diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..eb9e19d7caf39a184e21e969b6ce663727cf9012 --- /dev/null +++ b/README.md @@ -0,0 +1,10 @@ +--- +title: SsrfunModels +emoji: 🔥 +colorFrom: green +colorTo: gray +sdk: static +pinned: false +--- + +Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference diff --git a/ckpt/AnythingV5_v5PrtRE.safetensors b/ckpt/AnythingV5_v5PrtRE.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd1689c6518c8193e8bcd6b9e15d4ecb8d5ff586 --- /dev/null +++ b/ckpt/AnythingV5_v5PrtRE.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f96a1a9ca9b3a3242a9ae95d19284f0d2da8d5282b42d2d974398bf7663a252 +size 2132626102 diff --git a/ckpt/aom3a3.safetensors b/ckpt/aom3a3.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e28fbb095fc355f1d70565fccbef8eea8ba26929 --- /dev/null +++ b/ckpt/aom3a3.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb4099ba9cd5e69ab526fca22a2e967f286f8512d9509b735c892fa6468767cf +size 2132626071 diff --git a/ckpt/majicmicRealistic_v5.safetensors b/ckpt/majicmicRealistic_v5.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb9a2f709eaf72e46dce8f1dc18d12c6972b35d3 --- /dev/null +++ b/ckpt/majicmicRealistic_v5.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c9f6dfcbd3b86e76ffdfc58253ee73f6c1b513238481dcd5d6a27b7ad3df0f +size 2400040290 diff --git a/controlnet/control_v11e_sd15_ip2p.yaml b/controlnet/control_v11e_sd15_ip2p.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11e_sd15_ip2p_fp16.safetensors b/controlnet/control_v11e_sd15_ip2p_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a614a3bb45cc624dc21837c1274da5deebfc32f5 --- /dev/null +++ b/controlnet/control_v11e_sd15_ip2p_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e7dbe52a73f66e701c1faa77b8a2cb0ee3abd721e1cae31123f5b299093435 +size 722601100 diff --git a/controlnet/control_v11e_sd15_shuffle.yaml b/controlnet/control_v11e_sd15_shuffle.yaml new file mode 100644 index 0000000000000000000000000000000000000000..862304b0090bf65984473c30ab0ebc30a4858400 --- /dev/null +++ b/controlnet/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/controlnet/control_v11e_sd15_shuffle_fp16.safetensors b/controlnet/control_v11e_sd15_shuffle_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..11a372bd23547e7cc49886026fec8098412781c8 --- /dev/null +++ b/controlnet/control_v11e_sd15_shuffle_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cc77ae071888abefd6e80bafce3d2574f9f6f8aac7ab205db98fb12a53c1132 +size 722601100 diff --git a/controlnet/control_v11f1e_sd15_tile.yaml b/controlnet/control_v11f1e_sd15_tile.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11f1e_sd15_tile_fp16.safetensors b/controlnet/control_v11f1e_sd15_tile_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b54ca49b5e7464f11f00f5ce67e7e9eccab083f6 --- /dev/null +++ b/controlnet/control_v11f1e_sd15_tile_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f31868eedb243a77932e3c63907a6ba0a2058b6d65b5c27b89ee1b7f618ea33 +size 722601104 diff --git a/controlnet/control_v11f1p_sd15_depth.yaml b/controlnet/control_v11f1p_sd15_depth.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11f1p_sd15_depth_fp16.safetensors b/controlnet/control_v11f1p_sd15_depth_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f182c98c72b2d2a0005c9f590038d27216160ddb --- /dev/null +++ b/controlnet/control_v11f1p_sd15_depth_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4a79aa52fb63f607cb9ff479ea5aa1923b6ceb21267bd14b69bd05d7b617be +size 722601100 diff --git a/controlnet/control_v11p_sd15_canny.yaml b/controlnet/control_v11p_sd15_canny.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11p_sd15_canny_fp16.safetensors b/controlnet/control_v11p_sd15_canny_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5f376f7c38b7748485d922ea77ac02caee3fb982 --- /dev/null +++ b/controlnet/control_v11p_sd15_canny_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8932b66e15aae835b3490dbf989f56c253104cee08a88bf21283762f557c9f10 +size 722601100 diff --git a/controlnet/control_v11p_sd15_inpaint.yaml b/controlnet/control_v11p_sd15_inpaint.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11p_sd15_inpaint_fp16.safetensors b/controlnet/control_v11p_sd15_inpaint_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc721fd8edfa9e6b7df2daed9bf1932f0d9bc320 --- /dev/null +++ b/controlnet/control_v11p_sd15_inpaint_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677a4fe351edecd40cd0d7cc210a8686b59d4e55207317f12319ef746a7a5a89 +size 722601100 diff --git a/controlnet/control_v11p_sd15_lineart.yaml b/controlnet/control_v11p_sd15_lineart.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11p_sd15_lineart_fp16.safetensors b/controlnet/control_v11p_sd15_lineart_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7affa7f156cbd231392e1a19d5bb45a7c127bfa6 --- /dev/null +++ b/controlnet/control_v11p_sd15_lineart_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10559106d1bb8196298b7a81565ede9279295d2b2df15165b9dbe189994def56 +size 722601100 diff --git a/controlnet/control_v11p_sd15_mlsd.yaml b/controlnet/control_v11p_sd15_mlsd.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11p_sd15_mlsd_fp16.safetensors b/controlnet/control_v11p_sd15_mlsd_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..64a8f1fb09783d5d83e04b52e61b031eae7479ea --- /dev/null +++ b/controlnet/control_v11p_sd15_mlsd_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d689682fcc9341581b788524ab813cda789acdbc16bdbecbd1b9d2221e119b7 +size 722601100 diff --git a/controlnet/control_v11p_sd15_normalbae.yaml b/controlnet/control_v11p_sd15_normalbae.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11p_sd15_normalbae_fp16.safetensors b/controlnet/control_v11p_sd15_normalbae_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f09b754ec6eeebe291fe9586cd8a8ffc1394df7 --- /dev/null +++ b/controlnet/control_v11p_sd15_normalbae_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79864bfc3a1df58ed35bd92fc8dd1e4d7b85cac424cc427b9049ddc7647cceec +size 722601100 diff --git a/controlnet/control_v11p_sd15_openpose.yaml b/controlnet/control_v11p_sd15_openpose.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11p_sd15_openpose_fp16.safetensors b/controlnet/control_v11p_sd15_openpose_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ec5a3b296ac5a2002e9dd8d69ff870ded494cd2b --- /dev/null +++ b/controlnet/control_v11p_sd15_openpose_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4003c1da17b0e4ba444e02140e1c0d83bb24b79e4dcfd613c3a554d38f0f89c7 +size 722601100 diff --git a/controlnet/control_v11p_sd15_scribble.yaml b/controlnet/control_v11p_sd15_scribble.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11p_sd15_scribble_fp16.safetensors b/controlnet/control_v11p_sd15_scribble_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3d62447a2fdbc308baf2eddb3375d199837f04b --- /dev/null +++ b/controlnet/control_v11p_sd15_scribble_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99edfd25b54c18c0ab19fba8c5618f741aac1f8c3101e7fa62cce925ad87ae68 +size 722601100 diff --git a/controlnet/control_v11p_sd15_seg.yaml b/controlnet/control_v11p_sd15_seg.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11p_sd15_seg_fp16.safetensors b/controlnet/control_v11p_sd15_seg_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..65c09abfbe53ab108c239044ae2d6364098ae07d --- /dev/null +++ b/controlnet/control_v11p_sd15_seg_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd4dd3df2da2f1f2b9dd00f4504cc0d98b20afb608e25f1789a95c0ccdba14a +size 722601100 diff --git a/controlnet/control_v11p_sd15_softedge.yaml b/controlnet/control_v11p_sd15_softedge.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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/controlnet/control_v11p_sd15_softedge_fp16.safetensors b/controlnet/control_v11p_sd15_softedge_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..976eb04e7aa2c0e5a722b9c2c4325c0a537c0dbe --- /dev/null +++ b/controlnet/control_v11p_sd15_softedge_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78fea5b4599fec2ecd7e3f14b171feb290b88200c95d569ec0ff59a19bc3478 +size 722601100 diff --git a/controlnet/control_v11p_sd15s2_lineart_anime.yaml b/controlnet/control_v11p_sd15s2_lineart_anime.yaml new file mode 100644 index 0000000000000000000000000000000000000000..fde1825577acd46dc90d8d7c6730e22be762fccb --- /dev/null +++ b/controlnet/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 diff --git a/controlnet/control_v11p_sd15s2_lineart_anime_fp16.safetensors b/controlnet/control_v11p_sd15s2_lineart_anime_fp16.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b54f7c2014edb5cba82766eb1f91ba14bf5c0046 --- /dev/null +++ b/controlnet/control_v11p_sd15s2_lineart_anime_fp16.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:067bf845109afdd1049bd9553d44faed1ad53691bd6b5ac9ee31c87466ef7c27 +size 722601100 diff --git a/embeddings/NovelAI-Embeddings b/embeddings/NovelAI-Embeddings new file mode 160000 index 0000000000000000000000000000000000000000..e926fe210c65f3f6f6fd47a7cc8881ae5eb1bc23 --- /dev/null +++ b/embeddings/NovelAI-Embeddings @@ -0,0 +1 @@ +Subproject commit e926fe210c65f3f6f6fd47a7cc8881ae5eb1bc23 diff --git a/embeddings/easy_negative.safetensors b/embeddings/easy_negative.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17452fae90299ad12781fe9c4163dedab3d376ed --- /dev/null +++ b/embeddings/easy_negative.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74b4e810b030f6b75fde959e2db678c268d07115b85356d3c0138ba5eb42340 +size 24655 diff --git a/embeddings/models.zip b/embeddings/models.zip new file mode 100644 index 0000000000000000000000000000000000000000..baf9baf0f443c06409289c5a43d54f7a54e169c2 --- /dev/null +++ b/embeddings/models.zip @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d13e68d15d3bdf29d83e1386be9573fc2b27da8576a7ff6ed22ad3b87b814312 +size 31760952 diff --git a/embeddings/stable-diffusion-embeddings b/embeddings/stable-diffusion-embeddings new file mode 160000 index 0000000000000000000000000000000000000000..01b3d47b18bb123b341a227e2c8d18f2cdbd3d02 --- /dev/null +++ b/embeddings/stable-diffusion-embeddings @@ -0,0 +1 @@ +Subproject commit 01b3d47b18bb123b341a227e2c8d18f2cdbd3d02 diff --git a/index.html b/index.html new file mode 100644 index 0000000000000000000000000000000000000000..58275de3b1c343a98420342baa076b9baaafa157 --- /dev/null +++ b/index.html @@ -0,0 +1,19 @@ + + +
+ + +You can modify this app directly by editing index.html in the Files and versions tab.
++ Also don't forget to check the + Spaces documentation. +
+