xinyun/ComfyUI
1
0
Fork 0
mirror of https://git.datalinker.icu/comfyanonymous/ComfyUI synced 2025-12-09 22:14:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

Hunyuan refiner vae now works with tiled. (#9836)

Browse Source
This commit is contained in:
comfyanonymous 2025-09-12 16:46:46 -07:00 committed by GitHub
parent d7f40442f9
commit a3b04de700
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 15 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
comfy/ldm/hunyuan_video/vae_refiner.py
View File

@ -185,7 +185,6 @@ class Encoder(nn.Module):
self.regul = comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer()
def forward(self, x):
x = x.unsqueeze(2)
x = self.conv_in(x)
for stage in self.down:

21
comfy/sd.py
View File

@ -412,9 +412,12 @@ class VAE:
self.working_dtypes = [torch.bfloat16, torch.float32]
elif "decoder.conv_in.conv.weight" in sd and sd['decoder.conv_in.conv.weight'].shape[1] == 32:
ddconfig = {"block_out_channels": [128, 256, 512, 1024, 1024], "in_channels": 3, "out_channels": 3, "num_res_blocks": 2, "ffactor_spatial": 16, "ffactor_temporal": 4, "downsample_match_channel": True, "upsample_match_channel": True}
self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.conv.weight"].shape[1]
self.downscale_ratio = 16
self.upscale_ratio = 16
ddconfig['z_channels'] = sd["decoder.conv_in.conv.weight"].shape[1]
self.latent_channels = 64
self.upscale_ratio = (lambda a: max(0, a * 4 - 3), 16, 16)
self.upscale_index_formula = (4, 16, 16)
self.downscale_ratio = (lambda a: max(0, math.floor((a + 3) / 4)), 16, 16)
self.downscale_index_formula = (4, 16, 16)
self.latent_dim = 3
self.not_video = True
self.working_dtypes = [torch.float16, torch.bfloat16, torch.float32]
@ -684,8 +687,11 @@ class VAE:
self.throw_exception_if_invalid()
pixel_samples = self.vae_encode_crop_pixels(pixel_samples)
pixel_samples = pixel_samples.movedim(-1, 1)
if not self.not_video and self.latent_dim == 3 and pixel_samples.ndim < 5:
pixel_samples = pixel_samples.movedim(1, 0).unsqueeze(0)
if self.latent_dim == 3 and pixel_samples.ndim < 5:
if not self.not_video:
pixel_samples = pixel_samples.movedim(1, 0).unsqueeze(0)
else:
pixel_samples = pixel_samples.unsqueeze(2)
try:
memory_used = self.memory_used_encode(pixel_samples.shape, self.vae_dtype)
model_management.load_models_gpu([self.patcher], memory_required=memory_used, force_full_load=self.disable_offload)
@ -719,7 +725,10 @@ class VAE:
dims = self.latent_dim
pixel_samples = pixel_samples.movedim(-1, 1)
if dims == 3:
pixel_samples = pixel_samples.movedim(1, 0).unsqueeze(0)
if not self.not_video:
pixel_samples = pixel_samples.movedim(1, 0).unsqueeze(0)
else:
pixel_samples = pixel_samples.unsqueeze(2)
memory_used = self.memory_used_encode(pixel_samples.shape, self.vae_dtype) # TODO: calculate mem required for tile
model_management.load_models_gpu([self.patcher], memory_required=memory_used, force_full_load=self.disable_offload)