InvokeAI 2.2.4.5__py3-none-any.whl

configs/stable-diffusion/v1-finetune.yaml

@@ -0,0 +1,110 @@
+model:
+  base_learning_rate: 5.0e-03
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: true   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    embedding_reg_weight: 0.0
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ["sculpture"]
+        per_image_tokens: false
+        num_vectors_per_token: 1
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 1
+    num_workers: 2
+    wrap: false
+    train:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: train
+        per_image_tokens: false
+        repeats: 100
+    validation:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: val
+        per_image_tokens: false
+        repeats: 10
+
+lightning:
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 500
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 500
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True
+    max_steps: 4000000
+#    max_steps: 4000
+

configs/stable-diffusion/v1-finetune_style.yaml

@@ -0,0 +1,103 @@
+model:
+  base_learning_rate: 5.0e-03
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: true   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    embedding_reg_weight: 0.0
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ["painting"]
+        per_image_tokens: false
+        num_vectors_per_token: 1
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # 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
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 2
+    num_workers: 16
+    wrap: false
+    train:
+      target: ldm.data.personalized_style.PersonalizedBase
+      params:
+        size: 512
+        set: train
+        per_image_tokens: false
+        repeats: 100
+    validation:
+      target: ldm.data.personalized_style.PersonalizedBase
+      params:
+        size: 512
+        set: val
+        per_image_tokens: false
+        repeats: 10
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 500
+        max_images: 8
+        increase_log_steps: False
+
+  trainer:
+    benchmark: True

configs/stable-diffusion/v1-inference.yaml

@@ -0,0 +1,79 @@
+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. ]
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ['sculpture']
+        per_image_tokens: false
+        num_vectors_per_token: 1
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.WeightedFrozenCLIPEmbedder

configs/stable-diffusion/v1-inpainting-inference.yaml

@@ -0,0 +1,79 @@
+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. ]
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ['sculpture']
+        per_image_tokens: false
+        num_vectors_per_token: 8
+        progressive_words: False
+
+    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.WeightedFrozenCLIPEmbedder

configs/stable-diffusion/v1-m1-finetune.yaml

@@ -0,0 +1,110 @@
+model:
+  base_learning_rate: 5.0e-03
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: image
+    cond_stage_key: caption
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: true   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    embedding_reg_weight: 0.0
+
+    personalization_config:
+      target: ldm.modules.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ['sculpture']
+        per_image_tokens: false
+        num_vectors_per_token: 6
+        progressive_words: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 1
+    num_workers: 2
+    wrap: false
+    train:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: train
+        per_image_tokens: false
+        repeats: 100
+    validation:
+      target: ldm.data.personalized.PersonalizedBase
+      params:
+        size: 512
+        set: val
+        per_image_tokens: false
+        repeats: 10
+
+lightning:
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 500
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 500
+        max_images: 5
+        increase_log_steps: False
+
+  trainer:
+    benchmark: False
+    max_steps: 6200
+#    max_steps: 4000
+

invokeai-2.2.4.5.data/data/configs/INITIAL_MODELS.yaml

@@ -0,0 +1,80 @@
+stable-diffusion-1.5:
+   description: The newest Stable Diffusion version 1.5 weight file (4.27 GB)
+   repo_id: runwayml/stable-diffusion-v1-5
+   config: v1-inference.yaml
+   file: v1-5-pruned-emaonly.ckpt
+   recommended: true
+   width: 512
+   height: 512
+inpainting-1.5:
+   description: RunwayML SD 1.5 model optimized for inpainting (4.27 GB)
+   repo_id: runwayml/stable-diffusion-inpainting
+   config: v1-inpainting-inference.yaml
+   file: sd-v1-5-inpainting.ckpt
+   recommended: True
+   width: 512
+   height: 512
+ft-mse-improved-autoencoder-840000:
+   description: StabilityAI improved autoencoder fine-tuned for human faces (recommended; 335 MB)
+   repo_id: stabilityai/sd-vae-ft-mse-original
+   config: VAE/default
+   file: vae-ft-mse-840000-ema-pruned.ckpt
+   recommended: True
+   width: 512
+   height: 512
+stable-diffusion-1.4:
+   description: The original Stable Diffusion version 1.4 weight file (4.27 GB)
+   repo_id: CompVis/stable-diffusion-v-1-4-original
+   config: v1-inference.yaml
+   file: sd-v1-4.ckpt
+   recommended: False
+   width: 512
+   height: 512
+waifu-diffusion-1.3:
+   description: Stable Diffusion 1.4 fine tuned on anime-styled images (4.27 GB)
+   repo_id: hakurei/waifu-diffusion-v1-3
+   config: v1-inference.yaml
+   file: model-epoch09-float32.ckpt
+   recommended: False
+   width: 512
+   height: 512
+trinart-2.0:
+   description: An SD model finetuned with ~40,000 assorted high resolution manga/anime-style pictures (2.13 GB)
+   repo_id: naclbit/trinart_stable_diffusion_v2
+   config: v1-inference.yaml
+   file: trinart2_step95000.ckpt
+   recommended: False
+   width: 512
+   height: 512
+trinart_characters-1.0:
+   description: An SD model finetuned with 19.2M anime/manga style images (2.13 GB)
+   repo_id: naclbit/trinart_characters_19.2m_stable_diffusion_v1
+   config: v1-inference.yaml
+   file: trinart_characters_it4_v1.ckpt
+   recommended: False
+   width: 512
+   height: 512
+trinart_vae:
+   description: Custom autoencoder for trinart_characters
+   repo_id: naclbit/trinart_characters_19.2m_stable_diffusion_v1
+   config: VAE/trinart
+   file: autoencoder_fix_kl-f8-trinart_characters.ckpt
+   recommended: False
+   width: 512
+   height: 512
+papercut-1.0:
+   description: SD 1.5 fine-tuned for papercut art (use "PaperCut" in your prompts) (2.13 GB)
+   repo_id: Fictiverse/Stable_Diffusion_PaperCut_Model
+   config: v1-inference.yaml
+   file: PaperCut_v1.ckpt
+   recommended: False
+   width: 512
+   height: 512
+voxel_art-1.0:
+   description: Stable Diffusion trained on voxel art (use "VoxelArt" in your prompts) (4.27 GB)
+   repo_id: Fictiverse/Stable_Diffusion_VoxelArt_Model
+   config: v1-inference.yaml
+   file: VoxelArt_v1.ckpt
+   recommended: False
+   width: 512
+   height: 512

invokeai-2.2.4.5.data/data/configs/models.yaml.example

@@ -0,0 +1,29 @@
+# This file describes the alternative machine learning models
+# available to InvokeAI script.
+#
+# To add a new model, follow the examples below. Each
+# model requires a model config file, a weights file,
+# and the width and height of the images it
+# was trained on.
+stable-diffusion-1.5:
+  description: The newest Stable Diffusion version 1.5 weight file (4.27 GB)
+  weights: models/ldm/stable-diffusion-v1/v1-5-pruned-emaonly.ckpt
+  config: configs/stable-diffusion/v1-inference.yaml
+  width: 512
+  height: 512
+  vae: ./models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  default: true
+stable-diffusion-1.4:
+  description: Stable Diffusion inference model version 1.4
+  config: configs/stable-diffusion/v1-inference.yaml
+  weights: models/ldm/stable-diffusion-v1/sd-v1-4.ckpt
+  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  width: 512
+  height: 512
+inpainting-1.5:
+  weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
+  config: configs/stable-diffusion/v1-inpainting-inference.yaml
+  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
+  description: RunwayML SD 1.5 model optimized for inpainting
+  width: 512
+  height: 512