wupload

scottie-style/scottie-wd15-000001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5000c80513b3b9e78a8741be28f4a4c18825316b546e3131d2079e4b6b5e9a98
+size 13955908

scottie-style/scottie-wd15-000002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba997375356d2841ec353c2d8e5405df2f9636f6b5cdb42efb479012b8885cd8
+size 13955908

scottie-style/scottie-wd15-000003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:383d82ba56a64a0993ab435214d500a1921c57cc34b0cb251e7a4005a5b7c66e
+size 13955908

scottie-style/scottie-wd15-000004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e224600311b63d212cb30a7d4718f0fbb688c594f248cfc3e07574164a919f41
+size 13955908

scottie-style/scottie-wd15-000005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6482645515087baa7752e0378982c2ef42f36ea0d5823672f7d856f274f313
+size 13955908

scottie-style/scottie-wd15-000006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a307c98bc238292426fd1e59c75ca243e12db9d40a21dbffc1cf2ac6bfff5f6a
+size 13955907

scottie-style/scottie-wd15-000007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b70be5b39c22a2d943f5fbca814dd20e2ec551042e06b0c73b10a3c8a937c05
+size 13955908

scottie-style/scottie-wd15-000008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d31e6e92463ce38f2c1466caa9440789eadd7f443cebca0b9123ce89f2fa27
+size 13955908

scottie-style/scottie-wd15-000009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7cd96f1f5904fb02bdeeb8163cf087f572e447cae151f5501cd071a106f40d
+size 13955908

scottie-style/scottie-wd15.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098cb806c2d5305f031e7aa5ab71e6ca89ea8476a9448dbfa53e7f08ce1c984c
+size 13955909

scottie-style/scottie-wd15.yaml

@@ -0,0 +1,68 @@
+model:
+  base_learning_rate: 1.0e-4
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    parameterization: "v"
+    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"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False # we set this to false because this is an inference only config
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        use_fp16: 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"