From 5d3abf6e832ad8e5c047248da2c3d8d7e9c71693 Mon Sep 17 00:00:00 2001 From: ailab Date: Sat, 8 Jun 2024 05:37:18 +0800 Subject: [PATCH] first commit --- .gitattributes | 34 +++++++++++ README.md | 6 ++ control_v11e_sd15_ip2p.pth | 3 + control_v11e_sd15_ip2p.yaml | 79 +++++++++++++++++++++++++ control_v11e_sd15_shuffle.pth | 3 + control_v11e_sd15_shuffle.yaml | 80 ++++++++++++++++++++++++++ control_v11f1e_sd15_tile.pth | 3 + control_v11f1e_sd15_tile.yaml | 79 +++++++++++++++++++++++++ control_v11f1p_sd15_depth.pth | 3 + control_v11f1p_sd15_depth.yaml | 79 +++++++++++++++++++++++++ control_v11p_sd15_canny.pth | 3 + control_v11p_sd15_canny.yaml | 79 +++++++++++++++++++++++++ control_v11p_sd15_inpaint.pth | 3 + control_v11p_sd15_inpaint.yaml | 79 +++++++++++++++++++++++++ control_v11p_sd15_lineart.pth | 3 + control_v11p_sd15_lineart.yaml | 79 +++++++++++++++++++++++++ control_v11p_sd15_mlsd.pth | 3 + control_v11p_sd15_mlsd.yaml | 79 +++++++++++++++++++++++++ control_v11p_sd15_normalbae.pth | 3 + control_v11p_sd15_normalbae.yaml | 79 +++++++++++++++++++++++++ control_v11p_sd15_openpose.pth | 3 + control_v11p_sd15_openpose.yaml | 79 +++++++++++++++++++++++++ control_v11p_sd15_scribble.pth | 3 + control_v11p_sd15_scribble.yaml | 79 +++++++++++++++++++++++++ control_v11p_sd15_seg.pth | 3 + control_v11p_sd15_seg.yaml | 79 +++++++++++++++++++++++++ control_v11p_sd15_softedge.pth | 3 + control_v11p_sd15_softedge.yaml | 79 +++++++++++++++++++++++++ control_v11p_sd15s2_lineart_anime.pth | 3 + control_v11p_sd15s2_lineart_anime.yaml | 79 +++++++++++++++++++++++++ 30 files changed, 1189 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 control_v11e_sd15_ip2p.pth create mode 100644 control_v11e_sd15_ip2p.yaml create mode 100644 control_v11e_sd15_shuffle.pth create mode 100644 control_v11e_sd15_shuffle.yaml create mode 100644 control_v11f1e_sd15_tile.pth create mode 100644 control_v11f1e_sd15_tile.yaml create mode 100644 control_v11f1p_sd15_depth.pth create mode 100644 control_v11f1p_sd15_depth.yaml create mode 100644 control_v11p_sd15_canny.pth create mode 100644 control_v11p_sd15_canny.yaml create mode 100644 control_v11p_sd15_inpaint.pth create mode 100644 control_v11p_sd15_inpaint.yaml create mode 100644 control_v11p_sd15_lineart.pth create mode 100644 control_v11p_sd15_lineart.yaml create mode 100644 control_v11p_sd15_mlsd.pth create mode 100644 control_v11p_sd15_mlsd.yaml create mode 100644 control_v11p_sd15_normalbae.pth create mode 100644 control_v11p_sd15_normalbae.yaml create mode 100644 control_v11p_sd15_openpose.pth create mode 100644 control_v11p_sd15_openpose.yaml create mode 100644 control_v11p_sd15_scribble.pth create mode 100644 control_v11p_sd15_scribble.yaml create mode 100644 control_v11p_sd15_seg.pth create mode 100644 control_v11p_sd15_seg.yaml create mode 100644 control_v11p_sd15_softedge.pth create mode 100644 control_v11p_sd15_softedge.yaml create mode 100644 control_v11p_sd15s2_lineart_anime.pth create mode 100644 control_v11p_sd15s2_lineart_anime.yaml diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c7d9f33 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,34 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.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 +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5930e82 --- /dev/null +++ b/README.md @@ -0,0 +1,6 @@ +--- +license: openrail +--- + +This is the model files for [ControlNet 1.1](https://github.com/lllyasviel/ControlNet-v1-1-nightly). +This model card will be filled in a more detailed way after 1.1 is officially merged into ControlNet. diff --git a/control_v11e_sd15_ip2p.pth b/control_v11e_sd15_ip2p.pth new file mode 100644 index 0000000..b88b481 --- /dev/null +++ b/control_v11e_sd15_ip2p.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8d77429b111b25ffad4adb4c686a19c73c905d638dd8acb1e0b1d1da300192c +size 1445234339 diff --git a/control_v11e_sd15_ip2p.yaml b/control_v11e_sd15_ip2p.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11e_sd15_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 diff --git a/control_v11e_sd15_shuffle.pth b/control_v11e_sd15_shuffle.pth new file mode 100644 index 0000000..8c3655d --- /dev/null +++ b/control_v11e_sd15_shuffle.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657f632c35176c467e71c471b55b1a0e94ae1a49d739e1b705624f454e638e1d +size 1445235365 diff --git a/control_v11e_sd15_shuffle.yaml b/control_v11e_sd15_shuffle.yaml new file mode 100644 index 0000000..862304b --- /dev/null +++ b/control_v11e_sd15_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 diff --git a/control_v11f1e_sd15_tile.pth b/control_v11f1e_sd15_tile.pth new file mode 100644 index 0000000..f0c50ae --- /dev/null +++ b/control_v11f1e_sd15_tile.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aa69b8d391e72c2fced6a650268137dc0ed594cafe8a2c0f8b994799a21979b +size 1445235023 diff --git a/control_v11f1e_sd15_tile.yaml b/control_v11f1e_sd15_tile.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11f1e_sd15_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 diff --git a/control_v11f1p_sd15_depth.pth b/control_v11f1p_sd15_depth.pth new file mode 100644 index 0000000..e20ec5a --- /dev/null +++ b/control_v11f1p_sd15_depth.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:761077ffe369fe8cf16ae353f8226bd4ca29805b161052f82c0170c7b50f1d99 +size 1445235365 diff --git a/control_v11f1p_sd15_depth.yaml b/control_v11f1p_sd15_depth.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11f1p_sd15_depth.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 diff --git a/control_v11p_sd15_canny.pth b/control_v11p_sd15_canny.pth new file mode 100644 index 0000000..a397170 --- /dev/null +++ b/control_v11p_sd15_canny.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f99cfe4c70910e38e3fece9918a4979ed7d3dcf9b81cee293e1755363af5406a +size 1445234681 diff --git a/control_v11p_sd15_canny.yaml b/control_v11p_sd15_canny.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11p_sd15_canny.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 diff --git a/control_v11p_sd15_inpaint.pth b/control_v11p_sd15_inpaint.pth new file mode 100644 index 0000000..6edfc36 --- /dev/null +++ b/control_v11p_sd15_inpaint.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2a0ff91882a0fbacbded5edeca7babdb6d1bd8f770880a91c177bd44cd58633 +size 1445235365 diff --git a/control_v11p_sd15_inpaint.yaml b/control_v11p_sd15_inpaint.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11p_sd15_inpaint.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 diff --git a/control_v11p_sd15_lineart.pth b/control_v11p_sd15_lineart.pth new file mode 100644 index 0000000..36362b4 --- /dev/null +++ b/control_v11p_sd15_lineart.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb5fb912696830da948e5056b50adfa3fcc68ff760c43e4e7a8499853af43c61 +size 1445235365 diff --git a/control_v11p_sd15_lineart.yaml b/control_v11p_sd15_lineart.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11p_sd15_lineart.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 diff --git a/control_v11p_sd15_mlsd.pth b/control_v11p_sd15_mlsd.pth new file mode 100644 index 0000000..403300e --- /dev/null +++ b/control_v11p_sd15_mlsd.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22dab177f4c4566ac1c8f68dc2c429b023114e15a644e8c7c0e8f956afe92acf +size 1445234339 diff --git a/control_v11p_sd15_mlsd.yaml b/control_v11p_sd15_mlsd.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11p_sd15_mlsd.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 diff --git a/control_v11p_sd15_normalbae.pth b/control_v11p_sd15_normalbae.pth new file mode 100644 index 0000000..d57f40e --- /dev/null +++ b/control_v11p_sd15_normalbae.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9608158c204261259f4b5a7815ced8f5c15e5de4e30a9403d07f68f29f81e941 +size 1445236049 diff --git a/control_v11p_sd15_normalbae.yaml b/control_v11p_sd15_normalbae.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11p_sd15_normalbae.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 diff --git a/control_v11p_sd15_openpose.pth b/control_v11p_sd15_openpose.pth new file mode 100644 index 0000000..56b8d5b --- /dev/null +++ b/control_v11p_sd15_openpose.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db97becd92cd19aff71352a60e93c2508decba3dee64f01f686727b9b406a9dd +size 1445235707 diff --git a/control_v11p_sd15_openpose.yaml b/control_v11p_sd15_openpose.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11p_sd15_openpose.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 diff --git a/control_v11p_sd15_scribble.pth b/control_v11p_sd15_scribble.pth new file mode 100644 index 0000000..3959453 --- /dev/null +++ b/control_v11p_sd15_scribble.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d33e8bc14ba679595d976789e4eedc36a3d2d21866ab5896355a7e6677749f +size 1445235707 diff --git a/control_v11p_sd15_scribble.yaml b/control_v11p_sd15_scribble.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11p_sd15_scribble.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 diff --git a/control_v11p_sd15_seg.pth b/control_v11p_sd15_seg.pth new file mode 100644 index 0000000..faec95d --- /dev/null +++ b/control_v11p_sd15_seg.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad6d753886c0edc978e79dfb06083737ab1bd9702e5b7c0f81b1e16a5ed12cc +size 1445233933 diff --git a/control_v11p_sd15_seg.yaml b/control_v11p_sd15_seg.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11p_sd15_seg.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 diff --git a/control_v11p_sd15_softedge.pth b/control_v11p_sd15_softedge.pth new file mode 100644 index 0000000..65f19b2 --- /dev/null +++ b/control_v11p_sd15_softedge.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20759ef71a109c4796e637d86eea8db492ec9772b6d5cb7a9afd077847b403f3 +size 1445235707 diff --git a/control_v11p_sd15_softedge.yaml b/control_v11p_sd15_softedge.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11p_sd15_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 diff --git a/control_v11p_sd15s2_lineart_anime.pth b/control_v11p_sd15s2_lineart_anime.pth new file mode 100644 index 0000000..227a215 --- /dev/null +++ b/control_v11p_sd15s2_lineart_anime.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59169ab86e8ae15ad50208cc5832f1cc598b95391d4482ba742b344c8f7f6904 +size 1445238101 diff --git a/control_v11p_sd15s2_lineart_anime.yaml b/control_v11p_sd15s2_lineart_anime.yaml new file mode 100644 index 0000000..fde1825 --- /dev/null +++ b/control_v11p_sd15s2_lineart_anime.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