Upload folder using huggingface_hub

.gitattributes

@@ -25,7 +25,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,3 @@
+This repository hosts pruned `.safetensors` modules of [ControlNet](https://huggingface.co/lllyasviel/ControlNet), by [lllyasviel](https://huggingface.co/lllyasviel) and [T2I-Adapters](https://huggingface.co/TencentARC/T2I-Adapter), [TencentARC Team](https://huggingface.co/TencentARC)
+
+The modules are meant for [this extension for AUTOMATIC1111/stable-diffusion-webui](https://github.com/Mikubill/sd-webui-controlnet), but should work for different webuis too if they have it implemented. cheers!🥂

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

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"

control_canny-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2549278df9a7b3d7a6058f6cedb0ccf2ff09118054a0f7e6940bd6bcfa98557
+size 722596338

control_depth-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a50531fa706fec36899d8499f228dcc917583b2de87e2f44f3374684b5c9c3
+size 722596338

control_hed-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19bdd6e721adfd3b5474121a62716193581cdf45b8c0b8b48a0cc1d167e1a42
+size 722596338

control_mlsd-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8513fa9c65046467ed1a575f5593ac3e05f4cdffc8f07bf5f3c075afe0ea3d9
+size 722596338

control_normal-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e778bc30b7278aef1126b685a7ad2a4a0de6a5d8a29172cb5c9aab90e465096
+size 722596338

control_openpose-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337a30c5636697704370bd2413b43cebf1937abcdccc96f3525018ad5c220702
+size 722596338

control_scribble-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b186c052c65a3281f5d0d2636f7d9ba4640b7697dc99ffa09cd9928236df13b6
+size 722596338

control_seg-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c735dccfafcacfc9a0d6c99783895ef8b70244b85170c4ac70f34077189f2e
+size 722596338

t2iadapter_canny-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a0b00467470d64d704500a680c10830b1d93c683c815cf766bec085b694fef
+size 154004748

t2iadapter_color-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b27503688b7a6f863c2e4e6d50b7ba57435a0ceb3b47efb8d8083112c7f64c
+size 37385998

t2iadapter_depth-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed1102f5cfd489371359b06bae3c50f5b2cd4e9b9fd26b2c91c1979af968959
+size 154742029

t2iadapter_keypose-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49038e6014f742f76c0ea16d1f8c533b9c5191a4d29bf5e8a696fcf7586292a3
+size 154742029

t2iadapter_openpose-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8f87894f65f5b8736de6aaed9db84be6640c0bad2d56867768c38016bfec1e
+size 154742029

t2iadapter_seg-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a34a8afd53e46a10235d2f375f45ccd1ef726ce36073e9c31385823c81690e92
+size 154742029

t2iadapter_sketch-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c2a337a568f107a6fa30bae3c8a84256ac301a5ddf5d6b2e53718f14ab549a
+size 154004748

t2iadapter_style-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fccd0af0e8889baa5e0042cb7ddfc48d8e5d243609d8a9a27c97635802e09b8
+size 77179015