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

@@ -13,9 +13,15 @@ try:
except:
rms_norm_torch = None
def rms_norm(x, weight, eps=1e-6):
def rms_norm(x, weight=None, eps=1e-6):
if rms_norm_torch is not None and not (torch.jit.is_tracing() or torch.jit.is_scripting()):
return rms_norm_torch(x, weight.shape, weight=comfy.ops.cast_to(weight, dtype=x.dtype, device=x.device), eps=eps)
if weight is None:
return rms_norm_torch(x, (x.shape[-1],), eps=eps)
else:
return rms_norm_torch(x, weight.shape, weight=comfy.ops.cast_to(weight, dtype=x.dtype, device=x.device), eps=eps)
else:
rrms = torch.rsqrt(torch.mean(x**2, dim=-1, keepdim=True) + eps)
return (x * rrms) * comfy.ops.cast_to(weight, dtype=x.dtype, device=x.device)
r = x * torch.rsqrt(torch.mean(x**2, dim=-1, keepdim=True) + eps)
if weight is None:
return r
else:
return r * comfy.ops.cast_to(weight, dtype=x.dtype, device=x.device)