content

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

control_sd15_canny.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de384b16bc2d7a1fb258ca0cbd941d7dd0a721ae996aff89f905299d6923f45
+size 5710753329

control_sd15_depth.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726cd0b472c4b5c0341b01afcb7fdc4a7b4ab7c37fe797fd394c9805cbef60bf
+size 5710753329

control_sd15_hed.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ad5ff2c3ce279332650d79f24a912ef8aa411382fcbde2a20e6239cce65d9c
+size 5710750165

control_sd15_mlsd.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4520b22400756ac96be61f900a59ab648ec487127beb7a095a708a4d3472b6eb
+size 5710751843

control_sd15_normal.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1188b9ac6754c9c846536f51bc5128fef8188ab287fc2c3d5768c3a05e31a0d0
+size 5710754879

control_sd15_openpose.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d19ffffeeaff6d9feb2204b234c3e1b9aec039ab3e63fca07f4fe5646f2ef591
+size 5710751843

control_sd15_scribble.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591bc5a70a167821634fc3d4870217d7501bd839615540d1cc158579390e9ad3
+size 5710757851

control_sd15_seg.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c772486812fdd5331a86ee7135f5146dab91f78e6676fab3ec94420708f3a37
+size 5710750165