Basic Genmo Mochi video model support.

To use:
"Load CLIP" node with t5xxl + type mochi
"Load Diffusion Model" node with the mochi dit file.
"Load VAE" with the mochi vae file.

EmptyMochiLatentVideo node for the latent.
euler + linear_quadratic in the KSampler node.
This commit is contained in:
comfyanonymous
2024-10-26 06:54:00 -04:00
parent c3ffbae067
commit 5cbb01bc2f
18 changed files with 1677 additions and 24 deletions

View File

@@ -175,3 +175,30 @@ class Flux(SD3):
def process_out(self, latent):
return (latent / self.scale_factor) + self.shift_factor
class Mochi(LatentFormat):
latent_channels = 12
def __init__(self):
self.scale_factor = 1.0
self.latents_mean = torch.tensor([-0.06730895953510081, -0.038011381506090416, -0.07477820912866141,
-0.05565264470995561, 0.012767231469026969, -0.04703542746246419,
0.043896967884726704, -0.09346305707025976, -0.09918314763016893,
-0.008729793427399178, -0.011931556316503654, -0.0321993391887285]).view(1, self.latent_channels, 1, 1, 1)
self.latents_std = torch.tensor([0.9263795028493863, 0.9248894543193766, 0.9393059390890617,
0.959253732819592, 0.8244560132752793, 0.917259975397747,
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.taesd_decoder_name = None #TODO
def process_in(self, latent):
latents_mean = self.latents_mean.to(latent.device, latent.dtype)
latents_std = self.latents_std.to(latent.device, latent.dtype)
return (latent - latents_mean) * self.scale_factor / latents_std
def process_out(self, latent):
latents_mean = self.latents_mean.to(latent.device, latent.dtype)
latents_std = self.latents_std.to(latent.device, latent.dtype)
return latent * latents_std / self.scale_factor + latents_mean