Delete tools/Fooocus/models

tools/Fooocus/models/configs/anything_v3.yaml

@@ -1,73 +0,0 @@
-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

tools/Fooocus/models/configs/v1-inference.yaml

@@ -1,70 +0,0 @@
-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

tools/Fooocus/models/configs/v1-inference_clip_skip_2.yaml

@@ -1,73 +0,0 @@
-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

tools/Fooocus/models/configs/v1-inference_clip_skip_2_fp16.yaml

@@ -1,74 +0,0 @@
-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

tools/Fooocus/models/configs/v1-inference_fp16.yaml

@@ -1,71 +0,0 @@
-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

tools/Fooocus/models/configs/v1-inpainting-inference.yaml

@@ -1,71 +0,0 @@
-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
-

tools/Fooocus/models/configs/v2-inference-v.yaml

@@ -1,68 +0,0 @@
-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"

tools/Fooocus/models/configs/v2-inference-v_fp32.yaml

@@ -1,68 +0,0 @@
-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"

tools/Fooocus/models/configs/v2-inference.yaml

@@ -1,67 +0,0 @@
-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"

tools/Fooocus/models/configs/v2-inference_fp32.yaml

@@ -1,67 +0,0 @@
-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"

tools/Fooocus/models/configs/v2-inpainting-inference.yaml

@@ -1,158 +0,0 @@
-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

tools/Fooocus/models/prompt_expansion/fooocus_expansion/config.json

@@ -1,40 +0,0 @@
-{
-  "_name_or_path": "gpt2",
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
-  "pad_token_id": 50256,
-  "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 1024,
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.23.0.dev0",
-  "use_cache": true,
-  "vocab_size": 50257
-}

tools/Fooocus/models/prompt_expansion/fooocus_expansion/positive.txt

@@ -1,642 +0,0 @@
-abundant
-accelerated
-accepted
-accepting
-acclaimed
-accomplished
-acknowledged
-activated
-adapted
-adjusted
-admirable
-adorable
-adorned
-advanced
-adventurous
-advocated
-aesthetic
-affirmed
-affluent
-agile
-aimed
-aligned
-alive
-altered
-amazing
-ambient
-amplified
-analytical
-animated
-appealing
-applauded
-appreciated
-ardent
-aromatic
-arranged
-arresting
-articulate
-artistic
-associated
-assured
-astonishing
-astounding
-atmosphere
-attempted
-attentive
-attractive
-authentic
-authoritative
-awarded
-awesome
-backed
-background
-baked
-balance
-balanced
-balancing
-beaten
-beautiful
-beloved
-beneficial
-benevolent
-best
-bestowed
-blazing
-blended
-blessed
-boosted
-borne
-brave
-breathtaking
-brewed
-bright
-brilliant
-brought
-built
-burning
-calm
-calmed
-candid
-caring
-carried
-catchy
-celebrated
-celestial
-certain
-championed
-changed
-charismatic
-charming
-chased
-cheered
-cheerful
-cherished
-chic
-chosen
-cinematic
-clad
-classic
-classy
-clear
-coached
-coherent
-collected
-color
-colorful
-colors
-colossal
-combined
-comforting
-commanding
-committed
-compassionate
-compatible
-complete
-complex
-complimentary
-composed
-composition
-comprehensive
-conceived
-conferred
-confident
-connected
-considerable
-considered
-consistent
-conspicuous
-constructed
-constructive
-contemplated
-contemporary
-content
-contrasted
-conveyed
-cooked
-cool
-coordinated
-coupled
-courageous
-coveted
-cozy
-created
-creative
-credited
-crisp
-critical
-cultivated
-cured
-curious
-current
-customized
-cute
-daring
-darling
-dazzling
-decorated
-decorative
-dedicated
-deep
-defended
-definitive
-delicate
-delightful
-delivered
-depicted
-designed
-desirable
-desired
-destined
-detail
-detailed
-determined
-developed
-devoted
-devout
-diligent
-direct
-directed
-discovered
-dispatched
-displayed
-distilled
-distinct
-distinctive
-distinguished
-diverse
-divine
-dramatic
-draped
-dreamed
-driven
-dynamic
-earnest
-eased
-ecstatic
-educated
-effective
-elaborate
-elegant
-elevated
-elite
-eminent
-emotional
-empowered
-empowering
-enchanted
-encouraged
-endorsed
-endowed
-enduring
-energetic
-engaging
-enhanced
-enigmatic
-enlightened
-enormous
-enticing
-envisioned
-epic
-esteemed
-eternal
-everlasting
-evolved
-exalted
-examining
-excellent
-exceptional
-exciting
-exclusive
-exemplary
-exotic
-expansive
-exposed
-expressive
-exquisite
-extended
-extraordinary
-extremely
-fabulous
-facilitated
-fair
-faithful
-famous
-fancy
-fantastic
-fascinating
-fashionable
-fashioned
-favorable
-favored
-fearless
-fermented
-fertile
-festive
-fiery
-fine
-finest
-firm
-fixed
-flaming
-flashing
-flashy
-flavored
-flawless
-flourishing
-flowing
-focus
-focused
-formal
-formed
-fortunate
-fostering
-frank
-fresh
-fried
-friendly
-fruitful
-fulfilled
-full
-futuristic
-generous
-gentle
-genuine
-gifted
-gigantic
-glamorous
-glorious
-glossy
-glowing
-gorgeous
-graceful
-gracious
-grand
-granted
-grateful
-great
-grilled
-grounded
-grown
-guarded
-guided
-hailed
-handsome
-healing
-healthy
-heartfelt
-heavenly
-heroic
-highly
-historic
-holistic
-holy
-honest
-honored
-hoped
-hopeful
-iconic
-ideal
-illuminated
-illuminating
-illumination
-illustrious
-imaginative
-imagined
-immense
-immortal
-imposing
-impressive
-improved
-incredible
-infinite
-informed
-ingenious
-innocent
-innovative
-insightful
-inspirational
-inspired
-inspiring
-instructed
-integrated
-intense
-intricate
-intriguing
-invaluable
-invented
-investigative
-invincible
-inviting
-irresistible
-joined
-joyful
-keen
-kindly
-kinetic
-knockout
-laced
-lasting
-lauded
-lavish
-legendary
-lifted
-light
-limited
-linked
-lively
-located
-logical
-loved
-lovely
-loving
-loyal
-lucid
-lucky
-lush
-luxurious
-luxury
-magic
-magical
-magnificent
-majestic
-marked
-marvelous
-massive
-matched
-matured
-meaningful
-memorable
-merged
-merry
-meticulous
-mindful
-miraculous
-modern
-modified
-monstrous
-monumental
-motivated
-motivational
-moved
-moving
-mystical
-mythical
-naive
-neat
-new
-nice
-nifty
-noble
-notable
-noteworthy
-novel
-nuanced
-offered
-open
-optimal
-optimistic
-orderly
-organized
-original
-originated
-outstanding
-overwhelming
-paired
-palpable
-passionate
-peaceful
-perfect
-perfected
-perpetual
-persistent
-phenomenal
-pious
-pivotal
-placed
-planned
-pleasant
-pleased
-pleasing
-plentiful
-plotted
-plush
-poetic
-poignant
-polished
-positive
-praised
-precious
-precise
-premier
-premium
-presented
-preserved
-prestigious
-pretty
-priceless
-prime
-pristine
-probing
-productive
-professional
-profound
-progressed
-progressive
-prominent
-promoted
-pronounced
-propelled
-proportional
-prosperous
-protected
-provided
-provocative
-pure
-pursued
-pushed
-quaint
-quality
-questioning
-quiet
-radiant
-rare
-rational
-real
-reborn
-reclaimed
-recognized
-recovered
-refined
-reflected
-refreshed
-refreshing
-related
-relaxed
-relentless
-reliable
-relieved
-remarkable
-renewed
-renowned
-representative
-rescued
-resilient
-respected
-respectful
-restored
-retrieved
-revealed
-revealing
-revered
-revived
-rewarded
-rich
-roasted
-robust
-romantic
-royal
-sacred
-salient
-satisfied
-satisfying
-saturated
-saved
-scenic
-scientific
-select
-sensational
-serious
-set
-shaped
-sharp
-shielded
-shining
-shiny
-shown
-significant
-silent
-sincere
-singular
-situated
-sleek
-slick
-smart
-snug
-solemn
-solid
-soothing
-sophisticated
-sought
-sparkling
-special
-spectacular
-sped
-spirited
-spiritual
-splendid
-spread
-stable
-steady
-still
-stimulated
-stimulating
-stirred
-straightforward
-striking
-strong
-structured
-stunning
-sturdy
-stylish
-sublime
-successful
-sunny
-superb
-superior
-supplied
-supported
-supportive
-supreme
-sure
-surreal
-sweet
-symbolic
-symmetry
-synchronized
-systematic
-tailored
-taking
-targeted
-taught
-tempting
-tender
-terrific
-thankful
-theatrical
-thought
-thoughtful
-thrilled
-thrilling
-thriving
-tidy
-timeless
-touching
-tough
-trained
-tranquil
-transformed
-translucent
-transparent
-transported
-tremendous
-trendy
-tried
-trim
-true
-trustworthy
-unbelievable
-unconditional
-uncovered
-unified
-unique
-united
-universal
-unmatched
-unparalleled
-upheld
-valiant
-valued
-varied
-very
-vibrant
-virtuous
-vivid
-warm
-wealthy
-whole
-winning
-wished
-witty
-wonderful
-worshipped
-worthy

tools/Fooocus/models/prompt_expansion/fooocus_expansion/special_tokens_map.json

@@ -1,5 +0,0 @@
-{
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
-}

tools/Fooocus/models/prompt_expansion/fooocus_expansion/tokenizer_config.json

@@ -1,10 +0,0 @@
-{
-  "add_prefix_space": false,
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 1024,
-  "name_or_path": "gpt2",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
-}