropout: 0.0
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 12
+    wrap: True
+    train:
+      target: ldm.data.imagenet.ImageNetSRTrain
+      params:
+        size: 256
+        degradation: pil_nearest
+    validation:
+      target: ldm.data.imagenet.ImageNetSRValidation
+      params:
+        size: 256
+        degradation: pil_nearest
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: True
+
+  trainer:
+    benchmark: True
+    accumulate_grad_batches: 2

configs/latent-diffusion/celebahq-ldm-vq-4.yaml

@@ -0,0 +1,86 @@
+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
+    image_size: 64
+    channels: 3
+    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: 224
+        attention_resolutions:
+        # note: this isn\t actually the resolution but
+        # the downsampling factor, i.e. this corresnponds to
+        # attention on spatial resolution 8,16,32, as the
+        # spatial reolution of the latents is 64 for f4
+        - 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
+        ckpt_path: models/first_stage_models/vq-f4/model.ckpt
+        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: taming.data.faceshq.CelebAHQTrain
+      params:
+        size: 256
+    validation:
+      target: taming.data.faceshq.CelebAHQValidation
+      params:
+        size: 256
+
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 5000
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True

configs/latent-diffusion/cin-ldm-vq-f8.yaml

@@ -0,0 +1,98 @@
+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:
+        #note: this isn\t actually the resolution but
+        # the downsampling factor, i.e. this corresnponds to
+        # attention on spatial resolution 8,16,32, as the
+        # spatial reolution of the latents is 32 for f8
+        - 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
+        ckpt_path: configs/first_stage_models/vq-f8/model.yaml
+        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
+
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 5000
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True

configs/latent-diffusion/cin256-v2.yaml

@@ -0,0 +1,68 @@
+model:
+  base_learning_rate: 0.0001
+  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: true
+    conditioning_key: crossattn
+    monitor: val/loss
+    use_ema: False
+    
+    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_heads: 1
+        use_spatial_transformer: true
+        transformer_depth: 1
+        context_dim: 512
+    
+    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.ClassEmbedder
+      params:
+        n_classes: 1001
+        embed_dim: 512
+        key: class_label

configs/latent-diffusion/ffhq-ldm-vq-4.yaml

@@ -0,0 +1,85 @@
+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
+    image_size: 64
+    channels: 3
+    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: 224
+        attention_resolutions:
+        # note: this isn\t actually the resolution but
+        # the downsampling factor, i.e. this corresnponds to
+        # attention on spatial resolution 8,16,32, as the
+        # spatial reolution of the latents is 64 for f4
+        - 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
+        ckpt_path: configs/first_stage_models/vq-f4/model.yaml
+        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: taming.data.faceshq.FFHQTrain
+      params:
+        size: 256
+    validation:
+      target: taming.data.faceshq.FFHQValidation
+      params:
+        size: 256
+
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 5000
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True

configs/latent-diffusion/lsun_bedrooms-ldm-vq-4.yaml

@@ -0,0 +1,85 @@
+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
+    image_size: 64
+    channels: 3
+    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: 224
+        attention_resolutions:
+        # note: this isn\t actually the resolution but
+        # the downsampling factor, i.e. this corresnponds to
+        # attention on spatial resolution 8,16,32, as the
+        # spatial reolution of the latents is 64 for f4
+        - 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:
+        ckpt_path: configs/first_stage_models/vq-f4/model.yaml
+        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
+
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 5000
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True

configs/latent-diffusion/lsun_churches-ldm-kl-8.yaml

@@ -0,0 +1,91 @@
+model:
+  base_learning_rate: 5.0e-5   # set to target_lr by starting main.py with '--scale_lr False'
+  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: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [10000]
+        cycle_lengths: [10000000000000]
+        f_start: [1.e-6]
+        f_max: [1.]
+        f_min: [ 1.]
+
+    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 ]   # 32, 16, 8, 4
+        num_res_blocks: 2
+        channel_mult: [ 1,2,2,4,4 ]  # 32, 16, 8, 4, 2
+        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"
+        ckpt_path: "models/first_stage_models/kl-f8/model.ckpt"
+        ddconfig:
+          double_z: True
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult: [ 1,2,4,4 ]  # num_down = len(ch_mult)-1
+          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
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 5000
+        max_images: 8
+        increase_log_steps: False
+
+
+  trainer:
+    benchmark: True

configs/latent-diffusion/txt2img-1p4B-eval.yaml

@@ -0,0 +1,71 @@
+model:
+  base_learning_rate: 5.0e-05
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.012
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 32
+    channels: 4
+    cond_stage_trainable: true
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions:
+        - 4
+        - 2
+        - 1
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 4
+        - 4
+        num_heads: 8
+        use_spatial_transformer: true
+        transformer_depth: 1
+        context_dim: 1280
+        use_checkpoint: true
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.BERTEmbedder
+      params:
+        n_embed: 1280
+        n_layer: 32

configs/latent-diffusion/txt2img-1p4B-eval_with_tokens.yaml

@@ -0,0 +1,77 @@
+model:
+  base_learning_rate: 5.0e-05
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.012
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 32
+    channels: 4
+    cond_stage_trainable: true
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: []
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions:
+        - 4
+        - 2
+        - 1
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 4
+        - 4
+        num_heads: 8
+        use_spatial_transformer: true
+        transformer_depth: 1
+        context_dim: 1280
+        use_checkpoint: true
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.BERTEmbedder
+      params:
+        n_embed: 1280
+        n_layer: 32

configs/latent-diffusion/txt2img-1p4B-finetune.yaml

@@ -0,0 +1,119 @@
+model:
+  base_learning_rate: 5.0e-3
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.012
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 32
+    channels: 4
+    cond_stage_trainable: true
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    embedding_reg_weight: 0.0
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ["sculpture"]
+        per_image_tokens: false
+        num_vectors_per_token: 1
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions:
+        - 4
+        - 2
+        - 1
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 4
+        - 4
+        num_heads: 8
+        use_spatial_transformer: true
+        transformer_depth: 1
+        context_dim: 1280
+        use_checkpoint: true
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.BERTEmbedder
+      params:
+        n_embed: 1280
+        n_layer: 32
+
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 4
+    num_workers: 2
+    wrap: false
+    train:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 256
+        set: train
+        per_image_tokens: false
+        repeats: 100
+    validation:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 256
+        set: val
+        per_image_tokens: false
+        repeats: 10
+
+lightning:
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 500
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 500
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True
+    max_steps: 6100

configs/latent-diffusion/txt2img-1p4B-finetune_style.yaml

@@ -0,0 +1,117 @@
+model:
+  base_learning_rate: 5.0e-3
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.012
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 32
+    channels: 4
+    cond_stage_trainable: true
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    embedding_reg_weight: 0.0
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ["painting"]
+        per_image_tokens: false
+        num_vectors_per_token: 1
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions:
+        - 4
+        - 2
+        - 1
+        num_res_blocks: 2
+        channel_mult:
+        - 1
+        - 2
+        - 4
+        - 4
+        num_heads: 8
+        use_spatial_transformer: true
+        transformer_depth: 1
+        context_dim: 1280
+        use_checkpoint: true
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.BERTEmbedder
+      params:
+        n_embed: 1280
+        n_layer: 32
+
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 4
+    num_workers: 4
+    wrap: false
+    train:
+      target: ldm.data.personalized_style.PersonalizedBase
+      params:
+        size: 256
+        set: train
+        per_image_tokens: false
+        repeats: 100
+    validation:
+      target: ldm.data.personalized_style.PersonalizedBase
+      params:
+        size: 256
+        set: val
+        per_image_tokens: false
+        repeats: 10
+
+lightning:
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 500
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 500
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True

configs/stable-diffusion/v1-finetune.yaml

@@ -0,0 +1,110 @@
+model:
+  base_learning_rate: 5.0e-03
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: true   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    embedding_reg_weight: 0.0
+    unfreeze_model: False
+    model_lr: 0.0
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ["sculpture"]
+        per_image_tokens: false
+        num_vectors_per_token: 1
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 512
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 2
+    wrap: false
+    train:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: train
+        per_image_tokens: false
+        repeats: 100
+    validation:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: val
+        per_image_tokens: false
+        repeats: 10
+
+lightning:
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 500
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 500
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True
+    max_steps: 6100

configs/stable-diffusion/v1-finetune_unfrozen.yaml

@@ -0,0 +1,120 @@
+model:
+  base_learning_rate: 1.0e-06
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    reg_weight: 1.0
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: true   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    embedding_reg_weight: 0.0
+    unfreeze_model: True
+    model_lr: 1.0e-6
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ["sculpture"]
+        per_image_tokens: false
+        num_vectors_per_token: 1
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 512
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 1
+    num_workers: 2
+    wrap: false
+    train:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: train
+        per_image_tokens: false
+        repeats: 100
+    reg:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: train
+        reg: true
+        per_image_tokens: false
+        repeats: 10
+        
+    validation:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: val
+        per_image_tokens: false
+        repeats: 10
+
+lightning:
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 500
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 500
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True
+    max_steps: 800

configs/stable-diffusion/v1-inference.yaml

@@ -0,0 +1,70 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ["sculpture"]
+        per_image_tokens: false
+        num_vectors_per_token: 1
+        progressive_words: False
+        
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder

environment.yaml

@@ -0,0 +1,31 @@
+name: ldm
+channels:
+  - pytorch
+  - defaults
+dependencies:
+  - python=3.8.10
+  - pip=20.3
+  - cudatoolkit=11.3
+  - pytorch=1.10.2
+  - torchvision=0.11.3
+  - numpy=1.22.3
+  - pip:
+    - albumentations==1.1.0
+    - opencv-python==4.2.0.34
+    - pudb==2019.2
+    - imageio==2.14.1
+    - imageio-ffmpeg==0.4.7
+    - pytorch-lightning==1.5.9
+    - omegaconf==2.1.1
+    - test-tube>=0.7.5
+    - streamlit>=0.73.1
+    - setuptools==59.5.0
+    - pillow==9.0.1
+    - einops==0.4.1
+    - torch-fidelity==0.3.0
+    - transformers==4.18.0
+    - torchmetrics==0.6.0
+    - kornia==0.6
+    - -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
+    - -e git+https://github.com/openai/CLIP.git@main#egg=clip
+    - -e .

evaluation/clip_eval.py

@@ -0,0 +1,113 @@
+import clip
+import torch
+from torchvision import transforms
+
+from ldm.models.diffusion.ddim import DDIMSampler
+
+class CLIPEvaluator(object):
+    def __init__(self, device, clip_model='ViT-B/32') -> None:
+        self.device = device
+        self.model, clip_preprocess = clip.load(clip_model, device=self.device)
+
+        self.clip_preprocess = clip_preprocess
+        
+        self.preprocess = transforms.Compose([transforms.Normalize(mean=[-1.0, -1.0, -1.0], std=[2.0, 2.0, 2.0])] + # Un-normalize from [-1.0, 1.0] (generator output) to [0, 1].
+                                              clip_preprocess.transforms[:2] +                                      # to match CLIP input scale assumptions
+                                              clip_preprocess.transforms[4:])                                       # + skip convert PIL to tensor
+
+    def tokenize(self, strings: list):
+        return clip.tokenize(strings).to(self.device)
+
+    @torch.no_grad()
+    def encode_text(self, tokens: list) -> torch.Tensor:
+        return self.model.encode_text(tokens)
+
+    @torch.no_grad()
+    def encode_images(self, images: torch.Tensor) -> torch.Tensor:
+        images = self.preprocess(images).to(self.device)
+        return self.model.encode_image(images)
+
+    def get_text_features(self, text: str, norm: bool = True) -> torch.Tensor:
+
+        tokens = clip.tokenize(text).to(self.device)
+
+        text_features = self.encode_text(tokens).detach()
+
+        if norm:
+            text_features /= text_features.norm(dim=-1, keepdim=True)
+
+        return text_features
+
+    def get_image_features(self, img: torch.Tensor, norm: bool = True) -> torch.Tensor:
+        image_features = self.encode_images(img)
+        
+        if norm:
+            image_features /= image_features.clone().norm(dim=-1, keepdim=True)
+
+        return image_features
+
+    def img_to_img_similarity(self, src_images, generated_images):
+        src_img_features = self.get_image_features(src_images)
+        gen_img_features = self.get_image_features(generated_images)
+
+        return (src_img_features @ gen_img_features.T).mean()
+
+    def txt_to_img_similarity(self, text, generated_images):
+        text_features    = self.get_text_features(text)
+        gen_img_features = self.get_image_features(generated_images)
+
+        return (text_features @ gen_img_features.T).mean()
+
+
+class LDMCLIPEvaluator(CLIPEvaluator):
+    def __init__(self, device, clip_model='ViT-B/32') -> None:
+        super().__init__(device, clip_model)
+
+    def evaluate(self, ldm_model, src_images, target_text, n_samples=64, n_steps=50):
+        
+        sampler = DDIMSampler(ldm_model)
+
+        samples_per_batch = 8
+        n_batches         = n_samples // samples_per_batch
+
+        # generate samples
+        all_samples=list()
+        with torch.no_grad():
+            with ldm_model.ema_scope():                
+                uc = ldm_model.get_learned_conditioning(samples_per_batch * [""])
+
+                for batch in range(n_batches):
+                    c = ldm_model.get_learned_conditioning(samples_per_batch * [target_text])
+                    shape = [4, 256//8, 256//8]
+                    samples_ddim, _ = sampler.sample(S=n_steps,
+                                                    conditioning=c,
+                                                    batch_size=samples_per_batch,
+                                                    shape=shape,
+                                                    verbose=False,
+                                                    unconditional_guidance_scale=5.0,
+                                                    unconditional_conditioning=uc,
+                                                    eta=0.0)
+
+                    x_samples_ddim = ldm_model.decode_first_stage(samples_ddim)
+                    x_samples_ddim = torch.clamp(x_samples_ddim, min=-1.0, max=1.0)
+
+                    all_samples.append(x_samples_ddim)
+        
+        all_samples = torch.cat(all_samples, axis=0)
+
+        sim_samples_to_img  = self.img_to_img_similarity(src_images, all_samples)
+        sim_samples_to_text = self.txt_to_img_similarity(target_text.replace("*", ""), all_samples)
+
+        return sim_samples_to_img, sim_samples_to_text
+
+
+class ImageDirEvaluator(CLIPEvaluator):
+    def __init__(self, device, clip_model='ViT-B/32') -> None:
+        super().__init__(device, clip_model)
+
+    def evaluate(self, gen_samples, src_images, target_text):
+
+        sim_samples_to_img  = self.img_to_img_similarity(src_images, gen_samples)
+        sim_samples_to_text = self.txt_to_img_similarity(target_text.replace("*", ""), gen_samples)
+
+        return sim_samples_to_img, sim_samples_to_text

ldm/data/base.py

@@ -0,0 +1,23 @@
+from abc import abstractmethod
+from torch.utils.data import Dataset, ConcatDataset, ChainDataset, IterableDataset
+
+
+class Txt2ImgIterableBaseDataset(IterableDataset):
+    '''
+    Define an interface to make the IterableDatasets for text2img data chainable
+    '''
+    def __init__(self, num_records=0, valid_ids=None, size=256):
+        super().__init__()
+        self.num_records = num_records
+        self.valid_ids = valid_ids
+        self.sample_ids = valid_ids
+        self.size = size
+
+        print(f'{self.__class__.__name__} dataset contains {self.__len__()} examples.')
+
+    def __len__(self):
+        return self.num_records
+
+    @abstractmethod
+    def __iter__(self):
+        pass

ldm/data/imagenet.py

@@ -0,0 +1,394 @@
+import os, yaml, pickle, shutil, tarfile, glob
+import cv2
+import albumentations
+import PIL
+import numpy as np
+import torchvision.transforms.functional as TF
+from omegaconf import OmegaConf
+from functools import partial
+from PIL import Image
+from tqdm import tqdm
+from torch.utils.data import Dataset, Subset
+
+import taming.data.utils as tdu
+from taming.data.imagenet import str_to_indices, give_synsets_from_indices, download, retrieve
+from taming.data.imagenet import ImagePaths
+
+from ldm.modules.image_degradation import degradation_fn_bsr, degradation_fn_bsr_light
+
+
+def synset2idx(path_to_yaml="data/index_synset.yaml"):
+    with open(path_to_yaml) as f:
+        di2s = yaml.load(f)
+    return dict((v,k) for k,v in di2s.items())
+
+
+class ImageNetBase(Dataset):
+    def __init__(self, config=None):
+        self.config = config or OmegaConf.create()
+        if not type(self.config)==dict:
+            self.config = OmegaConf.to_container(self.config)
+        self.keep_orig_class_label = self.config.get("keep_orig_class_label", False)
+        self.process_images = True  # if False we skip loading & processing images and self.data contains filepaths
+        self._prepare()
+        self._prepare_synset_to_human()
+        self._prepare_idx_to_synset()
+        self._prepare_human_to_integer_label()
+        self._load()
+
+    def __len__(self):
+        return len(self.data)
+
+    def __getitem__(self, i):
+        return self.data[i]
+
+    def _prepare(self):
+        raise NotImplementedError()
+
+    def _filter_relpaths(self, relpaths):
+        ignore = set([
+            "n06596364_9591.JPEG",
+        ])
+        relpaths = [rpath for rpath in relpaths if not rpath.split("/")[-1] in ignore]
+        if "sub_indices" in self.config:
+            indices = str_to_indices(self.config["sub_indices"])
+            synsets = give_synsets_from_indices(indices, path_to_yaml=self.idx2syn)  # returns a list of strings
+            self.synset2idx = synset2idx(path_to_yaml=self.idx2syn)
+            files = []
+            for rpath in relpaths:
+                syn = rpath.split("/")[0]
+                if syn in synsets:
+                    files.append(rpath)
+            return files
+        else:
+            return relpaths
+
+    def _prepare_synset_to_human(self):
+        SIZE = 2655750
+        URL = "https://heibox.uni-heidelberg.de/f/9f28e956cd304264bb82/?dl=1"
+        self.human_dict = os.path.join(self.root, "synset_human.txt")
+        if (not os.path.exists(self.human_dict) or
+                not os.path.getsize(self.human_dict)==SIZE):
+            download(URL, self.human_dict)
+
+    def _prepare_idx_to_synset(self):
+        URL = "https://heibox.uni-heidelberg.de/f/d835d5b6ceda4d3aa910/?dl=1"
+        self.idx2syn = os.path.join(self.root, "index_synset.yaml")
+        if (not os.path.exists(self.idx2syn)):
+            download(URL, self.idx2syn)
+
+    def _prepare_human_to_integer_label(self):
+        URL = "https://heibox.uni-heidelberg.de/f/2362b797d5be43b883f6/?dl=1"
+        self.human2integer = os.path.join(self.root, "imagenet1000_clsidx_to_labels.txt")
+        if (not os.path.exists(self.human2integer)):
+            download(URL, self.human2integer)
+        with open(self.human2integer, "r") as f:
+            lines = f.read().splitlines()
+            assert len(lines) == 1000
+            self.human2integer_dict = dict()
+            for line in lines:
+                value, key = line.split(":")
+                self.human2integer_dict[key] = int(value)
+
+    def _load(self):
+        with open(self.txt_filelist, "r") as f:
+            self.relpaths = f.read().splitlines()
+            l1 = len(self.relpaths)
+            self.relpaths = self._filter_relpaths(self.relpaths)
+            print("Removed {} files from filelist during filtering.".format(l1 - len(self.relpaths)))
+
+        self.synsets = [p.split("/")[0] for p in self.relpaths]
+        self.abspaths = [os.path.join(self.datadir, p) for p in self.relpaths]
+
+        unique_synsets = np.unique(self.synsets)
+        class_dict = dict((synset, i) for i, synset in enumerate(unique_synsets))
+        if not self.keep_orig_class_label:
+            self.class_labels = [class_dict[s] for s in self.synsets]
+        else:
+            self.class_labels = [self.synset2idx[s] for s in self.synsets]
+
+        with open(self.human_dict, "r") as f:
+            human_dict = f.read().splitlines()
+            human_dict = dict(line.split(maxsplit=1) for line in human_dict)
+
+        self.human_labels = [human_dict[s] for s in self.synsets]
+
+        labels = {
+            "relpath": np.array(self.relpaths),
+            "synsets": np.array(self.synsets),
+            "class_label": np.array(self.class_labels),
+            "human_label": np.array(self.human_labels),
+        }
+
+        if self.process_images:
+            self.size = retrieve(self.config, "size", default=256)
+            self.data = ImagePaths(self.abspaths,
+                                   labels=labels,
+                                   size=self.size,
+                                   random_crop=self.random_crop,
+                                   )
+        else:
+            self.data = self.abspaths
+
+
+class ImageNetTrain(ImageNetBase):
+    NAME = "ILSVRC2012_train"
+    URL = "http://www.image-net.org/challenges/LSVRC/2012/"
+    AT_HASH = "a306397ccf9c2ead27155983c254227c0fd938e2"
+    FILES = [
+        "ILSVRC2012_img_train.tar",
+    ]
+    SIZES = [
+        147897477120,
+    ]
+
+    def __init__(self, process_images=True, data_root=None, **kwargs):
+        self.process_images = process_images
+        self.data_root = data_root
+        super().__init__(**kwargs)
+
+    def _prepare(self):
+        if self.data_root:
+            self.root = os.path.join(self.data_root, self.NAME)
+        else:
+            cachedir = os.environ.get("XDG_CACHE_HOME", os.path.expanduser("~/.cache"))
+            self.root = os.path.join(cachedir, "autoencoders/data", self.NAME)
+
+        self.datadir = os.path.join(self.root, "data")
+        self.txt_filelist = os.path.join(self.root, "filelist.txt")
+        self.expected_length = 1281167
+        self.random_crop = retrieve(self.config, "ImageNetTrain/random_crop",
+                                    default=True)
+        if not tdu.is_prepared(self.root):
+            # prep
+            print("Preparing dataset {} in {}".format(self.NAME, self.root))
+
+            datadir = self.datadir
+            if not os.path.exists(datadir):
+                path = os.path.join(self.root, self.FILES[0])
+                if not os.path.exists(path) or not os.path.getsize(path)==self.SIZES[0]:
+                    import academictorrents as at
+                    atpath = at.get(self.AT_HASH, datastore=self.root)
+                    assert atpath == path
+
+                print("Extracting {} to {}".format(path, datadir))
+                os.makedirs(datadir, exist_ok=True)
+                with tarfile.open(path, "r:") as tar:
+                    tar.extractall(path=datadir)
+
+                print("Extracting sub-tars.")
+                subpaths = sorted(glob.glob(os.path.join(datadir, "*.tar")))
+                for subpath in tqdm(subpaths):
+                    subdir = subpath[:-len(".tar")]
+                    os.makedirs(subdir, exist_ok=True)
+                    with tarfile.open(subpath, "r:") as tar:
+                        tar.extractall(path=subdir)
+
+            filelist = glob.glob(os.path.join(datadir, "**", "*.JPEG"))
+            filelist = [os.path.relpath(p, start=datadir) for p in filelist]
+            filelist = sorted(filelist)
+            filelist = "\n".join(filelist)+"\n"
+            with open(self.txt_filelist, "w") as f:
+                f.write(filelist)
+
+            tdu.mark_prepared(self.root)
+
+
+class ImageNetValidation(ImageNetBase):
+    NAME = "ILSVRC2012_validation"
+    URL = "http://www.image-net.org/challenges/LSVRC/2012/"
+    AT_HASH = "5d6d0df7ed81efd49ca99ea4737e0ae5e3a5f2e5"
+    VS_URL = "https://heibox.uni-heidelberg.de/f/3e0f6e9c624e45f2bd73/?dl=1"
+    FILES = [
+        "ILSVRC2012_img_val.tar",
+        "validation_synset.txt",
+    ]
+    SIZES = [
+        6744924160,
+        1950000,
+    ]
+
+    def __init__(self, process_images=True, data_root=None, **kwargs):
+        self.data_root = data_root
+        self.process_images = process_images
+        super().__init__(**kwargs)
+
+    def _prepare(self):
+        if self.data_root:
+            self.root = os.path.join(self.data_root, self.NAME)
+        else:
+            cachedir = os.environ.get("XDG_CACHE_HOME", os.path.expanduser("~/.cache"))
+            self.root = os.path.join(cachedir, "autoencoders/data", self.NAME)
+        self.datadir = os.path.join(self.root, "data")
+        self.txt_filelist = os.path.join(self.root, "filelist.txt")
+        self.expected_length = 50000
+        self.random_crop = retrieve(self.config, "ImageNetValidation/random_crop",
+                                    default=False)
+        if not tdu.is_prepared(self.root):
+            # prep
+            print("Preparing dataset {} in {}".format(self.NAME, self.root))
+
+            datadir = self.datadir
+            if not os.path.exists(datadir):
+                path = os.path.join(self.root, self.FILES[0])
+                if not os.path.exists(path) or not os.path.getsize(path)==self.SIZES[0]:
+                    import academictorrents as at
+                    atpath = at.get(self.AT_HASH, datastore=self.root)
+                    assert atpath == path
+
+                print("Extracting {} to {}".format(path, datadir))
+                os.makedirs(datadir, exist_ok=True)
+                with tarfile.open(path, "r:") as tar:
+                    tar.extractall(path=datadir)
+
+                vspath = os.path.join(self.root, self.FILES[1])
+                if not os.path.exists(vspath) or not os.path.getsize(vspath)==self.SIZES[1]:
+                    download(self.VS_URL, vspath)
+
+                with open(vspath, "r") as f:
+                    synset_dict = f.read().splitlines()
+                    synset_dict = dict(line.split() for line in synset_dict)
+
+                print("Reorganizing into synset folders")
+                synsets = np.unique(list(synset_dict.values()))
+                for s in synsets:
+                    os.makedirs(os.path.join(datadir, s), exist_ok=True)
+                for k, v in synset_dict.items():
+                    src = os.path.join(datadir, k)
+                    dst = os.path.join(datadir, v)
+                    shutil.move(src, dst)
+
+            filelist = glob.glob(os.path.join(datadir, "**", "*.JPEG"))
+            filelist = [os.path.relpath(p, start=datadir) for p in filelist]
+            filelist = sorted(filelist)
+            filelist = "\n".join(filelist)+"\n"
+            with open(self.txt_filelist, "w") as f:
+                f.write(filelist)
+
+            tdu.mark_prepared(self.root)
+
+
+
+class ImageNetSR(Dataset):
+    def __init__(self, size=None,
+                 degradation=None, downscale_f=4, min_crop_f=0.5, max_crop_f=1.,
+                 random_crop=True):
+        """
+        Imagenet Superresolution Dataloader
+        Performs following ops in order:
+        1.  crops a crop of size s from image either as random or center crop
+        2.  resizes crop to size with cv2.area_interpolation
+        3.  degrades resized crop with degradation_fn
+
+        :param size: resizing to size after cropping
+        :param degradation: degradation_fn, e.g. cv_bicubic or bsrgan_light
+        :param downscale_f: Low Resolution Downsample factor
+        :param min_crop_f: determines crop size s,
+          where s = c * min_img_side_len with c sampled from interval (min_crop_f, max_crop_f)
+        :param max_crop_f: ""
+        :param data_root:
+        :param random_crop:
+        """
+        self.base = self.get_base()
+        assert size
+        assert (size / downscale_f).is_integer()
+        self.size = size
+        self.LR_size = int(size / downscale_f)
+        self.min_crop_f = min_crop_f
+        self.max_crop_f = max_crop_f
+        assert(max_crop_f <= 1.)
+        self.center_crop = not random_crop
+
+        self.image_rescaler = albumentations.SmallestMaxSize(max_size=size, interpolation=cv2.INTER_AREA)
+
+        self.pil_interpolation = False # gets reset later if incase interp_op is from pillow
+
+        if degradation == "bsrgan":
+            self.degradation_process = partial(degradation_fn_bsr, sf=downscale_f)
+
+        elif degradation == "bsrgan_light":
+            self.degradation_process = partial(degradation_fn_bsr_light, sf=downscale_f)
+
+        else:
+            interpolation_fn = {
+            "cv_nearest": cv2.INTER_NEAREST,
+            "cv_bilinear": cv2.INTER_LINEAR,
+            "cv_bicubic": cv2.INTER_CUBIC,
+            "cv_area": cv2.INTER_AREA,
+            "cv_lanczos": cv2.INTER_LANCZOS4,
+            "pil_nearest": PIL.Image.NEAREST,
+            "pil_bilinear": PIL.Image.BILINEAR,
+            "pil_bicubic": PIL.Image.BICUBIC,
+            "pil_box": PIL.Image.BOX,
+            "pil_hamming": PIL.Image.HAMMING,
+            "pil_lanczos": PIL.Image.LANCZOS,
+            }[degradation]
+
+            self.pil_interpolation = degradation.startswith("pil_")
+
+            if self.pil_interpolation:
+                self.degradation_process = partial(TF.resize, size=self.LR_size, interpolation=interpolation_fn)
+
+            else:
+                self.degradation_process = albumentations.SmallestMaxSize(max_size=self.LR_size,
+                                                                          interpolation=interpolation_fn)
+
+    def __len__(self):
+        return len(self.base)
+
+    def __getitem__(self, i):
+        example = self.base[i]
+        image = Image.open(example["file_path_"])
+
+        if not image.mode == "RGB":
+            image = image.convert("RGB")
+
+        image = np.array(image).astype(np.uint8)
+
+        min_side_len = min(image.shape[:2])
+        crop_side_len = min_side_len * np.random.uniform(self.min_crop_f, self.max_crop_f, size=None)
+        crop_side_len = int(crop_side_len)
+
+        if self.center_crop:
+            self.cropper = albumentations.CenterCrop(height=crop_side_len, width=crop_side_len)
+
+        else:
+            self.cropper = albumentations.RandomCrop(height=crop_side_len, width=crop_side_len)
+
+        image = self.cropper(image=image)["image"]
+        image = self.image_rescaler(image=image)["image"]
+
+        if self.pil_interpolation:
+            image_pil = PIL.Image.fromarray(image)
+            LR_image = self.degradation_process(image_pil)
+            LR_image = np.array(LR_image).astype(np.uint8)
+
+        else:
+            LR_image = self.degradation_process(image=image)["image"]
+
+        example["image"] = (image/127.5 - 1.0).astype(np.float32)
+        example["LR_image"] = (LR_image/127.5 - 1.0).astype(np.float32)
+
+        return example
+
+
+class ImageNetSRTrain(ImageNetSR):
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def get_base(self):
+        with open("data/imagenet_train_hr_indices.p", "rb") as f:
+            indices = pickle.load(f)
+        dset = ImageNetTrain(process_images=False,)
+        return Subset(dset, indices)
+
+
+class ImageNetSRValidation(ImageNetSR):
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def get_base(self):
+        with open("data/imagenet_val_hr_indices.p", "rb") as f:
+            indices = pickle.load(f)
+        dset = ImageNetValidation(process_images=False,)
+        return Subset(dset, indices)

ldm/data/lsun.py

@@ -0,0 +1,92 @@
+import os
+import numpy as np
+import PIL
+from PIL import Image
+from torch.utils.data import Dataset
+from torchvision import transforms
+
+
+class LSUNBase(Dataset):
+    def __init__(self,
+                 txt_file,
+                 data_root,
+                 size=None,
+                 interpolation="bicubic",
+                 flip_p=0.5
+                 ):
+        self.data_paths = txt_file
+        self.data_root = data_root
+        with open(self.data_paths, "r") as f:
+            self.image_paths = f.read().splitlines()
+        self._length = len(self.image_paths)
+        self.labels = {
+            "relative_file_path_": [l for l in self.image_paths],
+            "file_path_": [os.path.join(self.data_root, l)
+                           for l in self.image_paths],
+        }
+
+        self.size = size
+        self.interpolation = {"linear": PIL.Image.LINEAR,
+                              "bilinear": PIL.Image.BILINEAR,
+                              "bicubic": PIL.Image.BICUBIC,
+                              "lanczos": PIL.Image.LANCZOS,
+                              }[interpolation]
+        self.flip = transforms.RandomHorizontalFlip(p=flip_p)
+
+    def __len__(self):
+        return self._length
+
+    def __getitem__(self, i):
+        example = dict((k, self.labels[k][i]) for k in self.labels)
+        image = Image.open(example["file_path_"])
+        if not image.mode == "RGB":
+            image = image.convert("RGB")
+
+        # default to score-sde preprocessing
+        img = np.array(image).astype(np.uint8)
+        crop = min(img.shape[0], img.shape[1])
+        h, w, = img.shape[0], img.shape[1]
+        img = img[(h - crop) // 2:(h + crop) // 2,
+              (w - crop) // 2:(w + crop) // 2]
+
+        image = Image.fromarray(img)
+        if self.size is not None:
+            image = image.resize((self.size, self.size), resample=self.interpolation)
+
+        image = self.flip(image)
+        image = np.array(image).astype(np.uint8)
+        example["image"] = (image / 127.5 - 1.0).astype(np.float32)
+        return example
+
+
+class LSUNChurchesTrain(LSUNBase):
+    def __init__(self, **kwargs):
+        super().__init__(txt_file="data/lsun/church_outdoor_train.txt", data_root="data/lsun/churches", **kwargs)
+
+
+class LSUNChurchesValidation(LSUNBase):
+    def __init__(self, flip_p=0., **kwargs):
+        super().__init__(txt_file="data/lsun/church_outdoor_val.txt", data_root="data/lsun/churches",
+                         flip_p=flip_p, **kwargs)
+
+
+class LSUNBedroomsTrain(LSUNBase):
+    def __init__(self, **kwargs):
+        super().__init__(txt_file="data/lsun/bedrooms_train.txt", data_root="data/lsun/bedrooms", **kwargs)
+
+
+class LSUNBedroomsValidation(LSUNBase):
+    def __init__(self, flip_p=0.0, **kwargs):
+        super().__init__(txt_file="data/lsun/bedrooms_val.txt", data_root="data/lsun/bedrooms",
+                         flip_p=flip_p, **kwargs)
+
+
+class LSUNCatsTrain(LSUNBase):
+    def __init__(self, **kwargs):
+        super().__init__(txt_file="data/lsun/cat_train.txt", data_root="data/lsun/cats", **kwargs)
+
+
+class LSUNCatsValidation(LSUNBase):
+    def __init__(self, flip_p=0., **kwargs):
+        super().__init__(txt_file="data/lsun/cat_val.txt", data_root="data/lsun/cats",
+                         flip_p=flip_p, **kwargs)

ldm/data/personalized.py

@@ -0,0 +1,220 @@
+import os
+import numpy as np
+import PIL
+from PIL import Image
+from torch.utils.data import Dataset
+from torchvision import transforms
+
+import random
+
+training_templates_smallest = [
+    'photo of a sks {}',
+]
+
+reg_templates_smallest = [
+    'photo of a {}',
+]
+
+imagenet_templates_small = [
+    'a photo of a {}',
+    'a rendering of a {}',
+    'a cropped photo of the {}',
+    'the photo of a {}',
+    'a photo of a clean {}',
+    'a photo of a dirty {}',
+    'a dark photo of the {}',
+    'a photo of my {}',
+    'a photo of the cool {}',
+    'a close-up photo of a {}',
+    'a bright photo of the {}',
+    'a cropped photo of a {}',
+    'a photo of the {}',
+    'a good photo of the {}',
+    'a photo of one {}',
+    'a close-up photo of the {}',
+    'a rendition of the {}',
+    'a photo of the clean {}',
+    'a rendition of a {}',
+    'a photo of a nice {}',
+    'a good photo of a {}',
+    'a photo of the nice {}',
+    'a photo of the small {}',
+    'a photo of the weird {}',
+    'a photo of the large {}',
+    'a photo of a cool {}',
+    'a photo of a small {}',
+    'an illustration of a {}',
+    'a rendering of a {}',
+    'a cropped photo of the {}',
+    'the photo of a {}',
+    'an illustration of a clean {}',
+    'an illustration of a dirty {}',
+    'a dark photo of the {}',
+    'an illustration of my {}',
+    'an illustration of the cool {}',
+    'a close-up photo of a {}',
+    'a bright photo of the {}',
+    'a cropped photo of a {}',
+    'an illustration of the {}',
+    'a good photo of the {}',
+    'an illustration of one {}',
+    'a close-up photo of the {}',
+    'a rendition of the {}',
+    'an illustration of the clean {}',
+    'a rendition of a {}',
+    'an illustration of a nice {}',
+    'a good photo of a {}',
+    'an illustration of the nice {}',
+    'an illustration of the small {}',
+    'an illustration of the weird {}',
+    'an illustration of the large {}',
+    'an illustration of a cool {}',
+    'an illustration of a small {}',
+    'a depiction of a {}',
+    'a rendering of a {}',
+    'a cropped photo of the {}',
+    'the photo of a {}',
+    'a depiction of a clean {}',
+    'a depiction of a dirty {}',
+    'a dark photo of the {}',
+    'a depiction of my {}',
+    'a depiction of the cool {}',
+    'a close-up photo of a {}',
+    'a bright photo of the {}',
+    'a cropped photo of a {}',
+    'a depiction of the {}',
+    'a good photo of the {}',
+    'a depiction of one {}',
+    'a close-up photo of the {}',
+    'a rendition of the {}',
+    'a depiction of the clean {}',
+    'a rendition of a {}',
+    'a depiction of a nice {}',
+    'a good photo of a {}',
+    'a depiction of the nice {}',
+    'a depiction of the small {}',
+    'a depiction of the weird {}',
+    'a depiction of the large {}',
+    'a depiction of a cool {}',
+    'a depiction of a small {}',
+]
+
+imagenet_dual_templates_small = [
+    'a photo of a {} with {}',
+    'a rendering of a {} with {}',
+    'a cropped photo of the {} with {}',
+    'the photo of a {} with {}',
+    'a photo of a clean {} with {}',
+    'a photo of a dirty {} with {}',
+    'a dark photo of the {} with {}',
+    'a photo of my {} with {}',
+    'a photo of the cool {} with {}',
+    'a close-up photo of a {} with {}',
+    'a bright photo of the {} with {}',
+    'a cropped photo of a {} with {}',
+    'a photo of the {} with {}',
+    'a good photo of the {} with {}',
+    'a photo of one {} with {}',
+    'a close-up photo of the {} with {}',
+    'a rendition of the {} with {}',
+    'a photo of the clean {} with {}',
+    'a rendition of a {} with {}',
+    'a photo of a nice {} with {}',
+    'a good photo of a {} with {}',
+    'a photo of the nice {} with {}',
+    'a photo of the small {} with {}',
+    'a photo of the weird {} with {}',
+    'a photo of the large {} with {}',
+    'a photo of a cool {} with {}',
+    'a photo of a small {} with {}',
+]
+
+per_img_token_list = [
+    'א', 'ב', 'ג', 'ד', 'ה', 'ו', 'ז', 'ח', 'ט', 'י', 'כ', 'ל', 'מ', 'נ', 'ס', 'ע', 'פ', 'צ', 'ק', 'ר', 'ש', 'ת',
+]
+
+class PersonalizedBase(Dataset):
+    def __init__(self,
+                 data_root,
+                 size=None,
+                 repeats=100,
+                 interpolation="bicubic",
+                 flip_p=0.5,
+                 set="train",
+                 placeholder_token="dog",
+                 per_image_tokens=False,
+                 center_crop=False,
+                 mixing_prob=0.25,
+                 coarse_class_text=None,
+                 reg = False
+                 ):
+
+        self.data_root = data_root
+
+        self.image_paths = [os.path.join(self.data_root, file_path) for file_path in os.listdir(self.data_root)]
+
+        # self._length = len(self.image_paths)
+        self.num_images = len(self.image_paths)
+        self._length = self.num_images 
+
+        self.placeholder_token = placeholder_token
+
+        self.per_image_tokens = per_image_tokens
+        self.center_crop = center_crop
+        self.mixing_prob = mixing_prob
+
+        self.coarse_class_text = coarse_class_text
+
+        if per_image_tokens:
+            assert self.num_images < len(per_img_token_list), f"Can't use per-image tokens when the training set contains more than {len(per_img_token_list)} tokens. To enable larger sets, add more tokens to 'per_img_token_list'."
+
+        if set == "train":
+            self._length = self.num_images * repeats
+
+        self.size = size
+        self.interpolation = {"linear": PIL.Image.LINEAR,
+                              "bilinear": PIL.Image.BILINEAR,
+                              "bicubic": PIL.Image.BICUBIC,
+                              "lanczos": PIL.Image.LANCZOS,
+                              }[interpolation]
+        self.flip = transforms.RandomHorizontalFlip(p=flip_p)
+        self.reg = reg
+
+    def __len__(self):
+        return self._length
+
+    def __getitem__(self, i):
+        example = {}
+        image = Image.open(self.image_paths[i % self.num_images])
+
+        if not image.mode == "RGB":
+            image = image.convert("RGB")
+
+        placeholder_string = self.placeholder_token
+        if self.coarse_class_text:
+            placeholder_string = f"{self.coarse_class_text} {placeholder_string}"
+
+        if not self.reg:
+            text = random.choice(training_templates_smallest).format(placeholder_string)
+        else:
+            text = random.choice(reg_templates_smallest).format(placeholder_string)
+            
+        example["caption"] = text
+
+        # default to score-sde preprocessing
+        img = np.array(image).astype(np.uint8)
+        
+        if self.center_crop:
+            crop = min(img.shape[0], img.shape[1])
+            h, w, = img.shape[0], img.shape[1]
+            img = img[(h - crop) // 2:(h + crop) // 2,
+                (w - crop) // 2:(w + crop) // 2]
+
+        image = Image.fromarray(img)
+        if self.size is not None:
+            image = image.resize((self.size, self.size), resample=self.interpolation)
+
+        image = self.flip(image)
+        image = np.array(image).astype(np.uint8)
+        example["image"] = (image / 127.5 - 1.0).astype(np.float32)
+        return example

ldm/data/personalized_style.py

@@ -0,0 +1,129 @@
+import os
+import numpy as np
+import PIL
+from PIL import Image
+from torch.utils.data import Dataset
+from torchvision import transforms
+
+import random
+
+imagenet_templates_small = [
+    'a painting in the style of {}',
+    'a rendering in the style of {}',
+    'a cropped painting in the style of {}',
+    'the painting in the style of {}',
+    'a clean painting in the style of {}',
+    'a dirty painting in the style of {}',
+    'a dark painting in the style of {}',
+    'a picture in the style of {}',
+    'a cool painting in the style of {}',
+    'a close-up painting in the style of {}',
+    'a bright painting in the style of {}',
+    'a cropped painting in the style of {}',
+    'a good painting in the style of {}',
+    'a close-up painting in the style of {}',
+    'a rendition in the style of {}',
+    'a nice painting in the style of {}',
+    'a small painting in the style of {}',
+    'a weird painting in the style of {}',
+    'a large painting in the style of {}',
+]
+
+imagenet_dual_templates_small = [
+    'a painting in the style of {} with {}',
+    'a rendering in the style of {} with {}',
+    'a cropped painting in the style of {} with {}',
+    'the painting in the style of {} with {}',
+    'a clean painting in the style of {} with {}',
+    'a dirty painting in the style of {} with {}',
+    'a dark painting in the style of {} with {}',
+    'a cool painting in the style of {} with {}',
+    'a close-up painting in the style of {} with {}',
+    'a bright painting in the style of {} with {}',
+    'a cropped painting in the style of {} with {}',
+    'a good painting in the style of {} with {}',
+    'a painting of one {} in the style of {}',
+    'a nice painting in the style of {} with {}',
+    'a small painting in the style of {} with {}',
+    'a weird painting in the style of {} with {}',
+    'a large painting in the style of {} with {}',
+]
+
+per_img_token_list = [
+    'א', 'ב', 'ג', 'ד', 'ה', 'ו', 'ז', 'ח', 'ט', 'י', 'כ', 'ל', 'מ', 'נ', 'ס', 'ע', 'פ', 'צ', 'ק', 'ר', 'ש', 'ת',
+]
+
+class PersonalizedBase(Dataset):
+    def __init__(self,
+                 data_root,
+                 size=None,
+                 repeats=100,
+                 interpolation="bicubic",
+                 flip_p=0.5,
+                 set="train",
+                 placeholder_token="*",
+                 per_image_tokens=False,
+                 center_crop=False,
+                 ):
+
+        self.data_root = data_root
+
+        self.image_paths = [os.path.join(self.data_root, file_path) for file_path in os.listdir(self.data_root)]
+
+        # self._length = len(self.image_paths)
+        self.num_images = len(self.image_paths)
+        self._length = self.num_images 
+
+        self.placeholder_token = placeholder_token
+
+        self.per_image_tokens = per_image_tokens
+        self.center_crop = center_crop
+
+        if per_image_tokens:
+            assert self.num_images < len(per_img_token_list), f"Can't use per-image tokens when the training set contains more than {len(per_img_token_list)} tokens. To enable larger sets, add more tokens to 'per_img_token_list'."
+
+        if set == "train":
+            self._length = self.num_images * repeats
+
+        self.size = size
+        self.interpolation = {"linear": PIL.Image.LINEAR,
+                              "bilinear": PIL.Image.BILINEAR,
+                              "bicubic": PIL.Image.BICUBIC,
+                              "lanczos": PIL.Image.LANCZOS,
+                              }[interpolation]
+        self.flip = transforms.RandomHorizontalFlip(p=flip_p)
+
+    def __len__(self):
+        return self._length
+
+    def __getitem__(self, i):
+        example = {}
+        image = Image.open(self.image_paths[i % self.num_images])
+
+        if not image.mode == "RGB":
+            image = image.convert("RGB")
+
+        if self.per_image_tokens and np.random.uniform() < 0.25:
+            text = random.choice(imagenet_dual_templates_small).format(self.placeholder_token, per_img_token_list[i % self.num_images])
+        else:
+            text = random.choice(imagenet_templates_small).format(self.placeholder_token)
+            
+        example["caption"] = text
+
+        # default to score-sde preprocessing
+        img = np.array(image).astype(np.uint8)
+        
+        if self.center_crop:
+            crop = min(img.shape[0], img.shape[1])
+            h, w, = img.shape[0], img.shape[1]
+            img = img[(h - crop) // 2:(h + crop) // 2,
+                (w - crop) // 2:(w + crop) // 2]
+
+        image = Image.fromarray(img)
+        if self.size is not None:
+            image = image.resize((self.size, self.size), resample=self.interpolation)
+
+        image = self.flip(image)
+        image = np.array(image).astype(np.uint8)
+        example["image"] = (image / 127.5 - 1.0).astype(np.float32)
+        return example

ldm/lr_scheduler.py

@@ -0,0 +1,98 @@
+import numpy as np
+
+
+class LambdaWarmUpCosineScheduler:
+    """
+    note: use with a base_lr of 1.0
+    """
+    def __init__(self, warm_up_steps, lr_min, lr_max, lr_start, max_decay_steps, verbosity_interval=0):
+        self.lr_warm_up_steps = warm_up_steps
+        self.lr_start = lr_start
+        self.lr_min = lr_min
+        self.lr_max = lr_max
+        self.lr_max_decay_steps = max_decay_steps
+        self.last_lr = 0.
+        self.verbosity_interval = verbosity_interval
+
+    def schedule(self, n, **kwargs):
+        if self.verbosity_interval > 0:
+            if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_lr}")
+        if n < self.lr_warm_up_steps:
+            lr = (self.lr_max - self.lr_start) / self.lr_warm_up_steps * n + self.lr_start
+            self.last_lr = lr
+            return lr
+        else:
+            t = (n - self.lr_warm_up_steps) / (self.lr_max_decay_steps - self.lr_warm_up_steps)
+            t = min(t, 1.0)
+            lr = self.lr_min + 0.5 * (self.lr_max - self.lr_min) * (
+                    1 + np.cos(t * np.pi))
+            self.last_lr = lr
+            return lr
+
+    def __call__(self, n, **kwargs):
+        return self.schedule(n,**kwargs)
+
+
+class LambdaWarmUpCosineScheduler2:
+    """
+    supports repeated iterations, configurable via lists
+    note: use with a base_lr of 1.0.
+    """
+    def __init__(self, warm_up_steps, f_min, f_max, f_start, cycle_lengths, verbosity_interval=0):
+        assert len(warm_up_steps) == len(f_min) == len(f_max) == len(f_start) == len(cycle_lengths)
+        self.lr_warm_up_steps = warm_up_steps
+        self.f_start = f_start
+        self.f_min = f_min
+        self.f_max = f_max
+        self.cycle_lengths = cycle_lengths
+        self.cum_cycles = np.cumsum([0] + list(self.cycle_lengths))
+        self.last_f = 0.
+        self.verbosity_interval = verbosity_interval
+
+    def find_in_interval(self, n):
+        interval = 0
+        for cl in self.cum_cycles[1:]:
+            if n <= cl:
+                return interval
+            interval += 1
+
+    def schedule(self, n, **kwargs):
+        cycle = self.find_in_interval(n)
+        n = n - self.cum_cycles[cycle]
+        if self.verbosity_interval > 0:
+            if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_f}, "
+                                                       f"current cycle {cycle}")
+        if n < self.lr_warm_up_steps[cycle]:
+            f = (self.f_max[cycle] - self.f_start[cycle]) / self.lr_warm_up_steps[cycle] * n + self.f_start[cycle]
+            self.last_f = f
+            return f
+        else:
+            t = (n - self.lr_warm_up_steps[cycle]) / (self.cycle_lengths[cycle] - self.lr_warm_up_steps[cycle])
+            t = min(t, 1.0)
+            f = self.f_min[cycle] + 0.5 * (self.f_max[cycle] - self.f_min[cycle]) * (
+                    1 + np.cos(t * np.pi))
+            self.last_f = f
+            return f
+
+    def __call__(self, n, **kwargs):
+        return self.schedule(n, **kwargs)
+
+
+class LambdaLinearScheduler(LambdaWarmUpCosineScheduler2):
+
+    def schedule(self, n, **kwargs):
+        cycle = self.find_in_interval(n)
+        n = n - self.cum_cycles[cycle]
+        if self.verbosity_interval > 0:
+            if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_f}, "
+                                                       f"current cycle {cycle}")
+
+        if n < self.lr_warm_up_steps[cycle]:
+            f = (self.f_max[cycle] - self.f_start[cycle]) / self.lr_warm_up_steps[cycle] * n + self.f_start[cycle]
+            self.last_f = f
+            return f
+        else:
+            f = self.f_min[cycle] + (self.f_max[cycle] - self.f_min[cycle]) * (self.cycle_lengths[cycle] - n) / (self.cycle_lengths[cycle])
+            self.last_f = f
+            return f
+

ldm/models/autoencoder.py

@@ -0,0 +1,443 @@
+import torch
+import pytorch_lightning as pl
+import torch.nn.functional as F
+from contextlib import contextmanager
+
+from taming.modules.vqvae.quantize import VectorQuantizer2 as VectorQuantizer
+
+from ldm.modules.diffusionmodules.model import Encoder, Decoder
+from ldm.modules.distributions.distributions import DiagonalGaussianDistribution
+
+from ldm.util import instantiate_from_config
+
+
+class VQModel(pl.LightningModule):
+    def __init__(self,
+                 ddconfig,
+                 lossconfig,
+                 n_embed,
+                 embed_dim,
+                 ckpt_path=None,
+                 ignore_keys=[],
+                 image_key="image",
+                 colorize_nlabels=None,
+                 monitor=None,
+                 batch_resize_range=None,
+                 scheduler_config=None,
+                 lr_g_factor=1.0,
+                 remap=None,
+                 sane_index_shape=False, # tell vector quantizer to return indices as bhw
+                 use_ema=False
+                 ):
+        super().__init__()
+        self.embed_dim = embed_dim
+        self.n_embed = n_embed
+        self.image_key = image_key
+        self.encoder = Encoder(**ddconfig)
+        self.decoder = Decoder(**ddconfig)
+        self.loss = instantiate_from_config(lossconfig)
+        self.quantize = VectorQuantizer(n_embed, embed_dim, beta=0.25,
+                                        remap=remap,
+                                        sane_index_shape=sane_index_shape)
+        self.quant_conv = torch.nn.Conv2d(ddconfig["z_channels"], embed_dim, 1)
+        self.post_quant_conv = torch.nn.Conv2d(embed_dim, ddconfig["z_channels"], 1)
+        if colorize_nlabels is not None:
+            assert type(colorize_nlabels)==int
+            self.register_buffer("colorize", torch.randn(3, colorize_nlabels, 1, 1))
+        if monitor is not None:
+            self.monitor = monitor
+        self.batch_resize_range = batch_resize_range
+        if self.batch_resize_range is not None:
+            print(f"{self.__class__.__name__}: Using per-batch resizing in range {batch_resize_range}.")
+
+        self.use_ema = use_ema
+        if self.use_ema:
+            self.model_ema = LitEma(self)
+            print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+        if ckpt_path is not None:
+            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys)
+        self.scheduler_config = scheduler_config
+        self.lr_g_factor = lr_g_factor
+
+    @contextmanager
+    def ema_scope(self, context=None):
+        if self.use_ema:
+            self.model_ema.store(self.parameters())
+            self.model_ema.copy_to(self)
+            if context is not None:
+                print(f"{context}: Switched to EMA weights")
+        try:
+            yield None
+        finally:
+            if self.use_ema:
+                self.model_ema.restore(self.parameters())
+                if context is not None:
+                    print(f"{context}: Restored training weights")
+
+    def init_from_ckpt(self, path, ignore_keys=list()):
+        sd = torch.load(path, map_location="cpu")["state_dict"]
+        keys = list(sd.keys())
+        for k in keys:
+            for ik in ignore_keys:
+                if k.startswith(ik):
+                    print("Deleting key {} from state_dict.".format(k))
+                    del sd[k]
+        missing, unexpected = self.load_state_dict(sd, strict=False)
+        print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
+        if len(missing) > 0:
+            print(f"Missing Keys: {missing}")
+            print(f"Unexpected Keys: {unexpected}")
+
+    def on_train_batch_end(self, *args, **kwargs):
+        if self.use_ema:
+            self.model_ema(self)
+
+    def encode(self, x):
+        h = self.encoder(x)
+        h = self.quant_conv(h)
+        quant, emb_loss, info = self.quantize(h)
+        return quant, emb_loss, info
+
+    def encode_to_prequant(self, x):
+        h = self.encoder(x)
+        h = self.quant_conv(h)
+        return h
+
+    def decode(self, quant):
+        quant = self.post_quant_conv(quant)
+        dec = self.decoder(quant)
+        return dec
+
+    def decode_code(self, code_b):
+        quant_b = self.quantize.embed_code(code_b)
+        dec = self.decode(quant_b)
+        return dec
+
+    def forward(self, input, return_pred_indices=False):
+        quant, diff, (_,_,ind) = self.encode(input)
+        dec = self.decode(quant)
+        if return_pred_indices:
+            return dec, diff, ind
+        return dec, diff
+
+    def get_input(self, batch, k):
+        x = batch[k]
+        if len(x.shape) == 3:
+            x = x[..., None]
+        x = x.permute(0, 3, 1, 2).to(memory_format=torch.contiguous_format).float()
+        if self.batch_resize_range is not None:
+            lower_size = self.batch_resize_range[0]
+            upper_size = self.batch_resize_range[1]
+            if self.global_step <= 4:
+                # do the first few batches with max size to avoid later oom
+                new_resize = upper_size
+            else:
+                new_resize = np.random.choice(np.arange(lower_size, upper_size+16, 16))
+            if new_resize != x.shape[2]:
+                x = F.interpolate(x, size=new_resize, mode="bicubic")
+            x = x.detach()
+        return x
+
+    def training_step(self, batch, batch_idx, optimizer_idx):
+        # https://github.com/pytorch/pytorch/issues/37142
+        # try not to fool the heuristics
+        x = self.get_input(batch, self.image_key)
+        xrec, qloss, ind = self(x, return_pred_indices=True)
+
+        if optimizer_idx == 0:
+            # autoencode
+            aeloss, log_dict_ae = self.loss(qloss, x, xrec, optimizer_idx, self.global_step,
+                                            last_layer=self.get_last_layer(), split="train",
+                                            predicted_indices=ind)
+
+            self.log_dict(log_dict_ae, prog_bar=False, logger=True, on_step=True, on_epoch=True)
+            return aeloss
+
+        if optimizer_idx == 1:
+            # discriminator
+            discloss, log_dict_disc = self.loss(qloss, x, xrec, optimizer_idx, self.global_step,
+                                            last_layer=self.get_last_layer(), split="train")
+            self.log_dict(log_dict_disc, prog_bar=False, logger=True, on_step=True, on_epoch=True)
+            return discloss
+
+    def validation_step(self, batch, batch_idx):
+        log_dict = self._validation_step(batch, batch_idx)
+        with self.ema_scope():
+            log_dict_ema = self._validation_step(batch, batch_idx, suffix="_ema")
+        return log_dict
+
+    def _validation_step(self, batch, batch_idx, suffix=""):
+        x = self.get_input(batch, self.image_key)
+        xrec, qloss, ind = self(x, return_pred_indices=True)
+        aeloss, log_dict_ae = self.loss(qloss, x, xrec, 0,
+                                        self.global_step,
+                                        last_layer=self.get_last_layer(),
+                                        split="val"+suffix,
+                                        predicted_indices=ind
+                                        )
+
+        discloss, log_dict_disc = self.loss(qloss, x, xrec, 1,
+                                            self.global_step,
+                                            last_layer=self.get_last_layer(),
+                                            split="val"+suffix,
+                                            predicted_indices=ind
+                                            )
+        rec_loss = log_dict_ae[f"val{suffix}/rec_loss"]
+        self.log(f"val{suffix}/rec_loss", rec_loss,
+                   prog_bar=True, logger=True, on_step=False, on_epoch=True, sync_dist=True)
+        self.log(f"val{suffix}/aeloss", aeloss,
+                   prog_bar=True, logger=True, on_step=False, on_epoch=True, sync_dist=True)
+        if version.parse(pl.__version__) >= version.parse('1.4.0'):
+            del log_dict_ae[f"val{suffix}/rec_loss"]
+        self.log_dict(log_dict_ae)
+        self.log_dict(log_dict_disc)
+        return self.log_dict
+
+    def configure_optimizers(self):
+        lr_d = self.learning_rate
+        lr_g = self.lr_g_factor*self.learning_rate
+        print("lr_d", lr_d)
+        print("lr_g", lr_g)
+        opt_ae = torch.optim.Adam(list(self.encoder.parameters())+
+                                  list(self.decoder.parameters())+
+                                  list(self.quantize.parameters())+
+                                  list(self.quant_conv.parameters())+
+                                  list(self.post_quant_conv.parameters()),
+                                  lr=lr_g, betas=(0.5, 0.9))
+        opt_disc = torch.optim.Adam(self.loss.discriminator.parameters(),
+                                    lr=lr_d, betas=(0.5, 0.9))
+
+        if self.scheduler_config is not None:
+            scheduler = instantiate_from_config(self.scheduler_config)
+
+            print("Setting up LambdaLR scheduler...")
+            scheduler = [
+                {
+                    'scheduler': LambdaLR(opt_ae, lr_lambda=scheduler.schedule),
+                    'interval': 'step',
+                    'frequency': 1
+                },
+                {
+                    'scheduler': LambdaLR(opt_disc, lr_lambda=scheduler.schedule),
+                    'interval': 'step',
+                    'frequency': 1
+                },
+            ]
+            return [opt_ae, opt_disc], scheduler
+        return [opt_ae, opt_disc], []
+
+    def get_last_layer(self):
+        return self.decoder.conv_out.weight
+
+    def log_images(self, batch, only_inputs=False, plot_ema=False, **kwargs):
+        log = dict()
+        x = self.get_input(batch, self.image_key)
+        x = x.to(self.device)
+        if only_inputs:
+            log["inputs"] = x
+            return log
+        xrec, _ = self(x)
+        if x.shape[1] > 3:
+            # colorize with random projection
+            assert xrec.shape[1] > 3
+            x = self.to_rgb(x)
+            xrec = self.to_rgb(xrec)
+        log["inputs"] = x
+        log["reconstructions"] = xrec
+        if plot_ema:
+            with self.ema_scope():
+                xrec_ema, _ = self(x)
+                if x.shape[1] > 3: xrec_ema = self.to_rgb(xrec_ema)
+                log["reconstructions_ema"] = xrec_ema
+        return log
+
+    def to_rgb(self, x):
+        assert self.image_key == "segmentation"
+        if not hasattr(self, "colorize"):
+            self.register_buffer("colorize", torch.randn(3, x.shape[1], 1, 1).to(x))
+        x = F.conv2d(x, weight=self.colorize)
+        x = 2.*(x-x.min())/(x.max()-x.min()) - 1.
+        return x
+
+
+class VQModelInterface(VQModel):
+    def __init__(self, embed_dim, *args, **kwargs):
+        super().__init__(embed_dim=embed_dim, *args, **kwargs)
+        self.embed_dim = embed_dim
+
+    def encode(self, x):
+        h = self.encoder(x)
+        h = self.quant_conv(h)
+        return h
+
+    def decode(self, h, force_not_quantize=False):
+        # also go through quantization layer
+        if not force_not_quantize:
+            quant, emb_loss, info = self.quantize(h)
+        else:
+            quant = h
+        quant = self.post_quant_conv(quant)
+        dec = self.decoder(quant)
+        return dec
+
+
+class AutoencoderKL(pl.LightningModule):
+    def __init__(self,
+                 ddconfig,
+                 lossconfig,
+                 embed_dim,
+                 ckpt_path=None,
+                 ignore_keys=[],
+                 image_key="image",
+                 colorize_nlabels=None,
+                 monitor=None,
+                 ):
+        super().__init__()
+        self.image_key = image_key
+        self.encoder = Encoder(**ddconfig)
+        self.decoder = Decoder(**ddconfig)
+        self.loss = instantiate_from_config(lossconfig)
+        assert ddconfig["double_z"]
+        self.quant_conv = torch.nn.Conv2d(2*ddconfig["z_channels"], 2*embed_dim, 1)
+        self.post_quant_conv = torch.nn.Conv2d(embed_dim, ddconfig["z_channels"], 1)
+        self.embed_dim = embed_dim
+        if colorize_nlabels is not None:
+            assert type(colorize_nlabels)==int
+            self.register_buffer("colorize", torch.randn(3, colorize_nlabels, 1, 1))
+        if monitor is not None:
+            self.monitor = monitor
+        if ckpt_path is not None:
+            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys)
+
+    def init_from_ckpt(self, path, ignore_keys=list()):
+        sd = torch.load(path, map_location="cpu")["state_dict"]
+        keys = list(sd.keys())
+        for k in keys:
+            for ik in ignore_keys:
+                if k.startswith(ik):
+                    print("Deleting key {} from state_dict.".format(k))
+                    del sd[k]
+        self.load_state_dict(sd, strict=False)
+        print(f"Restored from {path}")
+
+    def encode(self, x):
+        h = self.encoder(x)
+        moments = self.quant_conv(h)
+        posterior = DiagonalGaussianDistribution(moments)
+        return posterior
+
+    def decode(self, z):
+        z = self.post_quant_conv(z)
+        dec = self.decoder(z)
+        return dec
+
+    def forward(self, input, sample_posterior=True):
+        posterior = self.encode(input)
+        if sample_posterior:
+            z = posterior.sample()
+        else:
+            z = posterior.mode()
+        dec = self.decode(z)
+        return dec, posterior
+
+    def get_input(self, batch, k):
+        x = batch[k]
+        if len(x.shape) == 3:
+            x = x[..., None]
+        x = x.permute(0, 3, 1, 2).to(memory_format=torch.contiguous_format).float()
+        return x
+
+    def training_step(self, batch, batch_idx, optimizer_idx):
+        inputs = self.get_input(batch, self.image_key)
+        reconstructions, posterior = self(inputs)
+
+        if optimizer_idx == 0:
+            # train encoder+decoder+logvar
+            aeloss, log_dict_ae = self.loss(inputs, reconstructions, posterior, optimizer_idx, self.global_step,
+                                            last_layer=self.get_last_layer(), split="train")
+            self.log("aeloss", aeloss, prog_bar=True, logger=True, on_step=True, on_epoch=True)
+            self.log_dict(log_dict_ae, prog_bar=False, logger=True, on_step=True, on_epoch=False)
+            return aeloss
+
+        if optimizer_idx == 1:
+            # train the discriminator
+            discloss, log_dict_disc = self.loss(inputs, reconstructions, posterior, optimizer_idx, self.global_step,
+                                                last_layer=self.get_last_layer(), split="train")
+
+            self.log("discloss", discloss, prog_bar=True, logger=True, on_step=True, on_epoch=True)
+            self.log_dict(log_dict_disc, prog_bar=False, logger=True, on_step=True, on_epoch=False)
+            return discloss
+
+    def validation_step(self, batch, batch_idx):
+        inputs = self.get_input(batch, self.image_key)
+        reconstructions, posterior = self(inputs)
+        aeloss, log_dict_ae = self.loss(inputs, reconstructions, posterior, 0, self.global_step,
+                                        last_layer=self.get_last_layer(), split="val")
+
+        discloss, log_dict_disc = self.loss(inputs, reconstructions, posterior, 1, self.global_step,
+                                            last_layer=self.get_last_layer(), split="val")
+
+        self.log("val/rec_loss", log_dict_ae["val/rec_loss"])
+        self.log_dict(log_dict_ae)
+        self.log_dict(log_dict_disc)
+        return self.log_dict
+
+    def configure_optimizers(self):
+        lr = self.learning_rate
+        opt_ae = torch.optim.Adam(list(self.encoder.parameters())+
+                                  list(self.decoder.parameters())+
+                                  list(self.quant_conv.parameters())+
+                                  list(self.post_quant_conv.parameters()),
+                                  lr=lr, betas=(0.5, 0.9))
+        opt_disc = torch.optim.Adam(self.loss.discriminator.parameters(),
+                                    lr=lr, betas=(0.5, 0.9))
+        return [opt_ae, opt_disc], []
+
+    def get_last_layer(self):
+        return self.decoder.conv_out.weight
+
+    @torch.no_grad()
+    def log_images(self, batch, only_inputs=False, **kwargs):
+        log = dict()
+        x = self.get_input(batch, self.image_key)
+        x = x.to(self.device)
+        if not only_inputs:
+            xrec, posterior = self(x)
+            if x.shape[1] > 3:
+                # colorize with random projection
+                assert xrec.shape[1] > 3
+                x = self.to_rgb(x)
+                xrec = self.to_rgb(xrec)
+            log["samples"] = self.decode(torch.randn_like(posterior.sample()))
+            log["reconstructions"] = xrec
+        log["inputs"] = x
+        return log
+
+    def to_rgb(self, x):
+        assert self.image_key == "segmentation"
+        if not hasattr(self, "colorize"):
+            self.register_buffer("colorize", torch.randn(3, x.shape[1], 1, 1).to(x))
+        x = F.conv2d(x, weight=self.colorize)
+        x = 2.*(x-x.min())/(x.max()-x.min()) - 1.
+        return x
+
+
+class IdentityFirstStage(torch.nn.Module):
+    def __init__(self, *args, vq_interface=False, **kwargs):
+        self.vq_interface = vq_interface  # TODO: Should be true by default but check to not break older stuff
+        super().__init__()
+
+    def encode(self, x, *args, **kwargs):
+        return x
+
+    def decode(self, x, *args, **kwargs):
+        return x
+
+    def quantize(self, x, *args, **kwargs):
+        if self.vq_interface:
+            return x, None, [None, None, None]
+        return x
+
+    def forward(self, x, *args, **kwargs):
+        return x