Upload 104 files

models/configs/anything_v3.yaml

@@ -0,0 +1,73 @@
+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
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    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
+      params:
+        layer: "hidden"
+        layer_idx: -2

models/configs/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
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    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

models/configs/v1-inference_clip_skip_2.yaml

@@ -0,0 +1,73 @@
+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
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    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
+      params:
+        layer: "hidden"
+        layer_idx: -2

models/configs/v1-inference_clip_skip_2_fp16.yaml

@@ -0,0 +1,74 @@
+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
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_fp16: True
+        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
+      params:
+        layer: "hidden"
+        layer_idx: -2

models/configs/v1-inference_fp16.yaml

@@ -0,0 +1,71 @@
+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
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_fp16: True
+        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

models/configs/v1-inpainting-inference.yaml

@@ -0,0 +1,71 @@
+model:
+  base_learning_rate: 7.5e-05
+  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
+  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: hybrid   # important
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    finetune_keys: null
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 9  # 4 data + 4 downscaled image + 1 mask
+        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
+

models/configs/v2-inference-v.yaml

@@ -0,0 +1,68 @@
+model:
+  base_learning_rate: 1.0e-4
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    parameterization: "v"
+    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
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False # we set this to false because this is an inference only config
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        use_fp16: True
+        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_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          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.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"

models/configs/v2-inference-v_fp32.yaml

@@ -0,0 +1,68 @@
+model:
+  base_learning_rate: 1.0e-4
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    parameterization: "v"
+    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
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False # we set this to false because this is an inference only config
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        use_fp16: False
+        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_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          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.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"

models/configs/v2-inference.yaml

@@ -0,0 +1,67 @@
+model:
+  base_learning_rate: 1.0e-4
+  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
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False # we set this to false because this is an inference only config
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        use_fp16: True
+        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_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          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.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"

models/configs/v2-inference_fp32.yaml

@@ -0,0 +1,67 @@
+model:
+  base_learning_rate: 1.0e-4
+  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
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False # we set this to false because this is an inference only config
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        use_fp16: False
+        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_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          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.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"

models/configs/v2-inpainting-inference.yaml

@@ -0,0 +1,158 @@
+model:
+  base_learning_rate: 5.0e-05
+  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
+  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
+    conditioning_key: hybrid
+    scale_factor: 0.18215
+    monitor: val/loss_simple_ema
+    finetune_keys: null
+    use_ema: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        image_size: 32 # unused
+        in_channels: 9
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          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.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"
+
+
+data:
+  target: ldm.data.laion.WebDataModuleFromConfig
+  params:
+    tar_base: null  # for concat as in LAION-A
+    p_unsafe_threshold: 0.1
+    filter_word_list: "data/filters.yaml"
+    max_pwatermark: 0.45
+    batch_size: 8
+    num_workers: 6
+    multinode: True
+    min_size: 512
+    train:
+      shards:
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-0/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-1/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-2/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-3/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-4/{00000..18699}.tar -"  #{00000-94333}.tar"
+      shuffle: 10000
+      image_key: jpg
+      image_transforms:
+      - target: torchvision.transforms.Resize
+        params:
+          size: 512
+          interpolation: 3
+      - target: torchvision.transforms.RandomCrop
+        params:
+          size: 512
+      postprocess:
+        target: ldm.data.laion.AddMask
+        params:
+          mode: "512train-large"
+          p_drop: 0.25
+    # NOTE use enough shards to avoid empty validation loops in workers
+    validation:
+      shards:
+        - "pipe:aws s3 cp s3://deep-floyd-s3/datasets/laion_cleaned-part5/{93001..94333}.tar - "
+      shuffle: 0
+      image_key: jpg
+      image_transforms:
+      - target: torchvision.transforms.Resize
+        params:
+          size: 512
+          interpolation: 3
+      - target: torchvision.transforms.CenterCrop
+        params:
+          size: 512
+      postprocess:
+        target: ldm.data.laion.AddMask
+        params:
+          mode: "512train-large"
+          p_drop: 0.25
+
+lightning:
+  find_unused_parameters: True
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 5000
+
+  callbacks:
+    metrics_over_trainsteps_checkpoint:
+      params:
+        every_n_train_steps: 10000
+
+    image_logger:
+      target: main.ImageLogger
+      params:
+        enable_autocast: False
+        disabled: False
+        batch_frequency: 1000
+        max_images: 4
+        increase_log_steps: False
+        log_first_step: False
+        log_images_kwargs:
+          use_ema_scope: False
+          inpaint: False
+          plot_progressive_rows: False
+          plot_diffusion_rows: False
+          N: 4
+          unconditional_guidance_scale: 5.0
+          unconditional_guidance_label: [""]
+          ddim_steps: 50  # todo check these out for depth2img,
+          ddim_eta: 0.0   # todo check these out for depth2img,
+
+  trainer:
+    benchmark: True
+    val_check_interval: 5000000
+    num_sanity_val_steps: 0
+    accumulate_grad_batches: 1

models/segformer-b3-fashion/.cache/huggingface/.gitignore

@@ -0,0 +1 @@
+*

models/segformer-b3-fashion/.cache/huggingface/download/.gitattributes.metadata

@@ -0,0 +1,3 @@
+e2474a9e7643d349ac6c525549b736b736e7e216
+a6344aac8c09253b3b630fb776ae94478aa0275b
+1737415590.9016962

models/segformer-b3-fashion/.cache/huggingface/download/.gitignore.metadata

@@ -0,0 +1,3 @@
+e2474a9e7643d349ac6c525549b736b736e7e216
+0348ea97130c017c407fcfb6fd4003859f17b84c
+1737415590.8378365

models/segformer-b3-fashion/.cache/huggingface/download/README.md.metadata

@@ -0,0 +1,3 @@
+e2474a9e7643d349ac6c525549b736b736e7e216
+4aa7d6b75f0baf02db7064559e1864163d7a35b0
+1737415590.8593767

models/segformer-b3-fashion/.cache/huggingface/download/config.json.metadata

@@ -0,0 +1,3 @@
+e2474a9e7643d349ac6c525549b736b736e7e216
+8fb2769b75445217cf9bc737f56abd740f313f1d
+1737415591.1487901

models/segformer-b3-fashion/.cache/huggingface/download/model.safetensors.metadata

@@ -0,0 +1,3 @@
+e2474a9e7643d349ac6c525549b736b736e7e216
+f3f5b30179f1480d329224d089f6d286580142c2b12846d08de814a48a81f42f
+1737415597.3801692

models/segformer-b3-fashion/.cache/huggingface/download/preprocessor_config.json.metadata

@@ -0,0 +1,3 @@
+e2474a9e7643d349ac6c525549b736b736e7e216
+b2340cf4e53b37fda4f5b92d28f11c0f33c3d0fd
+1737415590.8854265

models/segformer-b3-fashion/.cache/huggingface/download/pytorch_model.bin.metadata

@@ -0,0 +1,3 @@
+e2474a9e7643d349ac6c525549b736b736e7e216
+ec5749e86e5efad5d9dbbf7c2e4b996d675548dc22f26b06c0f1b6fc2e8bc1e2
+1737415599.2630093

models/segformer-b3-fashion/.cache/huggingface/download/training_args.bin.metadata

@@ -0,0 +1,3 @@
+e2474a9e7643d349ac6c525549b736b736e7e216
+f871f7bdbc3af72746e7b76beb628f6365db08040b58b3071238dca986de97ca
+1737415590.913134

models/segformer-b3-fashion/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

models/segformer-b3-fashion/.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

models/segformer-b3-fashion/README.md

@@ -0,0 +1,92 @@
+---
+license: other
+tags:
+- vision
+- image-segmentation
+- generated_from_trainer
+widget:
+- src: >-
+    https://media.istockphoto.com/id/515788534/photo/cheerful-and-confidant.jpg?s=612x612&w=0&k=20&c=T0Z4DfameRpyGhzevPomrm-wjZp7wmGjpAyjGcTzpkA=
+  example_title: Person
+- src: >-
+    https://storage.googleapis.com/pai-images/1484fd9ea9d746eb9f1de0d6778dbea2.jpeg
+  example_title: Person
+datasets:
+- sayeed99/fashion_segmentation
+model-index:
+- name: segformer-b3-fashion
+  results: []
+pipeline_tag: image-segmentation
+---
+
+
+# segformer-b3-fashion
+
+This model is a fine-tuned version of [nvidia/mit-b3](https://huggingface.co/nvidia/mit-b3) on the sayeed99/fashion_segmentation dataset using original image sizes without resizing.
+
+
+```python
+from transformers import SegformerImageProcessor, AutoModelForSemanticSegmentation
+from PIL import Image
+import requests
+import matplotlib.pyplot as plt
+import torch.nn as nn
+
+processor = SegformerImageProcessor.from_pretrained("sayeed99/segformer-b3-fashion")
+model = AutoModelForSemanticSegmentation.from_pretrained("sayeed99/segformer-b3-fashion")
+
+url = "https://plus.unsplash.com/premium_photo-1673210886161-bfcc40f54d1f?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxzZWFyY2h8MXx8cGVyc29uJTIwc3RhbmRpbmd8ZW58MHx8MHx8&w=1000&q=80"
+
+image = Image.open(requests.get(url, stream=True).raw)
+inputs = processor(images=image, return_tensors="pt")
+
+outputs = model(**inputs)
+logits = outputs.logits.cpu()
+
+upsampled_logits = nn.functional.interpolate(
+    logits,
+    size=image.size[::-1],
+    mode="bilinear",
+    align_corners=False,
+)
+
+pred_seg = upsampled_logits.argmax(dim=1)[0]
+plt.imshow(pred_seg)
+```
+
+Labels : {"0":"Unlabelled", "1": "shirt, blouse", "2": "top, t-shirt, sweatshirt", "3": "sweater", "4": "cardigan", "5": "jacket", "6": "vest", "7": "pants", "8": "shorts", "9": "skirt", "10": "coat", "11": "dress", "12": "jumpsuit", "13": "cape", "14": "glasses", "15": "hat", "16": "headband, head covering, hair accessory", "17": "tie", "18": "glove", "19": "watch", "20": "belt", "21": "leg warmer", "22": "tights, stockings", "23": "sock", "24": "shoe", "25": "bag, wallet", "26": "scarf", "27": "umbrella", "28": "hood", "29": "collar", "30": "lapel", "31": "epaulette", "32": "sleeve", "33": "pocket", "34": "neckline", "35": "buckle", "36": "zipper", "37": "applique", "38": "bead", "39": "bow", "40": "flower", "41": "fringe", "42": "ribbon", "43": "rivet", "44": "ruffle", "45": "sequin", "46": "tassel"}
+
+### Framework versions
+
+- Transformers 4.30.0
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.13.3
+
+
+### License
+
+The license for this model can be found [here](https://github.com/NVlabs/SegFormer/blob/master/LICENSE).
+
+### BibTeX entry and citation info
+
+```bibtex
+@article{DBLP:journals/corr/abs-2105-15203,
+  author    = {Enze Xie and
+               Wenhai Wang and
+               Zhiding Yu and
+               Anima Anandkumar and
+               Jose M. Alvarez and
+               Ping Luo},
+  title     = {SegFormer: Simple and Efficient Design for Semantic Segmentation with
+               Transformers},
+  journal   = {CoRR},
+  volume    = {abs/2105.15203},
+  year      = {2021},
+  url       = {https://arxiv.org/abs/2105.15203},
+  eprinttype = {arXiv},
+  eprint    = {2105.15203},
+  timestamp = {Wed, 02 Jun 2021 11:46:42 +0200},
+  biburl    = {https://dblp.org/rec/journals/corr/abs-2105-15203.bib},
+  bibsource = {dblp computer science bibliography, https://dblp.org}
+}

models/segformer-b3-fashion/config.json

@@ -0,0 +1,168 @@
+{
+  "_name_or_path": "nvidia/mit-b3",
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 768,
+  "depths": [
+    3,
+    4,
+    18,
+    3
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    64,
+    128,
+    320,
+    512
+  ],
+  "id2label": {
+    "0": "unlabelled",
+    "1": "shirt, blouse",
+    "2": "top, t-shirt, sweatshirt",
+    "3": "sweater",
+    "4": "cardigan",
+    "5": "jacket",
+    "6": "vest",
+    "7": "pants",
+    "8": "shorts",
+    "9": "skirt",
+    "10": "coat",
+    "11": "dress",
+    "12": "jumpsuit",
+    "13": "cape",
+    "14": "glasses",
+    "15": "hat",
+    "16": "headband, head covering, hair accessory",
+    "17": "tie",
+    "18": "glove",
+    "19": "watch",
+    "20": "belt",
+    "21": "leg warmer",
+    "22": "tights, stockings",
+    "23": "sock",
+    "24": "shoe",
+    "25": "bag, wallet",
+    "26": "scarf",
+    "27": "umbrella",
+    "28": "hood",
+    "29": "collar",
+    "30": "lapel",
+    "31": "epaulette",
+    "32": "sleeve",
+    "33": "pocket",
+    "34": "neckline",
+    "35": "buckle",
+    "36": "zipper",
+    "37": "applique",
+    "38": "bead",
+    "39": "bow",
+    "40": "flower",
+    "41": "fringe",
+    "42": "ribbon",
+    "43": "rivet",
+    "44": "ruffle",
+    "45": "sequin",
+    "46": "tassel"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "applique": 37,
+    "bag, wallet": 25,
+    "bead": 38,
+    "belt": 20,
+    "bow": 39,
+    "buckle": 35,
+    "cape": 13,
+    "cardigan": 4,
+    "coat": 10,
+    "collar": 29,
+    "dress": 11,
+    "epaulette": 31,
+    "flower": 40,
+    "fringe": 41,
+    "glasses": 14,
+    "glove": 18,
+    "hat": 15,
+    "headband, head covering, hair accessory": 16,
+    "hood": 28,
+    "jacket": 5,
+    "jumpsuit": 12,
+    "lapel": 30,
+    "leg warmer": 21,
+    "neckline": 34,
+    "pants": 7,
+    "pocket": 33,
+    "ribbon": 42,
+    "rivet": 43,
+    "ruffle": 44,
+    "scarf": 26,
+    "sequin": 45,
+    "shirt, blouse": 1,
+    "shoe": 24,
+    "shorts": 8,
+    "skirt": 9,
+    "sleeve": 32,
+    "sock": 23,
+    "sweater": 3,
+    "tassel": 46,
+    "tie": 17,
+    "tights, stockings": 22,
+    "top, t-shirt, sweatshirt": 2,
+    "umbrella": 27,
+    "unlabelled": 0,
+    "vest": 6,
+    "watch": 19,
+    "zipper": 36
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 3,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "reshape_last_stage": true,
+  "semantic_loss_ignore_index": 255,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0"
+}

models/segformer-b3-fashion/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f5b30179f1480d329224d089f6d286580142c2b12846d08de814a48a81f42f
+size 189118204

models/segformer-b3-fashion/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "SegformerImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 512,
+    "width": 512
+  }
+}

models/segformer-b3-fashion/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5749e86e5efad5d9dbbf7c2e4b996d675548dc22f26b06c0f1b6fc2e8bc1e2
+size 189264154

models/segformer-b3-fashion/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f871f7bdbc3af72746e7b76beb628f6365db08040b58b3071238dca986de97ca
+size 4408

models/segformer_b2_clothes/.cache/huggingface/.gitignore

@@ -0,0 +1 @@
+*