Model classification api

configs/controlnet/cldm_v15.yaml

@@ -0,0 +1,79 @@
+model:
+  target: cldm.cldm.ControlLDM
+  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"
+    control_key: "hint"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    only_mid_control: False
+
+    control_stage_config:
+      target: cldm.cldm.ControlNet
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        hint_channels: 3
+        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
+
+    unet_config:
+      target: cldm.cldm.ControlledUnetModel
+      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

configs/controlnet/cldm_v21.yaml

@@ -0,0 +1,85 @@
+model:
+  target: cldm.cldm.ControlLDM
+  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"
+    control_key: "hint"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+    only_mid_control: False
+
+    control_stage_config:
+      target: cldm.cldm.ControlNet
+      params:
+        use_checkpoint: True
+        image_size: 32 # unused
+        in_channels: 4
+        hint_channels: 3
+        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
+
+    unet_config:
+      target: cldm.cldm.ControlledUnetModel
+      params:
+        use_checkpoint: 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"

configs/stable-diffusion/sd_xl_base.yaml

@@ -0,0 +1,98 @@
+model:
+  target: sgm.models.diffusion.DiffusionEngine
+  params:
+    scale_factor: 0.13025
+    disable_first_stage_autocast: True
+
+    denoiser_config:
+      target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
+      params:
+        num_idx: 1000
+
+        weighting_config:
+          target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
+        scaling_config:
+          target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling
+        discretization_config:
+          target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
+
+    network_config:
+      target: sgm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        adm_in_channels: 2816
+        num_classes: sequential
+        use_checkpoint: True
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [4, 2]
+        num_res_blocks: 2
+        channel_mult: [1, 2, 4]
+        num_head_channels: 64
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: [1, 2, 10]  # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
+        context_dim: 2048
+        spatial_transformer_attn_type: softmax-xformers
+        legacy: False
+
+    conditioner_config:
+      target: sgm.modules.GeneralConditioner
+      params:
+        emb_models:
+          # crossattn cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenCLIPEmbedder
+            params:
+              layer: hidden
+              layer_idx: 11
+          # crossattn and vector cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
+            params:
+              arch: ViT-bigG-14
+              version: laion2b_s39b_b160k
+              freeze: True
+              layer: penultimate
+              always_return_pooled: True
+              legacy: False
+          # vector cond
+          - is_trainable: False
+            input_key: original_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: crop_coords_top_left
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: target_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+
+    first_stage_config:
+      target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
+      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

configs/stable-diffusion/sd_xl_inpaint.yaml

@@ -0,0 +1,98 @@
+model:
+  target: sgm.models.diffusion.DiffusionEngine
+  params:
+    scale_factor: 0.13025
+    disable_first_stage_autocast: True
+
+    denoiser_config:
+      target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
+      params:
+        num_idx: 1000
+
+        weighting_config:
+          target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
+        scaling_config:
+          target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling
+        discretization_config:
+          target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
+
+    network_config:
+      target: sgm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        adm_in_channels: 2816
+        num_classes: sequential
+        use_checkpoint: True
+        in_channels: 9
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [4, 2]
+        num_res_blocks: 2
+        channel_mult: [1, 2, 4]
+        num_head_channels: 64
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: [1, 2, 10]  # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
+        context_dim: 2048
+        spatial_transformer_attn_type: softmax-xformers
+        legacy: False
+
+    conditioner_config:
+      target: sgm.modules.GeneralConditioner
+      params:
+        emb_models:
+          # crossattn cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenCLIPEmbedder
+            params:
+              layer: hidden
+              layer_idx: 11
+          # crossattn and vector cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
+            params:
+              arch: ViT-bigG-14
+              version: laion2b_s39b_b160k
+              freeze: True
+              layer: penultimate
+              always_return_pooled: True
+              legacy: False
+          # vector cond
+          - is_trainable: False
+            input_key: original_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: crop_coords_top_left
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: target_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+
+    first_stage_config:
+      target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
+      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