Upload 28 files

Extra/Ip2p.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e7dbe52a73f66e701c1faa77b8a2cb0ee3abd721e1cae31123f5b299093435
+size 722601100

Extra/Ip2p.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

Extra/Shuffle.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc77ae071888abefd6e80bafce3d2574f9f6f8aac7ab205db98fb12a53c1132
+size 722601100

Extra/Shuffle.yaml

@@ -0,0 +1,80 @@
+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
+    global_average_pooling: True
+
+    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

Extra/Softedge.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e78fea5b4599fec2ecd7e3f14b171feb290b88200c95d569ec0ff59a19bc3478
+size 722601100

Extra/Softedge.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

Extra/T2-canny-v2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ec162813b3997a925d39dc546ff696c42f877fec55ef2e6afa3a4aa642018e
+size 308015219

Extra/T2-canny-v2.yaml

@@ -0,0 +1,9 @@
+model:
+  target: tencentarc.t21_adapter
+  params:
+    channels: [320, 640, 1280, 1280]
+    nums_rb: 2
+    ksize: 1
+    sk: true
+    cin: 64
+    use_conv: false

Extra/T2-canny.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb35d666889f622f7c499c5c11a8e94dabd9231029a13a5efd736364e76a987
+size 308013107

Extra/T2-canny.yaml

@@ -0,0 +1,9 @@
+model:
+  target: tencentarc.t21_adapter
+  params:
+    channels: [320, 640, 1280, 1280]
+    nums_rb: 2
+    ksize: 1
+    sk: true
+    cin: 64
+    use_conv: false

Extra/T2-depth-v2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec4a100ed622e8818c441a28d7bcef129fcd7bde5a3cd7ecc208ddc19cfc764
+size 309489779

Extra/T2-depth-v2.yaml

@@ -0,0 +1,9 @@
+model:
+  target: tencentarc.t21_adapter
+  params:
+    channels: [320, 640, 1280, 1280]
+    nums_rb: 2
+    ksize: 1
+    sk: true
+    cin: 192
+    use_conv: false

Extra/T2-depth.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6adc765d71cbd07567688a9320add25db9a0758eef2e3b6897cbca71e1cf9d36
+size 309487667

Extra/T2-depth.yaml

@@ -0,0 +1,9 @@
+model:
+  target: tencentarc.t21_adapter
+  params:
+    channels: [320, 640, 1280, 1280]
+    nums_rb: 2
+    ksize: 1
+    sk: true
+    cin: 192
+    use_conv: false

Extra/T2-keypose.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edca0cef5eb32feba66c8e0524d996204b87a19eace640d27826d04229d17d7e
+size 309487667

Extra/T2-keypose.yaml

@@ -0,0 +1,9 @@
+model:
+  target: tencentarc.t21_adapter
+  params:
+    channels: [320, 640, 1280, 1280]
+    nums_rb: 2
+    ksize: 1
+    sk: true
+    cin: 192
+    use_conv: false

Extra/T2-openpose.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d8027cbeae188dcae57b7475243b7dec20f2620c3c0fe7778319c56bf1ec6b
+size 309487667

Extra/T2-openpose.yaml

@@ -0,0 +1,9 @@
+model:
+  target: tencentarc.t21_adapter
+  params:
+    channels: [320, 640, 1280, 1280]
+    nums_rb: 2
+    ksize: 1
+    sk: true
+    cin: 192
+    use_conv: false

Extra/T2-seg.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01a17ecd473e3e375cea152c1e4135274f7113a495be35909b497d65b87713a
+size 309487667

Extra/T2-seg.yaml

@@ -0,0 +1,9 @@
+model:
+  target: tencentarc.t21_adapter
+  params:
+    channels: [320, 640, 1280, 1280]
+    nums_rb: 2
+    ksize: 1
+    sk: true
+    cin: 192
+    use_conv: false

Extra/T2-sketch-v2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8757c9e8ea0689b97257dc530172325b8215aa4e97df7c91c1a8d4e7265b894c
+size 308015219

Extra/T2-sketch-v2.yaml

@@ -0,0 +1,9 @@
+model:
+  target: tencentarc.t21_adapter
+  params:
+    channels: [320, 640, 1280, 1280]
+    nums_rb: 2
+    ksize: 1
+    sk: true
+    cin: 64
+    use_conv: false

Extra/T2-sketch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e006de134c9db86d1d44e6f13783e0846a78879afa3bd6f73feb3d7f6a5715b1
+size 308013107

Extra/T2-sketch.yaml

@@ -0,0 +1,9 @@
+model:
+  target: tencentarc.t21_adapter
+  params:
+    channels: [320, 640, 1280, 1280]
+    nums_rb: 2
+    ksize: 1
+    sk: true
+    cin: 64
+    use_conv: false

Extra/T2-zoedepth.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0acb308082f394df7732f2841767a2d19e17bf4c33f35c6296047d4850fe8450
+size 309489779

Extra/T2-zoedepth.yaml

@@ -0,0 +1,9 @@
+model:
+  target: tencentarc.t21_adapter
+  params:
+    channels: [320, 640, 1280, 1280]
+    nums_rb: 2
+    ksize: 1
+    sk: true
+    cin: 192
+    use_conv: false

Extra/Tile.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387ac74221099dcd163b3a76060d0fae441301e169646f186875f620b1287a8f
+size 722601100

Extra/Tile.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