dreambooth and custom diffusion upload

custom-diffusion/barn+dog-sdv4/checkpoints/delta_epoch=000004.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0372ff0308d045281cb19575ae382a6ba8f26ca0a466c55683d8a9f2bd76e22c
+size 76694594

custom-diffusion/barn+dog-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/barn+dog-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> barn
+        reg_caption: real_reg/samples_barn/caption.txt
+        datapath: data/barn
+        reg_datapath: real_reg/samples_barn/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> dog
+        reg_caption: real_reg/samples_dog/caption.txt
+        datapath: data/dog
+        reg_datapath: real_reg/samples_dog/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> barn
+        reg_caption: real_reg/samples_barn/caption.txt
+        datapath: data/barn
+        reg_datapath: real_reg/samples_barn/images.txt

custom-diffusion/cat+chair-sdv4/checkpoints/delta_epoch=000004.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b869e0a6787671e7d6c6c37722f32d5c91b14a6f052cff10fa95418873b07b
+size 76694594

custom-diffusion/cat+chair-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/cat+chair-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> cat
+        reg_caption: real_reg/samples_cat/caption.txt
+        datapath: data/cat
+        reg_datapath: real_reg/samples_cat/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> chair
+        reg_caption: real_reg/samples_chair/caption.txt
+        datapath: data/chair
+        reg_datapath: real_reg/samples_chair/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> cat
+        reg_caption: real_reg/samples_cat/caption.txt
+        datapath: data/cat
+        reg_datapath: real_reg/samples_cat/images.txt

custom-diffusion/dog+car-sdv4/checkpoints/delta_epoch=000004.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e7d7141ab88e13e64000d5beaf18987107983cc3ac492b0d48be76e2e38a3f
+size 76694594

custom-diffusion/dog+car-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/dog+car-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> dog
+        reg_caption: real_reg/samples_dog/caption.txt
+        datapath: data/dog
+        reg_datapath: real_reg/samples_dog/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> car
+        reg_caption: real_reg/samples_car/caption.txt
+        datapath: data/car
+        reg_datapath: real_reg/samples_car/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> dog
+        reg_caption: real_reg/samples_dog/caption.txt
+        datapath: data/dog
+        reg_datapath: real_reg/samples_dog/images.txt

custom-diffusion/dog+table-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/dog+table-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> dog
+        reg_caption: real_reg/samples_dog/caption.txt
+        datapath: data/dog
+        reg_datapath: real_reg/samples_dog/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> table
+        reg_caption: real_reg/samples_table/caption.txt
+        datapath: data/table
+        reg_datapath: real_reg/samples_table/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> dog
+        reg_caption: real_reg/samples_dog/caption.txt
+        datapath: data/dog
+        reg_datapath: real_reg/samples_dog/images.txt

custom-diffusion/flower+teddybear-sdv4/checkpoints/delta_epoch=000004.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05af2d2ccda3d0999c9faa66bf6c3d02953e1d3905fddfce5be5607f024bb45
+size 76694594

custom-diffusion/flower+teddybear-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/flower+teddybear-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> flower
+        reg_caption: real_reg/samples_flower/caption.txt
+        datapath: data/flower
+        reg_datapath: real_reg/samples_flower/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> teddybear
+        reg_caption: real_reg/samples_teddybear/caption.txt
+        datapath: data/teddybear
+        reg_datapath: real_reg/samples_teddybear/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> flower
+        reg_caption: real_reg/samples_flower/caption.txt
+        datapath: data/flower
+        reg_datapath: real_reg/samples_flower/images.txt

custom-diffusion/sd-v1-4.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4efff1e174c627256e44ec2991ba279b3816e364b49f9be2abc0b3ff3f8556
+size 4265380512

custom-diffusion/table+chair-sdv4/checkpoints/delta_epoch=000004.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1409a0f6601841298fd4b6da9db8190ee81575e19debf9f6ee36eca95f499d3
+size 76694594

custom-diffusion/table+chair-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/table+chair-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> table
+        reg_caption: real_reg/samples_table/caption.txt
+        datapath: data/table
+        reg_datapath: real_reg/samples_table/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> chair
+        reg_caption: real_reg/samples_chair/caption.txt
+        datapath: data/chair
+        reg_datapath: real_reg/samples_chair/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> table
+        reg_caption: real_reg/samples_table/caption.txt
+        datapath: data/table
+        reg_datapath: real_reg/samples_table/images.txt

custom-diffusion/teddybear+barn-sdv4/checkpoints/delta_epoch=000004.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11b477068cbe5d6786e32ac89e4f1aafb9dc5e7a9e790af3fe1120865021fd4
+size 76694594

custom-diffusion/teddybear+barn-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/teddybear+barn-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> teddybear
+        reg_caption: real_reg/samples_teddybear/caption.txt
+        datapath: data/teddybear
+        reg_datapath: real_reg/samples_teddybear/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> barn
+        reg_caption: real_reg/samples_barn/caption.txt
+        datapath: data/barn
+        reg_datapath: real_reg/samples_barn/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> teddybear
+        reg_caption: real_reg/samples_teddybear/caption.txt
+        datapath: data/teddybear
+        reg_datapath: real_reg/samples_teddybear/images.txt

custom-diffusion/teddybear+car-sdv4/checkpoints/delta_epoch=000004.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e407963aabdabd7b849be4d590436d15ccb39104e0ce12b46157cdc5eda7776
+size 76694594

custom-diffusion/teddybear+car-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/teddybear+car-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> teddybear
+        reg_caption: real_reg/samples_teddybear/caption.txt
+        datapath: data/teddybear
+        reg_datapath: real_reg/samples_teddybear/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> car
+        reg_caption: real_reg/samples_car/caption.txt
+        datapath: data/car
+        reg_datapath: real_reg/samples_car/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> teddybear
+        reg_caption: real_reg/samples_teddybear/caption.txt
+        datapath: data/teddybear
+        reg_datapath: real_reg/samples_teddybear/images.txt

custom-diffusion/tortoise_plushy+cat-sdv4/checkpoints/delta_epoch=000004.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b42e3e6098721eab1de81c7a57988dae1e25b0e80a63e5a8aafc717f1a1469c
+size 76694594

custom-diffusion/tortoise_plushy+cat-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/tortoise_plushy+cat-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> tortoise plushy
+        reg_caption: real_reg/samples_tortoise_plushy/caption.txt
+        datapath: data/tortoise_plushy
+        reg_datapath: real_reg/samples_tortoise_plushy/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> cat
+        reg_caption: real_reg/samples_cat/caption.txt
+        datapath: data/cat
+        reg_datapath: real_reg/samples_cat/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> tortoise plushy
+        reg_caption: real_reg/samples_tortoise_plushy/caption.txt
+        datapath: data/tortoise_plushy
+        reg_datapath: real_reg/samples_tortoise_plushy/images.txt

custom-diffusion/tortoise_plushy+table-sdv4/checkpoints/delta_epoch=000004.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec7d03e07edbb8373f3f1355a58479dfe1312ead51aecede686ea0446b282c9b
+size 76694594

custom-diffusion/tortoise_plushy+table-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/tortoise_plushy+table-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> tortoise plushy
+        reg_caption: real_reg/samples_tortoise_plushy/caption.txt
+        datapath: data/tortoise_plushy
+        reg_datapath: real_reg/samples_tortoise_plushy/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> table
+        reg_caption: real_reg/samples_table/caption.txt
+        datapath: data/table
+        reg_datapath: real_reg/samples_table/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> tortoise plushy
+        reg_caption: real_reg/samples_tortoise_plushy/caption.txt
+        datapath: data/tortoise_plushy
+        reg_datapath: real_reg/samples_tortoise_plushy/images.txt

custom-diffusion/wooden_pot+cat-sdv4/checkpoints/delta_epoch=000004.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f2d8c94b22848c3feb695192b43fc7fa2ce7ded7f368097b4c06ed89c96e7d
+size 76694594

custom-diffusion/wooden_pot+cat-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/wooden_pot+cat-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> wooden pot
+        reg_caption: real_reg/samples_wooden_pot/caption.txt
+        datapath: data/wooden_pot
+        reg_datapath: real_reg/samples_wooden_pot/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> cat
+        reg_caption: real_reg/samples_cat/caption.txt
+        datapath: data/cat
+        reg_datapath: real_reg/samples_cat/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> wooden pot
+        reg_caption: real_reg/samples_wooden_pot/caption.txt
+        datapath: data/wooden_pot
+        reg_datapath: real_reg/samples_wooden_pot/images.txt

custom-diffusion/wooden_pot+flower-sdv4/checkpoints/delta_epoch=000004.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d49f760131043be0d0aedcc1a6de61a87543a1cffee4951a09495ef3f0c4f88
+size 76694594

custom-diffusion/wooden_pot+flower-sdv4/configs/lightning.yaml

@@ -0,0 +1,12 @@
+lightning:
+  callbacks:
+    image_logger:
+      target: train.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: false
+  trainer:
+    max_steps: 550
+    accelerator: ddp
+    gpus: 0,1,2,3

custom-diffusion/wooden_pot+flower-sdv4/configs/project.yaml

@@ -0,0 +1,100 @@
+model:
+  base_learning_rate: 1.0e-05
+  target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.model.CustomDiffusion
+  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: 64
+    channels: 4
+    cond_stage_trainable: true
+    add_token: true
+    freeze_model: crossattn-kv
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: false
+    unet_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 64
+        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: false
+        legacy: false
+    first_stage_config:
+      target: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.stable-diffusion.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: src.imagen_hub.pipelines.custom_diffusion.custom_diffusion_src.src.custom_modules.FrozenCLIPEmbedderWrapper
+      params:
+        modifier_token: <new1>+<new2>
+    ckpt_path: null
+data:
+  target: train.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 4
+    wrap: false
+    train:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> wooden pot
+        reg_caption: real_reg/samples_wooden_pot/caption.txt
+        datapath: data/wooden_pot
+        reg_datapath: real_reg/samples_wooden_pot/images.txt
+    train2:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new2> flower
+        reg_caption: real_reg/samples_flower/caption.txt
+        datapath: data/flower
+        reg_datapath: real_reg/samples_flower/images.txt
+    validation:
+      target: src.finetune_data.MaskBase
+      params:
+        size: 512
+        caption: <new1> wooden pot
+        reg_caption: real_reg/samples_wooden_pot/caption.txt
+        datapath: data/wooden_pot
+        reg_datapath: real_reg/samples_wooden_pot/images.txt

dreambooth/cat+chair/feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

dreambooth/cat+chair/model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.18.0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    "stable_diffusion",
+    "StableDiffusionSafetyChecker"
+  ],
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

dreambooth/cat+chair/safety_checker/config.json

@@ -0,0 +1,168 @@
+{
+  "_commit_hash": "133a221b8aa7292a167afc5127cb63fb5005638b",
+  "_name_or_path": "/home1/x/xingyuf2/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/safety_checker",
+  "architectures": [
+    "StableDiffusionSafetyChecker"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.28.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.28.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

dreambooth/cat+chair/safety_checker/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f5f098f12e0b765dd8f917182dccbea8c87d269265f3e616cf67282c426940
+size 1216067303

dreambooth/cat+chair/scheduler/scheduler_config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "PNDMScheduler",
+  "_diffusers_version": "0.18.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

dreambooth/cat+chair/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home1/x/xingyuf2/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "vocab_size": 49408
+}

dreambooth/cat+chair/text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:485096afb4482023ec75c414a5373ba300aa91a4cc2ab534074b5748d6b91ee8
+size 492308087

dreambooth/cat+chair/tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

dreambooth/cat+chair/tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

dreambooth/cat+chair/unet/config.json

@@ -0,0 +1,65 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.18.0",
+  "_name_or_path": "/home1/x/xingyuf2/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/unet",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

dreambooth/cat+chair/unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c16134d186c043f85eecdbc7d410de06f51d0cbfb668572325d4599c1c12372
+size 3438364325

dreambooth/cat+chair/vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.18.0",
+  "_name_or_path": "/home1/x/xingyuf2/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}