298977887/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-01-25 15:55:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

A different way of handling multiple images passed to SVD.

Browse Source 
Previously when a list of 3 images [0, 1, 2] was used for a 6 frame video
they were concated like this:
[0, 1, 2, 0, 1, 2]

now they are concated like this:
[0, 0, 1, 1, 2, 2]
This commit is contained in:
comfyanonymous 2023-12-03 03:31:47 -05:00
parent b2517b4ceb
commit 61a123a1e0
2 changed files with 21 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/model_base.py
View File

@ -303,7 +303,7 @@ class SVD_img2vid(BaseModel):
if latent_image.shape[1:] != noise.shape[1:]:
latent_image = utils.common_upscale(latent_image, noise.shape[-1], noise.shape[-2], "bilinear", "center")
latent_image = utils.repeat_to_batch_size(latent_image, noise.shape[0])
latent_image = utils.resize_to_batch_size(latent_image, noise.shape[0])
out['c_concat'] = comfy.conds.CONDNoiseShape(latent_image)

20
comfy/utils.py
View File

@ -239,6 +239,26 @@ def repeat_to_batch_size(tensor, batch_size):
return tensor.repeat([math.ceil(batch_size / tensor.shape[0])] + [1] * (len(tensor.shape) - 1))[:batch_size]
return tensor
def resize_to_batch_size(tensor, batch_size):
in_batch_size = tensor.shape[0]
if in_batch_size == batch_size:
return tensor
if batch_size <= 1:
return tensor[:batch_size]
output = torch.empty([batch_size] + list(tensor.shape)[1:], dtype=tensor.dtype, device=tensor.device)
if batch_size < in_batch_size:
scale = (in_batch_size - 1) / (batch_size - 1)
for i in range(batch_size):
output[i] = tensor[min(round(i * scale), in_batch_size - 1)]
else:
scale = in_batch_size / batch_size
for i in range(batch_size):
output[i] = tensor[min(math.floor((i + 0.5) * scale), in_batch_size - 1)]
return output
def convert_sd_to(state_dict, dtype):
keys = list(state_dict.keys())
for k in keys: