1 files changed, 44 insertions, 8 deletions
diff --git a/modules/sd_vae_taesd.py b/modules/sd_vae_taesd.py
index 5bf7c76e..808eb362 100644
--- a/modules/sd_vae_taesd.py
+++ b/modules/sd_vae_taesd.py
@@ -44,7 +44,17 @@ def decoder():
     )
 
 
-class TAESD(nn.Module):
+def encoder():
+    return nn.Sequential(
+        conv(3, 64), Block(64, 64),
+        conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64),
+        conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64),
+        conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64),
+        conv(64, 4),
+    )
+
+
+class TAESDDecoder(nn.Module):
     latent_magnitude = 3
     latent_shift = 0.5
 
@@ -55,21 +65,28 @@ class TAESD(nn.Module):
         self.decoder.load_state_dict(
             torch.load(decoder_path, map_location='cpu' if devices.device.type != 'cuda' else None))
 
-    @staticmethod
-    def unscale_latents(x):
-        """[0, 1] -> raw latents"""
-        return x.sub(TAESD.latent_shift).mul(2 * TAESD.latent_magnitude)
+
+class TAESDEncoder(nn.Module):
+    latent_magnitude = 3
+    latent_shift = 0.5
+
+    def __init__(self, encoder_path="taesd_encoder.pth"):
+        """Initialize pretrained TAESD on the given device from the given checkpoints."""
+        super().__init__()
+        self.encoder = encoder()
+        self.encoder.load_state_dict(
+            torch.load(encoder_path, map_location='cpu' if devices.device.type != 'cuda' else None))
 
 
 def download_model(model_path, model_url):
     if not os.path.exists(model_path):
         os.makedirs(os.path.dirname(model_path), exist_ok=True)
 
-        print(f'Downloading TAESD decoder to: {model_path}')
+        print(f'Downloading TAESD model to: {model_path}')
         torch.hub.download_url_to_file(model_url, model_path)
 
 
-def model():
+def decoder_model():
     model_name = "taesdxl_decoder.pth" if getattr(shared.sd_model, 'is_sdxl', False) else "taesd_decoder.pth"
     loaded_model = sd_vae_taesd_models.get(model_name)
 
@@ -78,7 +95,7 @@ def model():
         download_model(model_path, 'https://github.com/madebyollin/taesd/raw/main/' + model_name)
 
         if os.path.exists(model_path):
-            loaded_model = TAESD(model_path)
+            loaded_model = TAESDDecoder(model_path)
             loaded_model.eval()
             loaded_model.to(devices.device, devices.dtype)
             sd_vae_taesd_models[model_name] = loaded_model
@@ -86,3 +103,22 @@ def model():
             raise FileNotFoundError('TAESD model not found')
 
     return loaded_model.decoder
+
+
+def encoder_model():
+    model_name = "taesdxl_encoder.pth" if getattr(shared.sd_model, 'is_sdxl', False) else "taesd_encoder.pth"
+    loaded_model = sd_vae_taesd_models.get(model_name)
+
+    if loaded_model is None:
+        model_path = os.path.join(paths_internal.models_path, "VAE-taesd", model_name)
+        download_model(model_path, 'https://github.com/madebyollin/taesd/raw/main/' + model_name)
+
+        if os.path.exists(model_path):
+            loaded_model = TAESDEncoder(model_path)
+            loaded_model.eval()
+            loaded_model.to(devices.device, devices.dtype)
+            sd_vae_taesd_models[model_name] = loaded_model
+        else:
+            raise FileNotFoundError('TAESD model not found')
+
+    return loaded_model.encoder