298977887/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-03-13 14:21:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Don't resize clip vision image when the size is already good.

Browse Source
This commit is contained in:
comfyanonymous 2023-12-16 03:06:10 -05:00
parent 13e6d5366e
commit e45d920ae3
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
comfy/clip_vision.py
View File

@ -19,11 +19,13 @@ class Output:
def clip_preprocess(image, size=224):
mean = torch.tensor([ 0.48145466,0.4578275,0.40821073], device=image.device, dtype=image.dtype)
std = torch.tensor([0.26862954,0.26130258,0.27577711], device=image.device, dtype=image.dtype)
scale = (size / min(image.shape[1], image.shape[2]))
image = torch.nn.functional.interpolate(image.movedim(-1, 1), size=(round(scale * image.shape[1]), round(scale * image.shape[2])), mode="bicubic", antialias=True)
h = (image.shape[2] - size)//2
w = (image.shape[3] - size)//2
image = image[:,:,h:h+size,w:w+size]
image = image.movedim(-1, 1)
if not (image.shape[2] == size and image.shape[3] == size):
scale = (size / min(image.shape[2], image.shape[3]))
image = torch.nn.functional.interpolate(image, size=(round(scale * image.shape[2]), round(scale * image.shape[3])), mode="bicubic", antialias=True)
h = (image.shape[2] - size)//2
w = (image.shape[3] - size)//2
image = image[:,:,h:h+size,w:w+size]
image = torch.clip((255. * image), 0, 255).round() / 255.0
return (image - mean.view([3,1,1])) / std.view([3,1,1])