Fast previews for mochi.

Author: comfyanonymous

comfy/latent_formats.py

@@ -190,7 +190,21 @@ def __init__(self):
                                          0.9294154431013696, 1.3720942357788521, 0.881393668867029,
                                          0.9168315692124348, 0.9185249279345552, 0.9274757570805041]).view(1, self.latent_channels, 1, 1, 1)
 
-        self.latent_rgb_factors = None #TODO
+        self.latent_rgb_factors =[
+            [-0.0069, -0.0045,  0.0018],
+            [ 0.0154, -0.0692, -0.0274],
+            [ 0.0333,  0.0019,  0.0206],
+            [-0.1390,  0.0628,  0.1678],
+            [-0.0725,  0.0134, -0.1898],
+            [ 0.0074, -0.0270, -0.0209],
+            [-0.0176, -0.0277, -0.0221],
+            [ 0.5294,  0.5204,  0.3852],
+            [-0.0326, -0.0446, -0.0143],
+            [-0.0659,  0.0153, -0.0153],
+            [ 0.0185, -0.0217,  0.0014],
+            [-0.0396, -0.0495, -0.0281]
+        ]
+        self.latent_rgb_factors_bias = [-0.0940, -0.1418, -0.1453]
         self.taesd_decoder_name = None #TODO
 
     def process_in(self, latent):

latent_preview.py

@@ -47,7 +47,12 @@ def decode_latent_to_preview(self, x0):
         if self.latent_rgb_factors_bias is not None:
             self.latent_rgb_factors_bias = self.latent_rgb_factors_bias.to(dtype=x0.dtype, device=x0.device)
 
-        latent_image = torch.nn.functional.linear(x0[0].permute(1, 2, 0), self.latent_rgb_factors, bias=self.latent_rgb_factors_bias)
+        if x0.ndim == 5:
+            x0 = x0[0, :, 0]
+        else:
+            x0 = x0[0]
+
+        latent_image = torch.nn.functional.linear(x0.movedim(0, -1), self.latent_rgb_factors, bias=self.latent_rgb_factors_bias)
         # latent_image = x0[0].permute(1, 2, 0) @ self.latent_rgb_factors
 
         return preview_to_image(latent_image)